144 files changed, 1608 insertions, 999 deletions
diff --git a/Documentation/filesystems/ntfs.txt b/Documentation/filesystems/ntfs.txt
index 614de3124901..251168587899 100644
--- a/Documentation/filesystems/ntfs.txt
+++ b/Documentation/filesystems/ntfs.txt
@@ -457,6 +457,12 @@ ChangeLog
 Note, a technical ChangeLog aimed at kernel hackers is in fs/ntfs/ChangeLog.
+2.1.26:
+        - Implement support for sector sizes above 512 bytes (up to the maximum
+          supported by NTFS which is 4096 bytes).
+        - Enhance support for NTFS volumes which were supported by Windows but
+          not by Linux due to invalid attribute list attribute flags.
+        - A few minor updates and bug fixes.
 2.1.25:
        - Write support is now extended with write(2) being able to both
          overwrite existing file data and to extend files.  Also, if a write
diff --git a/Documentation/filesystems/tmpfs.txt b/Documentation/filesystems/tmpfs.txt
index 8a155418c705..1773106976a2 100644
--- a/Documentation/filesystems/tmpfs.txt
+++ b/Documentation/filesystems/tmpfs.txt
@@ -92,6 +92,15 @@ NodeList format is a comma-separated list of decimal numbers and ranges,
 a range being two hyphen-separated decimal numbers, the smallest and
 largest node numbers in the range.  For example, mpol=bind:0-3,5,7,9-15
+Note that trying to mount a tmpfs with an mpol option will fail if the
+running kernel does not support NUMA; and will fail if its nodelist
+specifies a node >= MAX_NUMNODES.  If your system relies on that tmpfs
+being mounted, but from time to time runs a kernel built without NUMA
+capability (perhaps a safe recovery kernel), or configured to support
+fewer nodes, then it is advisable to omit the mpol option from automatic
+mount options.  It can be added later, when the tmpfs is already mounted
+on MountPoint, by 'mount -o remount,mpol=Policy:NodeList MountPoint'.
 To specify the initial root directory you can use the following mount
 options:
diff --git a/Documentation/x86_64/boot-options.txt b/Documentation/x86_64/boot-options.txt
index 153740f460a6..1921353259ae 100644
--- a/Documentation/x86_64/boot-options.txt
+++ b/Documentation/x86_64/boot-options.txt
@@ -52,6 +52,10 @@ APICs
                 apicmaintimer. Useful when your PIT timer is totally
                 broken.
+   disable_8254_timer / enable_8254_timer
+                 Enable interrupt 0 timer routing over the 8254 in addition to over
+                 the IO-APIC. The kernel tries to set a sensible default.
 Early Console
   syntax: earlyprintk=vga
diff --git a/Makefile b/Makefile
index 77a448c8e776..46eea76bc570 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 2
 PATCHLEVEL = 6
 SUBLEVEL = 16
-EXTRAVERSION =-rc4
+EXTRAVERSION =-rc5
 NAME=Sliding Snow Leopard
 # *DOCUMENTATION*
diff --git a/arch/arm/mach-at91rm9200/gpio.c b/arch/arm/mach-at91rm9200/gpio.c
index a9f718bf8ba8..0e396feec468 100644
--- a/arch/arm/mach-at91rm9200/gpio.c
+++ b/arch/arm/mach-at91rm9200/gpio.c
@@ -274,8 +274,18 @@ static void gpio_irq_handler(unsigned irq, struct irqdesc *desc, struct pt_regs
                gpio = &irq_desc[pin];
                while (isr) {
-                        if (isr & 1)
+                        if (isr & 1) {
-                                gpio->handle(pin, gpio, regs);
+                                if (unlikely(gpio->disable_depth)) {
+                                        /*
+                                         * The core ARM interrupt handler lazily disables IRQs so
+                                         * another IRQ must be generated before it actually gets
+                                         * here to be disabled on the GPIO controller.
+                                         */
+                                        gpio_irq_mask(pin);
+                                }
+                                else
+                                        gpio->handle(pin, gpio, regs);
+                        }
                        pin++;
                        gpio++;
                        isr >>= 1;
diff --git a/arch/i386/Kconfig b/arch/i386/Kconfig
index 0afec8566e7b..5b1a7d46d1d9 100644
--- a/arch/i386/Kconfig
+++ b/arch/i386/Kconfig
@@ -733,7 +733,7 @@ config PHYSICAL_START
 config HOTPLUG_CPU
        bool "Support for hot-pluggable CPUs (EXPERIMENTAL)"
-        depends on SMP && HOTPLUG && EXPERIMENTAL
+        depends on SMP && HOTPLUG && EXPERIMENTAL && !X86_VOYAGER
        ---help---
          Say Y here to experiment with turning CPUs off and on.  CPUs
          can be controlled through /sys/devices/system/cpu.
@@ -1060,6 +1060,7 @@ source "arch/i386/oprofile/Kconfig"
 config KPROBES
        bool "Kprobes (EXPERIMENTAL)"
+        depends on EXPERIMENTAL && MODULES
        help
          Kprobes allows you to trap at almost any kernel address and
          execute a callback function.  register_kprobe() establishes
diff --git a/arch/i386/kernel/Makefile b/arch/i386/kernel/Makefile
index 60c3f76dfca4..53bb9a79e274 100644
--- a/arch/i386/kernel/Makefile
+++ b/arch/i386/kernel/Makefile
@@ -7,7 +7,7 @@ extra-y := head.o init_task.o vmlinux.lds
 obj-y   := process.o semaphore.o signal.o entry.o traps.o irq.o \
                ptrace.o time.o ioport.o ldt.o setup.o i8259.o sys_i386.o \
                pci-dma.o i386_ksyms.o i387.o dmi_scan.o bootflag.o \
-                quirks.o i8237.o
+                quirks.o i8237.o topology.o
 obj-y                           += cpu/
 obj-y                           += timers/
diff --git a/arch/i386/kernel/cpu/common.c b/arch/i386/kernel/cpu/common.c
index 7eb9213734a3..4ecd4b326ded 100644
--- a/arch/i386/kernel/cpu/common.c
+++ b/arch/i386/kernel/cpu/common.c
@@ -4,6 +4,7 @@
 #include <linux/smp.h>
 #include <linux/module.h>
 #include <linux/percpu.h>
+#include <linux/bootmem.h>
 #include <asm/semaphore.h>
 #include <asm/processor.h>
 #include <asm/i387.h>
@@ -18,6 +19,9 @@
 #include "cpu.h"
+DEFINE_PER_CPU(struct Xgt_desc_struct, cpu_gdt_descr);
+EXPORT_PER_CPU_SYMBOL(cpu_gdt_descr);
 DEFINE_PER_CPU(unsigned char, cpu_16bit_stack[CPU_16BIT_STACK_SIZE]);
 EXPORT_PER_CPU_SYMBOL(cpu_16bit_stack);
@@ -571,8 +575,9 @@ void __devinit cpu_init(void)
        int cpu = smp_processor_id();
        struct tss_struct * t = &per_cpu(init_tss, cpu);
        struct thread_struct *thread = &current->thread;
-        struct desc_struct *gdt = get_cpu_gdt_table(cpu);
+        struct desc_struct *gdt;
        __u32 stk16_off = (__u32)&per_cpu(cpu_16bit_stack, cpu);
+        struct Xgt_desc_struct *cpu_gdt_descr = &per_cpu(cpu_gdt_descr, cpu);
        if (cpu_test_and_set(cpu, cpu_initialized)) {
                printk(KERN_WARNING "CPU#%d already initialized!\n", cpu);
@@ -590,6 +595,25 @@ void __devinit cpu_init(void)
        }
        /*
+         * This is a horrible hack to allocate the GDT.  The problem
+         * is that cpu_init() is called really early for the boot CPU
+         * (and hence needs bootmem) but much later for the secondary
+         * CPUs, when bootmem will have gone away
+         */
+        if (NODE_DATA(0)->bdata->node_bootmem_map) {
+                gdt = (struct desc_struct *)alloc_bootmem_pages(PAGE_SIZE);
+                /* alloc_bootmem_pages panics on failure, so no check */
+                memset(gdt, 0, PAGE_SIZE);
+        } else {
+                gdt = (struct desc_struct *)get_zeroed_page(GFP_KERNEL);
+                if (unlikely(!gdt)) {
+                        printk(KERN_CRIT "CPU%d failed to allocate GDT\n", cpu);
+                        for (;;)
+                                local_irq_enable();
+                }
+        }
+        /*
         * Initialize the per-CPU GDT with the boot GDT,
         * and set up the GDT descriptor:
         */
@@ -601,10 +625,10 @@ void __devinit cpu_init(void)
                ((((__u64)stk16_off) << 32) & 0xff00000000000000ULL) |
                (CPU_16BIT_STACK_SIZE - 1);
-        cpu_gdt_descr[cpu].size = GDT_SIZE - 1;
+        cpu_gdt_descr->size = GDT_SIZE - 1;
-        cpu_gdt_descr[cpu].address = (unsigned long)gdt;
+        cpu_gdt_descr->address = (unsigned long)gdt;
-        load_gdt(&cpu_gdt_descr[cpu]);
+        load_gdt(cpu_gdt_descr);
        load_idt(&idt_descr);
        /*
diff --git a/arch/i386/kernel/efi.c b/arch/i386/kernel/efi.c
index ecad519fd395..e3e42fd62401 100644
--- a/arch/i386/kernel/efi.c
+++ b/arch/i386/kernel/efi.c
@@ -103,17 +103,19 @@ static void efi_call_phys_prelog(void)
         */
        local_flush_tlb();
-        cpu_gdt_descr[0].address = __pa(cpu_gdt_descr[0].address);
+        per_cpu(cpu_gdt_descr, 0).address =
-        load_gdt((struct Xgt_desc_struct *) __pa(&cpu_gdt_descr[0]));
+                                 __pa(per_cpu(cpu_gdt_descr, 0).address);
+        load_gdt((struct Xgt_desc_struct *)__pa(&per_cpu(cpu_gdt_descr, 0)));
 }
 static void efi_call_phys_epilog(void)
 {
        unsigned long cr4;
-        cpu_gdt_descr[0].address =
+        per_cpu(cpu_gdt_descr, 0).address =
-                (unsigned long) __va(cpu_gdt_descr[0].address);
+                        (unsigned long)__va(per_cpu(cpu_gdt_descr, 0).address);
-        load_gdt(&cpu_gdt_descr[0]);
+        load_gdt((struct Xgt_desc_struct *)__va(&per_cpu(cpu_gdt_descr, 0)));
        cr4 = read_cr4();
        if (cr4 & X86_CR4_PSE) {
diff --git a/arch/i386/kernel/head.S b/arch/i386/kernel/head.S
index 2bee6499edd9..e0b7c632efbc 100644
--- a/arch/i386/kernel/head.S
+++ b/arch/i386/kernel/head.S
@@ -534,5 +534,3 @@ ENTRY(cpu_gdt_table)
        .quad 0x0000000000000000        /* 0xf0 - unused */
        .quad 0x0000000000000000        /* 0xf8 - GDT entry 31: double-fault TSS */
-        /* Be sure this is zeroed to avoid false validations in Xen */
-        .fill PAGE_SIZE_asm / 8 - GDT_ENTRIES,8,0
diff --git a/arch/i386/kernel/i386_ksyms.c b/arch/i386/kernel/i386_ksyms.c
index 3999bec50c33..055325056a74 100644
--- a/arch/i386/kernel/i386_ksyms.c
+++ b/arch/i386/kernel/i386_ksyms.c
@@ -3,8 +3,6 @@
 #include <asm/checksum.h>
 #include <asm/desc.h>
-EXPORT_SYMBOL_GPL(cpu_gdt_descr);
 EXPORT_SYMBOL(__down_failed);
 EXPORT_SYMBOL(__down_failed_interruptible);
 EXPORT_SYMBOL(__down_failed_trylock);
diff --git a/arch/i386/kernel/io_apic.c b/arch/i386/kernel/io_apic.c
index f2dd218d88cb..235822b3f41b 100644
--- a/arch/i386/kernel/io_apic.c
+++ b/arch/i386/kernel/io_apic.c
@@ -2566,8 +2566,10 @@ int __init io_apic_get_unique_id (int ioapic, int apic_id)
                spin_unlock_irqrestore(&ioapic_lock, flags);
                /* Sanity check */
-                if (reg_00.bits.ID != apic_id)
+                if (reg_00.bits.ID != apic_id) {
-                        panic("IOAPIC[%d]: Unable change apic_id!\n", ioapic);
+                        printk("IOAPIC[%d]: Unable to change apic_id!\n", ioapic);
+                        return -1;
+                }
        }
        apic_printk(APIC_VERBOSE, KERN_INFO
diff --git a/arch/i386/kernel/kprobes.c b/arch/i386/kernel/kprobes.c
index 6483eeb1a4e8..694a13997637 100644
--- a/arch/i386/kernel/kprobes.c
+++ b/arch/i386/kernel/kprobes.c
@@ -58,6 +58,11 @@ static inline int is_IF_modifier(kprobe_opcode_t opcode)
 int __kprobes arch_prepare_kprobe(struct kprobe *p)
 {
+        /* insn: must be on special executable page on i386. */
+        p->ainsn.insn = get_insn_slot();
+        if (!p->ainsn.insn)
+                return -ENOMEM;
        memcpy(p->ainsn.insn, p->addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t));
        p->opcode = *p->addr;
        return 0;
@@ -77,6 +82,13 @@ void __kprobes arch_disarm_kprobe(struct kprobe *p)
                           (unsigned long) p->addr + sizeof(kprobe_opcode_t));
 }
+void __kprobes arch_remove_kprobe(struct kprobe *p)
+{
+        down(&kprobe_mutex);
+        free_insn_slot(p->ainsn.insn);
+        up(&kprobe_mutex);
+}
 static inline void save_previous_kprobe(struct kprobe_ctlblk *kcb)
 {
        kcb->prev_kprobe.kp = kprobe_running();
@@ -111,7 +123,7 @@ static inline void prepare_singlestep(struct kprobe *p, struct pt_regs *regs)
        if (p->opcode == BREAKPOINT_INSTRUCTION)
                regs->eip = (unsigned long)p->addr;
        else
-                regs->eip = (unsigned long)&p->ainsn.insn;
+                regs->eip = (unsigned long)p->ainsn.insn;
 }
 /* Called with kretprobe_lock held */
@@ -351,7 +363,7 @@ static void __kprobes resume_execution(struct kprobe *p,
 {
        unsigned long *tos = (unsigned long *)&regs->esp;
        unsigned long next_eip = 0;
-        unsigned long copy_eip = (unsigned long)&p->ainsn.insn;
+        unsigned long copy_eip = (unsigned long)p->ainsn.insn;
        unsigned long orig_eip = (unsigned long)p->addr;
        switch (p->ainsn.insn[0]) {
diff --git a/arch/i386/kernel/mpparse.c b/arch/i386/kernel/mpparse.c
index e7609abf3796..e6e2f43db85e 100644
--- a/arch/i386/kernel/mpparse.c
+++ b/arch/i386/kernel/mpparse.c
@@ -915,6 +915,7 @@ void __init mp_register_ioapic (
        u32                     gsi_base)
 {
        int                     idx = 0;
+        int                     tmpid;
        if (nr_ioapics >= MAX_IO_APICS) {
                printk(KERN_ERR "ERROR: Max # of I/O APICs (%d) exceeded "
@@ -935,9 +936,14 @@ void __init mp_register_ioapic (
        set_fixmap_nocache(FIX_IO_APIC_BASE_0 + idx, address);
        if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) && (boot_cpu_data.x86 < 15))
-                mp_ioapics[idx].mpc_apicid = io_apic_get_unique_id(idx, id);
+                tmpid = io_apic_get_unique_id(idx, id);
        else
-                mp_ioapics[idx].mpc_apicid = id;
+                tmpid = id;
+        if (tmpid == -1) {
+                nr_ioapics--;
+                return;
+        }
+        mp_ioapics[idx].mpc_apicid = tmpid;
        mp_ioapics[idx].mpc_apicver = io_apic_get_version(idx);
        
        /* 
diff --git a/arch/i386/kernel/smpboot.c b/arch/i386/kernel/smpboot.c
index fb00ab7b7612..eba7f53f8b4a 100644
--- a/arch/i386/kernel/smpboot.c
+++ b/arch/i386/kernel/smpboot.c
@@ -898,12 +898,6 @@ static int __devinit do_boot_cpu(int apicid, int cpu)
        unsigned long start_eip;
        unsigned short nmi_high = 0, nmi_low = 0;
-        if (!cpu_gdt_descr[cpu].address &&
-            !(cpu_gdt_descr[cpu].address = get_zeroed_page(GFP_KERNEL))) {
-                printk("Failed to allocate GDT for CPU %d\n", cpu);
-                return 1;
-        }
        ++cpucount;
        /*
diff --git a/arch/i386/mach-default/topology.c b/arch/i386/kernel/topology.c
index b64314069e78..67a0e1baa28b 100644
--- a/arch/i386/mach-default/topology.c
+++ b/arch/i386/kernel/topology.c
@@ -1,12 +1,12 @@
 /*
- * arch/i386/mach-generic/topology.c - Populate driverfs with topology information
+ * arch/i386/kernel/topology.c - Populate driverfs with topology information
 *
 * Written by: Matthew Dobson, IBM Corporation
 * Original Code: Paul Dorwin, IBM Corporation, Patrick Mochel, OSDL
 *
 * Copyright (C) 2002, IBM Corp.
 *
- * All rights reserved.          
+ * 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 as published by
@@ -34,7 +34,7 @@ static struct i386_cpu cpu_devices[NR_CPUS];
 int arch_register_cpu(int num){
        struct node *parent = NULL;
-        
 #ifdef CONFIG_NUMA
        int node = cpu_to_node(num);
        if (node_online(node))
diff --git a/arch/i386/mach-default/Makefile b/arch/i386/mach-default/Makefile
index e95bb0237921..012fe34459e6 100644
--- a/arch/i386/mach-default/Makefile
+++ b/arch/i386/mach-default/Makefile
@@ -2,4 +2,4 @@
 # Makefile for the linux kernel.
 #
-obj-y                           := setup.o topology.o
+obj-y                           := setup.o
diff --git a/arch/i386/mach-voyager/voyager_basic.c b/arch/i386/mach-voyager/voyager_basic.c
index aa49a33a572c..b584060ec004 100644
--- a/arch/i386/mach-voyager/voyager_basic.c
+++ b/arch/i386/mach-voyager/voyager_basic.c
@@ -23,6 +23,8 @@
 #include <linux/delay.h>
 #include <linux/reboot.h>
 #include <linux/sysrq.h>
+#include <linux/smp.h>
+#include <linux/nodemask.h>
 #include <asm/io.h>
 #include <asm/voyager.h>
 #include <asm/vic.h>
@@ -328,4 +330,3 @@ void machine_power_off(void)
        if (pm_power_off)
                pm_power_off();
 }
diff --git a/arch/i386/mach-voyager/voyager_smp.c b/arch/i386/mach-voyager/voyager_smp.c
index 6e4c3baef6cc..8165626a5c30 100644
--- a/arch/i386/mach-voyager/voyager_smp.c
+++ b/arch/i386/mach-voyager/voyager_smp.c
@@ -402,6 +402,7 @@ find_smp_config(void)
        cpus_addr(phys_cpu_present_map)[0] |= voyager_extended_cmos_read(VOYAGER_PROCESSOR_PRESENT_MASK + 1) << 8;
        cpus_addr(phys_cpu_present_map)[0] |= voyager_extended_cmos_read(VOYAGER_PROCESSOR_PRESENT_MASK + 2) << 16;
        cpus_addr(phys_cpu_present_map)[0] |= voyager_extended_cmos_read(VOYAGER_PROCESSOR_PRESENT_MASK + 3) << 24;
+        cpu_possible_map = phys_cpu_present_map;
        printk("VOYAGER SMP: phys_cpu_present_map = 0x%lx\n", cpus_addr(phys_cpu_present_map)[0]);
        /* Here we set up the VIC to enable SMP */
        /* enable the CPIs by writing the base vector to their register */
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 845cd0902a50..a85ea9d37f05 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -453,6 +453,7 @@ source "arch/ia64/oprofile/Kconfig"
 config KPROBES
        bool "Kprobes (EXPERIMENTAL)"
+        depends on EXPERIMENTAL && MODULES
        help
          Kprobes allows you to trap at almost any kernel address and
          execute a callback function.  register_kprobe() establishes
diff --git a/arch/m32r/Makefile b/arch/m32r/Makefile
index 983d438b14b6..4b3c90ba926c 100644
--- a/arch/m32r/Makefile
+++ b/arch/m32r/Makefile
@@ -12,14 +12,14 @@ CFLAGS_MODULE += -mmodel=large
 ifdef CONFIG_CHIP_VDEC2
 cflags-$(CONFIG_ISA_M32R2)      += -DNO_FPU -Wa,-bitinst
-aflags-$(CONFIG_ISA_M32R2)      += -DNO_FPU -Wa,-bitinst
+aflags-$(CONFIG_ISA_M32R2)      += -DNO_FPU -O2 -Wa,-bitinst -Wa,-no-parallel
 else
 cflags-$(CONFIG_ISA_M32R2)      += -DNO_FPU -m32r2
-aflags-$(CONFIG_ISA_M32R2)      += -DNO_FPU -m32r2
+aflags-$(CONFIG_ISA_M32R2)      += -DNO_FPU -m32r2 -O2
 endif
 cflags-$(CONFIG_ISA_M32R)       += -DNO_FPU
-aflags-$(CONFIG_ISA_M32R)       += -DNO_FPU -Wa,-no-bitinst
+aflags-$(CONFIG_ISA_M32R)       += -DNO_FPU -O2 -Wa,-no-bitinst
 CFLAGS += $(cflags-y)
 AFLAGS += $(aflags-y)
diff --git a/arch/m32r/kernel/signal.c b/arch/m32r/kernel/signal.c
index 71763f7a1d19..cb33097fefc4 100644
--- a/arch/m32r/kernel/signal.c
+++ b/arch/m32r/kernel/signal.c
@@ -36,7 +36,7 @@ int do_signal(struct pt_regs *, sigset_t *);
 asmlinkage int
 sys_rt_sigsuspend(sigset_t *unewset, size_t sigsetsize,
                  unsigned long r2, unsigned long r3, unsigned long r4,
-                  unsigned long r5, unsigned long r6, struct pt_regs regs)
+                  unsigned long r5, unsigned long r6, struct pt_regs *regs)
 {
        sigset_t saveset, newset;
@@ -54,21 +54,21 @@ sys_rt_sigsuspend(sigset_t *unewset, size_t sigsetsize,
        recalc_sigpending();
        spin_unlock_irq(&current->sighand->siglock);
-        regs.r0 = -EINTR;
+        regs->r0 = -EINTR;
        while (1) {
                current->state = TASK_INTERRUPTIBLE;
                schedule();
-                if (do_signal(&regs, &saveset))
+                if (do_signal(regs, &saveset))
-                        return regs.r0;
+                        return regs->r0;
        }
 }
 asmlinkage int
 sys_sigaltstack(const stack_t __user *uss, stack_t __user *uoss,
                unsigned long r2, unsigned long r3, unsigned long r4,
-                unsigned long r5, unsigned long r6, struct pt_regs regs)
+                unsigned long r5, unsigned long r6, struct pt_regs *regs)
 {
-        return do_sigaltstack(uss, uoss, regs.spu);
+        return do_sigaltstack(uss, uoss, regs->spu);
 }
@@ -140,11 +140,10 @@ restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
 asmlinkage int
 sys_rt_sigreturn(unsigned long r0, unsigned long r1,
                 unsigned long r2, unsigned long r3, unsigned long r4,
-                 unsigned long r5, unsigned long r6, struct pt_regs regs)
+                 unsigned long r5, unsigned long r6, struct pt_regs *regs)
 {
-        struct rt_sigframe __user *frame = (struct rt_sigframe __user *)regs.spu;
+        struct rt_sigframe __user *frame = (struct rt_sigframe __user *)regs->spu;
        sigset_t set;
-        stack_t st;
        int result;
        if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
@@ -158,14 +157,11 @@ sys_rt_sigreturn(unsigned long r0, unsigned long r1,
        recalc_sigpending();
        spin_unlock_irq(&current->sighand->siglock);
-        if (restore_sigcontext(&regs, &frame->uc.uc_mcontext, &result))
+        if (restore_sigcontext(regs, &frame->uc.uc_mcontext, &result))
                goto badframe;
-        if (__copy_from_user(&st, &frame->uc.uc_stack, sizeof(st)))
+        if (do_sigaltstack(&frame->uc.uc_stack, NULL, regs->spu) == -EFAULT)
                goto badframe;
-        /* It is more difficult to avoid calling this function than to
-           call it and ignore errors.  */
-        do_sigaltstack(&st, NULL, regs.spu);
        return result;
diff --git a/arch/m32r/lib/usercopy.c b/arch/m32r/lib/usercopy.c
index ce16bbe26a52..2d1dd2106c4d 100644
--- a/arch/m32r/lib/usercopy.c
+++ b/arch/m32r/lib/usercopy.c
@@ -64,7 +64,7 @@ do {									\
                "       .balign 4\n"                                    \
                "       .long 0b,3b\n"                                  \
                ".previous"                                             \
-                : "=r"(res), "=r"(count), "=&r" (__d0), "=&r" (__d1),   \
+                : "=&r"(res), "=&r"(count), "=&r" (__d0), "=&r" (__d1), \
                  "=&r" (__d2)                                          \
                : "i"(-EFAULT), "0"(count), "1"(count), "3"(src),       \
                  "4"(dst)                                              \
@@ -101,7 +101,7 @@ do {									\
                "       .balign 4\n"                                    \
                "       .long 0b,3b\n"                                  \
                ".previous"                                             \
-                : "=r"(res), "=r"(count), "=&r" (__d0), "=&r" (__d1),   \
+                : "=&r"(res), "=&r"(count), "=&r" (__d0), "=&r" (__d1), \
                  "=&r" (__d2)                                          \
                : "i"(-EFAULT), "0"(count), "1"(count), "3"(src),       \
                  "4"(dst)                                              \
diff --git a/arch/mips/kernel/linux32.c b/arch/mips/kernel/linux32.c
index 5f68b220c26d..e00e5f6e7fdd 100644
--- a/arch/mips/kernel/linux32.c
+++ b/arch/mips/kernel/linux32.c
@@ -161,60 +161,6 @@ out:
        return error;
 }
-struct dirent32 {
-        unsigned int    d_ino;
-        unsigned int    d_off;
-        unsigned short  d_reclen;
-        char            d_name[NAME_MAX + 1];
-};
-static void
-xlate_dirent(void *dirent64, void *dirent32, long n)
-{
-        long off;
-        struct dirent *dirp;
-        struct dirent32 *dirp32;
-        off = 0;
-        while (off < n) {
-                dirp = (struct dirent *)(dirent64 + off);
-                dirp32 = (struct dirent32 *)(dirent32 + off);
-                off += dirp->d_reclen;
-                dirp32->d_ino = dirp->d_ino;
-                dirp32->d_off = (unsigned int)dirp->d_off;
-                dirp32->d_reclen = dirp->d_reclen;
-                strncpy(dirp32->d_name, dirp->d_name, dirp->d_reclen - ((3 * 4) + 2));
-        }
-        return;
-}
-asmlinkage long
-sys32_getdents(unsigned int fd, void * dirent32, unsigned int count)
-{
-        long n;
-        void *dirent64;
-        dirent64 = (void *)((unsigned long)(dirent32 + (sizeof(long) - 1)) & ~(sizeof(long) - 1));
-        if ((n = sys_getdents(fd, dirent64, count - (dirent64 - dirent32))) < 0)
-                return(n);
-        xlate_dirent(dirent64, dirent32, n);
-        return(n);
-}
-asmlinkage int old_readdir(unsigned int fd, void * dirent, unsigned int count);
-asmlinkage int
-sys32_readdir(unsigned int fd, void * dirent32, unsigned int count)
-{
-        int n;
-        struct dirent dirent64;
-        if ((n = old_readdir(fd, &dirent64, count)) < 0)
-                return(n);
-        xlate_dirent(&dirent64, dirent32, dirent64.d_reclen);
-        return(n);
-}
 asmlinkage int
 sys32_waitpid(compat_pid_t pid, unsigned int *stat_addr, int options)
 {
diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S
index d83e033dbc87..2f2dc54b2e26 100644
--- a/arch/mips/kernel/scall32-o32.S
+++ b/arch/mips/kernel/scall32-o32.S
@@ -626,7 +626,7 @@ einval:	li	v0, -EINVAL
        sys     sys_fstatat64           4
        sys     sys_unlinkat            3
        sys     sys_renameat            4       /* 4295 */
-        sys     sys_linkat              4
+        sys     sys_linkat              5
        sys     sys_symlinkat           3
        sys     sys_readlinkat          4
        sys     sys_fchmodat            3
diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S
index d87b5446fa13..02c8267e45e7 100644
--- a/arch/mips/kernel/scall64-n32.S
+++ b/arch/mips/kernel/scall64-n32.S
@@ -195,7 +195,7 @@ EXPORT(sysn32_call_table)
        PTR     sys_fdatasync
        PTR     sys_truncate
        PTR     sys_ftruncate                   /* 6075 */
-        PTR     sys32_getdents
+        PTR     compat_sys_getdents
        PTR     sys_getcwd
        PTR     sys_chdir
        PTR     sys_fchdir
diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S
index 5b0414018c9a..797e0d874889 100644
--- a/arch/mips/kernel/scall64-o32.S
+++ b/arch/mips/kernel/scall64-o32.S
@@ -293,7 +293,7 @@ sys_call_table:
        PTR     sys_uselib
        PTR     sys_swapon
        PTR     sys_reboot
-        PTR     sys32_readdir
+        PTR     compat_sys_old_readdir
        PTR     old_mmap                        /* 4090 */
        PTR     sys_munmap
        PTR     sys_truncate
@@ -345,7 +345,7 @@ sys_call_table:
        PTR     sys_setfsuid
        PTR     sys_setfsgid
        PTR     sys32_llseek                    /* 4140 */
-        PTR     sys32_getdents
+        PTR     compat_sys_getdents
        PTR     compat_sys_select
        PTR     sys_flock
        PTR     sys_msync
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index d86affa21278..d9293c558e41 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -540,6 +540,9 @@ void __init setup_arch(char **cmdline_p)
        sparse_init();
        paging_init();
        resource_init();
+#ifdef CONFIG_SMP
+        plat_smp_setup();
+#endif
 }
 int __init fpu_disable(char *s)
diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c
index 5e189862e523..06ed90752424 100644
--- a/arch/mips/kernel/smp.c
+++ b/arch/mips/kernel/smp.c
@@ -236,7 +236,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
        init_new_context(current, &init_mm);
        current_thread_info()->cpu = 0;
        smp_tune_scheduling();
-        prom_prepare_cpus(max_cpus);
+        plat_prepare_cpus(max_cpus);
 }
 /* preload SMP state for boot cpu */
diff --git a/arch/mips/kernel/smp_mt.c b/arch/mips/kernel/smp_mt.c
index c930364830d0..993b8bf56aaf 100644
--- a/arch/mips/kernel/smp_mt.c
+++ b/arch/mips/kernel/smp_mt.c
@@ -143,7 +143,7 @@ static struct irqaction irq_call = {
 * Make sure all CPU's are in a sensible state before we boot any of the
 * secondarys
 */
-void prom_prepare_cpus(unsigned int max_cpus)
+void plat_smp_setup(void)
 {
        unsigned long val;
        int i, num;
@@ -179,11 +179,9 @@ void prom_prepare_cpus(unsigned int max_cpus)
                                write_vpe_c0_vpeconf0(tmp);
                                /* Record this as available CPU */
-                                if (i < max_cpus) {
+                                cpu_set(i, phys_cpu_present_map);
-                                        cpu_set(i, phys_cpu_present_map);
+                                __cpu_number_map[i]     = ++num;
-                                        __cpu_number_map[i]     = ++num;
+                                __cpu_logical_map[num]  = i;
-                                        __cpu_logical_map[num]  = i;
-                                }
                        }
                        /* disable multi-threading with TC's */
@@ -241,7 +239,10 @@ void prom_prepare_cpus(unsigned int max_cpus)
                set_vi_handler (MIPS_CPU_IPI_RESCHED_IRQ, ipi_resched_dispatch);
                set_vi_handler (MIPS_CPU_IPI_CALL_IRQ, ipi_call_dispatch);
        }
+}
+void __init plat_prepare_cpus(unsigned int max_cpus)
+{
        cpu_ipi_resched_irq = MIPSCPU_INT_BASE + MIPS_CPU_IPI_RESCHED_IRQ;
        cpu_ipi_call_irq = MIPSCPU_INT_BASE + MIPS_CPU_IPI_CALL_IRQ;
diff --git a/arch/mips/pmc-sierra/yosemite/smp.c b/arch/mips/pmc-sierra/yosemite/smp.c
index 7f8fda962190..c197311e15d3 100644
--- a/arch/mips/pmc-sierra/yosemite/smp.c
+++ b/arch/mips/pmc-sierra/yosemite/smp.c
@@ -50,37 +50,25 @@ void __init prom_grab_secondary(void)
 * We don't want to start the secondary CPU yet nor do we have a nice probing
 * feature in PMON so we just assume presence of the secondary core.
 */
-static char maxcpus_string[] __initdata =
+void __init plat_smp_setup(void)
-        KERN_WARNING "max_cpus set to 0; using 1 instead\n";
-void __init prom_prepare_cpus(unsigned int max_cpus)
 {
-        int enabled = 0, i;
+        int i;
-        if (max_cpus == 0) {
-                printk(maxcpus_string);
-                max_cpus = 1;
-        }
        cpus_clear(phys_cpu_present_map);
        for (i = 0; i < 2; i++) {
-                if (i == max_cpus)
-                        break;
-                /*
-                 * The boot CPU
-                 */
                cpu_set(i, phys_cpu_present_map);
                __cpu_number_map[i]     = i;
                __cpu_logical_map[i]    = i;
-                enabled++;
        }
+}
+void __init plat_prepare_cpus(unsigned int max_cpus)
+{
        /*
         * Be paranoid.  Enable the IPI only if we're really about to go SMP.
         */
-        if (enabled > 1)
+        if (cpus_weight(cpu_possible_map))
                set_c0_status(STATUSF_IP5);
 }
diff --git a/arch/mips/sgi-ip27/ip27-smp.c b/arch/mips/sgi-ip27/ip27-smp.c
index dbef3f6b5650..09fa7f5216f0 100644
--- a/arch/mips/sgi-ip27/ip27-smp.c
+++ b/arch/mips/sgi-ip27/ip27-smp.c
@@ -140,7 +140,7 @@ static __init void intr_clear_all(nasid_t nasid)
                REMOTE_HUB_CLR_INTR(nasid, i);
 }
-void __init prom_prepare_cpus(unsigned int max_cpus)
+void __init plat_smp_setup(void)
 {
        cnodeid_t       cnode;
@@ -161,6 +161,11 @@ void __init prom_prepare_cpus(unsigned int max_cpus)
        alloc_cpupda(0, 0);
 }
+void __init plat_prepare_cpus(unsigned int max_cpus)
+{
+        /* We already did everything necessary earlier */
+}
 /*
 * Launch a slave into smp_bootstrap().  It doesn't take an argument, and we
 * set sp to the kernel stack of the newly created idle process, gp to the proc
diff --git a/arch/mips/sibyte/cfe/smp.c b/arch/mips/sibyte/cfe/smp.c
index 4477af3d8074..eab20e2db323 100644
--- a/arch/mips/sibyte/cfe/smp.c
+++ b/arch/mips/sibyte/cfe/smp.c
@@ -31,7 +31,7 @@
 *
 * Common setup before any secondaries are started
 */
-void __init prom_prepare_cpus(unsigned int max_cpus)
+void __init plat_smp_setup(void)
 {
        int i, num;
@@ -40,14 +40,18 @@ void __init prom_prepare_cpus(unsigned int max_cpus)
        __cpu_number_map[0] = 0;
        __cpu_logical_map[0] = 0;
-        for (i=1, num=0; i<NR_CPUS; i++) {
+        for (i = 1, num = 0; i < NR_CPUS; i++) {
                if (cfe_cpu_stop(i) == 0) {
                        cpu_set(i, phys_cpu_present_map);
                        __cpu_number_map[i] = ++num;
                        __cpu_logical_map[num] = i;
                }
        }
-        printk("Detected %i available secondary CPU(s)\n", num);
+        printk(KERN_INFO "Detected %i available secondary CPU(s)\n", num);
+}
+void __init plat_prepare_cpus(unsigned int max_cpus)
+{
 }
 /*
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index d112aed2999b..fec07a12c6cd 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -989,7 +989,7 @@ source "arch/powerpc/oprofile/Kconfig"
 config KPROBES
        bool "Kprobes (EXPERIMENTAL)"
-        depends on PPC64
+        depends on PPC64 && EXPERIMENTAL && MODULES
        help
          Kprobes allows you to trap at almost any kernel address and
          execute a callback function.  register_kprobe() establishes
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 82d117c60d7f..d63cd562d9d5 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -816,8 +816,6 @@ void __init unflatten_device_tree(void)
 {
        unsigned long start, mem, size;
        struct device_node **allnextp = &allnodes;
-        char *p = NULL;
-        int l = 0;
        DBG(" -> unflatten_device_tree()\n");
@@ -853,19 +851,6 @@ void __init unflatten_device_tree(void)
        if (of_chosen == NULL)
                of_chosen = of_find_node_by_path("/chosen@0");
-        /* Retreive command line */
-        if (of_chosen != NULL) {
-                p = (char *)get_property(of_chosen, "bootargs", &l);
-                if (p != NULL && l > 0)
-                        strlcpy(cmd_line, p, min(l, COMMAND_LINE_SIZE));
-        }
-#ifdef CONFIG_CMDLINE
-        if (l == 0 || (l == 1 && (*p) == 0))
-                strlcpy(cmd_line, CONFIG_CMDLINE, COMMAND_LINE_SIZE);
-#endif /* CONFIG_CMDLINE */
-        DBG("Command line is: %s\n", cmd_line);
        DBG(" <- unflatten_device_tree()\n");
 }
@@ -936,6 +921,8 @@ static int __init early_init_dt_scan_chosen(unsigned long node,
 {
        u32 *prop;
        unsigned long *lprop;
+        unsigned long l;
+        char *p;
        DBG("search \"chosen\", depth: %d, uname: %s\n", depth, uname);
@@ -1000,6 +987,41 @@ static int __init early_init_dt_scan_chosen(unsigned long node,
               crashk_res.end = crashk_res.start + *lprop - 1;
 #endif
+        /* Retreive command line */
+        p = of_get_flat_dt_prop(node, "bootargs", &l);
+        if (p != NULL && l > 0)
+                strlcpy(cmd_line, p, min((int)l, COMMAND_LINE_SIZE));
+#ifdef CONFIG_CMDLINE
+        if (l == 0 || (l == 1 && (*p) == 0))
+                strlcpy(cmd_line, CONFIG_CMDLINE, COMMAND_LINE_SIZE);
+#endif /* CONFIG_CMDLINE */
+        DBG("Command line is: %s\n", cmd_line);
+        if (strstr(cmd_line, "mem=")) {
+                char *p, *q;
+                unsigned long maxmem = 0;
+                for (q = cmd_line; (p = strstr(q, "mem=")) != 0; ) {
+                        q = p + 4;
+                        if (p > cmd_line && p[-1] != ' ')
+                                continue;
+                        maxmem = simple_strtoul(q, &q, 0);
+                        if (*q == 'k' || *q == 'K') {
+                                maxmem <<= 10;
+                                ++q;
+                        } else if (*q == 'm' || *q == 'M') {
+                                maxmem <<= 20;
+                                ++q;
+                        } else if (*q == 'g' || *q == 'G') {
+                                maxmem <<= 30;
+                                ++q;
+                        }
+                }
+                memory_limit = maxmem;
+        }
        /* break now */
        return 1;
 }
@@ -1120,7 +1142,7 @@ static void __init early_reserve_mem(void)
                        size_32 = *(reserve_map_32++);
                        if (size_32 == 0)
                                break;
-                        DBG("reserving: %lx -> %lx\n", base_32, size_32);
+                        DBG("reserving: %x -> %x\n", base_32, size_32);
                        lmb_reserve(base_32, size_32);
                }
                return;
diff --git a/arch/powerpc/kernel/vdso64/gettimeofday.S b/arch/powerpc/kernel/vdso64/gettimeofday.S
index ccaeda5136d1..4ee871f1cadb 100644
--- a/arch/powerpc/kernel/vdso64/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso64/gettimeofday.S
@@ -225,9 +225,9 @@ V_FUNCTION_BEGIN(__do_get_xsec)
  .cfi_startproc
        /* check for update count & load values */
 1:      ld      r8,CFG_TB_UPDATE_COUNT(r3)
-        andi.   r0,r4,1                 /* pending update ? loop */
+        andi.   r0,r8,1                 /* pending update ? loop */
        bne-    1b
-        xor     r0,r4,r4                /* create dependency */
+        xor     r0,r8,r8                /* create dependency */
        add     r3,r3,r0
        /* Get TB & offset it */
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index ae2c919cbecd..7d9ce9a48219 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -169,7 +169,7 @@ int htab_bolt_mapping(unsigned long vstart, unsigned long vend,
 #ifdef CONFIG_PPC_ISERIES
                if (_machine == PLATFORM_ISERIES_LPAR)
                        ret = iSeries_hpte_insert(hpteg, va,
-                                                  virt_to_abs(paddr),
+                                                  __pa(vaddr),
                                                  tmp_mode,
                                                  HPTE_V_BOLTED,
                                                  psize);
diff --git a/arch/powerpc/platforms/pseries/eeh.c b/arch/powerpc/platforms/pseries/eeh.c
index 83578313ee7e..2ab9dcdfb415 100644
--- a/arch/powerpc/platforms/pseries/eeh.c
+++ b/arch/powerpc/platforms/pseries/eeh.c
@@ -893,6 +893,20 @@ void eeh_add_device_tree_early(struct device_node *dn)
 }
 EXPORT_SYMBOL_GPL(eeh_add_device_tree_early);
+void eeh_add_device_tree_late(struct pci_bus *bus)
+{
+        struct pci_dev *dev;
+        list_for_each_entry(dev, &bus->devices, bus_list) {
+                eeh_add_device_late(dev);
+                if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) {
+                        struct pci_bus *subbus = dev->subordinate;
+                        if (subbus)
+                                eeh_add_device_tree_late(subbus);
+                }
+        }
+}
 /**
 * eeh_add_device_late - perform EEH initialization for the indicated pci device
 * @dev: pci device for which to set up EEH
diff --git a/arch/powerpc/platforms/pseries/eeh_driver.c b/arch/powerpc/platforms/pseries/eeh_driver.c
index e3cbba49fd6e..b811d5ff92fe 100644
--- a/arch/powerpc/platforms/pseries/eeh_driver.c
+++ b/arch/powerpc/platforms/pseries/eeh_driver.c
@@ -37,7 +37,7 @@
 static inline const char * pcid_name (struct pci_dev *pdev)
 {
-        if (pdev->dev.driver)
+        if (pdev && pdev->dev.driver)
                return pdev->dev.driver->name;
        return "";
 }
diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c
index bdaa8aabdaa6..f3bad900bbcf 100644
--- a/arch/powerpc/platforms/pseries/pci_dlpar.c
+++ b/arch/powerpc/platforms/pseries/pci_dlpar.c
@@ -106,6 +106,8 @@ pcibios_fixup_new_pci_devices(struct pci_bus *bus, int fix_bus)
                        }
                }
        }
+        eeh_add_device_tree_late(bus);
 }
 EXPORT_SYMBOL_GPL(pcibios_fixup_new_pci_devices);
@@ -114,7 +116,6 @@ pcibios_pci_config_bridge(struct pci_dev *dev)
 {
        u8 sec_busno;
        struct pci_bus *child_bus;
-        struct pci_dev *child_dev;
        /* Get busno of downstream bus */
        pci_read_config_byte(dev, PCI_SECONDARY_BUS, &sec_busno);
@@ -129,10 +130,6 @@ pcibios_pci_config_bridge(struct pci_dev *dev)
        pci_scan_child_bus(child_bus);
-        list_for_each_entry(child_dev, &child_bus->devices, bus_list) {
-                eeh_add_device_late(child_dev);
-        }
        /* Fixup new pci devices without touching bus struct */
        pcibios_fixup_new_pci_devices(child_bus, 0);
@@ -160,18 +157,25 @@ pcibios_add_pci_devices(struct pci_bus * bus)
        eeh_add_device_tree_early(dn);
-        /* pci_scan_slot should find all children */
+        if (_machine == PLATFORM_PSERIES_LPAR) {
-        slotno = PCI_SLOT(PCI_DN(dn->child)->devfn);
+                /* use ofdt-based probe */
-        num = pci_scan_slot(bus, PCI_DEVFN(slotno, 0));
+                of_scan_bus(dn, bus);
-        if (num) {
+                if (!list_empty(&bus->devices)) {
-                pcibios_fixup_new_pci_devices(bus, 1);
+                        pcibios_fixup_new_pci_devices(bus, 0);
-                pci_bus_add_devices(bus);
+                        pci_bus_add_devices(bus);
-        }
+                }
+        } else {
+                /* use legacy probe */
+                slotno = PCI_SLOT(PCI_DN(dn->child)->devfn);
+                num = pci_scan_slot(bus, PCI_DEVFN(slotno, 0));
+                if (num) {
+                        pcibios_fixup_new_pci_devices(bus, 1);
+                        pci_bus_add_devices(bus);
+                }
-        list_for_each_entry(dev, &bus->devices, bus_list) {
+                list_for_each_entry(dev, &bus->devices, bus_list)
-                eeh_add_device_late (dev);
+                        if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE)
-                if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE)
+                                pcibios_pci_config_bridge(dev);
-                        pcibios_pci_config_bridge(dev);
        }
 }
 EXPORT_SYMBOL_GPL(pcibios_add_pci_devices);
diff --git a/arch/s390/kernel/compat_wrapper.S b/arch/s390/kernel/compat_wrapper.S
index 615964cca15f..50e80138e7ad 100644
--- a/arch/s390/kernel/compat_wrapper.S
+++ b/arch/s390/kernel/compat_wrapper.S
@@ -1552,6 +1552,7 @@ sys_linkat_wrapper:
        llgtr   %r3,%r3                 # const char *
        lgfr    %r4,%r4                 # int
        llgtr   %r5,%r5                 # const char *
+        lgfr    %r6,%r6                 # int
        jg      sys_linkat
        .globl sys_symlinkat_wrapper
diff --git a/arch/sparc64/Kconfig b/arch/sparc64/Kconfig
index ab733be9af08..4c0a50a76554 100644
--- a/arch/sparc64/Kconfig
+++ b/arch/sparc64/Kconfig
@@ -383,6 +383,7 @@ source "arch/sparc64/oprofile/Kconfig"
 config KPROBES
        bool "Kprobes (EXPERIMENTAL)"
+        depends on EXPERIMENTAL && MODULES
        help
          Kprobes allows you to trap at almost any kernel address and
          execute a callback function.  register_kprobe() establishes
diff --git a/arch/sparc64/kernel/setup.c b/arch/sparc64/kernel/setup.c
index 054461e6946d..158bd31e15b7 100644
--- a/arch/sparc64/kernel/setup.c
+++ b/arch/sparc64/kernel/setup.c
@@ -542,6 +542,8 @@ void __init setup_arch(char **cmdline_p)
        }
 #endif
+        smp_setup_cpu_possible_map();
        paging_init();
 }
diff --git a/arch/sparc64/kernel/smp.c b/arch/sparc64/kernel/smp.c
index 1fb6323e65a4..1f7ad8a69052 100644
--- a/arch/sparc64/kernel/smp.c
+++ b/arch/sparc64/kernel/smp.c
@@ -1079,18 +1079,12 @@ int setup_profiling_timer(unsigned int multiplier)
        return 0;
 }
+/* Constrain the number of cpus to max_cpus.  */
 void __init smp_prepare_cpus(unsigned int max_cpus)
 {
-        int instance, mid;
-        instance = 0;
-        while (!cpu_find_by_instance(instance, NULL, &mid)) {
-                if (mid < max_cpus)
-                        cpu_set(mid, phys_cpu_present_map);
-                instance++;
-        }
        if (num_possible_cpus() > max_cpus) {
+                int instance, mid;
                instance = 0;
                while (!cpu_find_by_instance(instance, NULL, &mid)) {
                        if (mid != boot_cpu_id) {
@@ -1105,6 +1099,22 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
        smp_store_cpu_info(boot_cpu_id);
 }
+/* Set this up early so that things like the scheduler can init
+ * properly.  We use the same cpu mask for both the present and
+ * possible cpu map.
+ */
+void __init smp_setup_cpu_possible_map(void)
+{
+        int instance, mid;
+        instance = 0;
+        while (!cpu_find_by_instance(instance, NULL, &mid)) {
+                if (mid < NR_CPUS)
+                        cpu_set(mid, phys_cpu_present_map);
+                instance++;
+        }
+}
 void __devinit smp_prepare_boot_cpu(void)
 {
        if (hard_smp_processor_id() >= NR_CPUS) {
diff --git a/arch/um/drivers/cow.h b/arch/um/drivers/cow.h
index dc36b222100b..04e3958266e0 100644
--- a/arch/um/drivers/cow.h
+++ b/arch/um/drivers/cow.h
@@ -46,7 +46,7 @@ extern int file_reader(__u64 offset, char *buf, int len, void *arg);
 extern int read_cow_header(int (*reader)(__u64, char *, int, void *),
                           void *arg, __u32 *version_out,
                           char **backing_file_out, time_t *mtime_out,
-                           unsigned long long *size_out, int *sectorsize_out,
+                           __u64 *size_out, int *sectorsize_out,
                           __u32 *align_out, int *bitmap_offset_out);
 extern int write_cow_header(char *cow_file, int fd, char *backing_file,
diff --git a/arch/um/drivers/cow_sys.h b/arch/um/drivers/cow_sys.h
index c83fc5d68936..94de4ead4f7a 100644
--- a/arch/um/drivers/cow_sys.h
+++ b/arch/um/drivers/cow_sys.h
@@ -23,17 +23,17 @@ static inline char *cow_strdup(char *str)
        return(uml_strdup(str));
 }
-static inline int cow_seek_file(int fd, unsigned long long offset)
+static inline int cow_seek_file(int fd, __u64 offset)
 {
        return(os_seek_file(fd, offset));
 }
-static inline int cow_file_size(char *file, unsigned long long *size_out)
+static inline int cow_file_size(char *file, __u64 *size_out)
 {
        return(os_file_size(file, size_out));
 }
-static inline int cow_write_file(int fd, char *buf, int size)
+static inline int cow_write_file(int fd, void *buf, int size)
 {
        return(os_write_file(fd, buf, size));
 }
diff --git a/arch/um/drivers/cow_user.c b/arch/um/drivers/cow_user.c
index fbe2217db5dd..61951b721268 100644
--- a/arch/um/drivers/cow_user.c
+++ b/arch/um/drivers/cow_user.c
@@ -176,7 +176,7 @@ int write_cow_header(char *cow_file, int fd, char *backing_file,
        err = -ENOMEM;
        header = cow_malloc(sizeof(*header));
        if(header == NULL){
-                cow_printf("Failed to allocate COW V3 header\n");
+                cow_printf("write_cow_header - failed to allocate COW V3 header\n");
                goto out;
        }
        header->magic = htonl(COW_MAGIC);
@@ -196,15 +196,17 @@ int write_cow_header(char *cow_file, int fd, char *backing_file,
        err = os_file_modtime(header->backing_file, &modtime);
        if(err < 0){
-                cow_printf("Backing file '%s' mtime request failed, "
+                cow_printf("write_cow_header - backing file '%s' mtime "
-                           "err = %d\n", header->backing_file, -err);
+                           "request failed, err = %d\n", header->backing_file,
+                           -err);
                goto out_free;
        }
        err = cow_file_size(header->backing_file, size);
        if(err < 0){
-                cow_printf("Couldn't get size of backing file '%s', "
+                cow_printf("write_cow_header - couldn't get size of "
-                           "err = %d\n", header->backing_file, -err);
+                           "backing file '%s', err = %d\n",
+                           header->backing_file, -err);
                goto out_free;
        }
@@ -214,10 +216,11 @@ int write_cow_header(char *cow_file, int fd, char *backing_file,
        header->alignment = htonl(alignment);
        header->cow_format = COW_BITMAP;
-        err = os_write_file(fd, header, sizeof(*header));
+        err = cow_write_file(fd, header, sizeof(*header));
        if(err != sizeof(*header)){
-                cow_printf("Write of header to new COW file '%s' failed, "
+                cow_printf("write_cow_header - write of header to "
-                           "err = %d\n", cow_file, -err);
+                           "new COW file '%s' failed, err = %d\n", cow_file,
+                           -err);
                goto out_free;
        }
        err = 0;
@@ -299,7 +302,7 @@ int read_cow_header(int (*reader)(__u64, char *, int, void *), void *arg,
        }
        else if(version == 3){
                if(n < sizeof(header->v3)){
-                        cow_printf("read_cow_header - failed to read V2 "
+                        cow_printf("read_cow_header - failed to read V3 "
                                   "header\n");
                        goto out;
                }
@@ -359,7 +362,8 @@ int init_cow_file(int fd, char *cow_file, char *backing_file, int sectorsize,
        if(err != sizeof(zero)){
                cow_printf("Write of bitmap to new COW file '%s' failed, "
                           "err = %d\n", cow_file, -err);
-                err = -EINVAL;
+                if (err >= 0)
+                        err = -EINVAL;
                goto out;
        }
diff --git a/arch/um/drivers/net_user.c b/arch/um/drivers/net_user.c
index 098fa65981ab..0e2f06187ea7 100644
--- a/arch/um/drivers/net_user.c
+++ b/arch/um/drivers/net_user.c
@@ -47,10 +47,12 @@ void tap_check_ips(char *gate_addr, unsigned char *eth_addr)
        }
 }
+/* Do reliable error handling as this fails frequently enough. */
 void read_output(int fd, char *output, int len)
 {
-        int remain, n, actual;
+        int remain, ret, expected;
        char c;
+        char *str;
        if(output == NULL){
                output = &c;
@@ -58,23 +60,31 @@ void read_output(int fd, char *output, int len)
        }
                
        *output = '\0';
-        n = os_read_file(fd, &remain, sizeof(remain));
+        ret = os_read_file(fd, &remain, sizeof(remain));
-        if(n != sizeof(remain)){
-                printk("read_output - read of length failed, err = %d\n", -n);
+        if (ret != sizeof(remain)) {
-                return;
+                expected = sizeof(remain);
+                str = "length";
+                goto err;
        }
        while(remain != 0){
-                n = (remain < len) ? remain : len;
+                expected = (remain < len) ? remain : len;
-                actual = os_read_file(fd, output, n);
+                ret = os_read_file(fd, output, expected);
-                if(actual != n){
+                if (ret != expected) {
-                        printk("read_output - read of data failed, "
+                        str = "data";
-                               "err = %d\n", -actual);
+                        goto err;
-                        return;
                }
-                remain -= actual;
+                remain -= ret;
        }
        return;
+err:
+        if (ret < 0)
+                printk("read_output - read of %s failed, errno = %d\n", str, -ret);
+        else
+                printk("read_output - read of %s failed, read only %d of %d bytes\n", str, ret, expected);
 }
 int net_read(int fd, void *buf, int len)
diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c
index 101efd26d467..fa617e0719ab 100644
--- a/arch/um/drivers/ubd_kern.c
+++ b/arch/um/drivers/ubd_kern.c
@@ -1135,7 +1135,7 @@ static int path_requires_switch(char *from_cmdline, char *from_cow, char *cow)
 static int backing_file_mismatch(char *file, __u64 size, time_t mtime)
 {
        unsigned long modtime;
-        long long actual;
+        unsigned long long actual;
        int err;
        err = os_file_modtime(file, &modtime);
diff --git a/arch/um/include/init.h b/arch/um/include/init.h
index cbd79a8d213d..d4de7c0120ce 100644
--- a/arch/um/include/init.h
+++ b/arch/um/include/init.h
@@ -122,7 +122,7 @@ extern struct uml_param __uml_setup_start, __uml_setup_end;
 #define __exitcall(fn) static exitcall_t __exitcall_##fn __exit_call = fn
-#define __init_call __attribute__ ((unused,__section__ (".initcall.init")))
+#define __init_call     __attribute_used__ __attribute__ ((__section__ (".initcall.init")))
 #endif
diff --git a/arch/um/include/os.h b/arch/um/include/os.h
index eb1710b81255..2a1c64d8d0bf 100644
--- a/arch/um/include/os.h
+++ b/arch/um/include/os.h
@@ -179,8 +179,11 @@ extern void os_stop_process(int pid);
 extern void os_kill_process(int pid, int reap_child);
 extern void os_kill_ptraced_process(int pid, int reap_child);
 extern void os_usr1_process(int pid);
+extern long os_ptrace_ldt(long pid, long addr, long data);
 extern int os_getpid(void);
 extern int os_getpgrp(void);
 extern void init_new_thread_stack(void *sig_stack, void (*usr1_handler)(int));
 extern void init_new_thread_signals(int altstack);
 extern int run_kernel_thread(int (*fn)(void *), void *arg, void **jmp_ptr);
diff --git a/arch/um/os-Linux/file.c b/arch/um/os-Linux/file.c
index f55773c819e6..3bd10deea280 100644
--- a/arch/um/os-Linux/file.c
+++ b/arch/um/os-Linux/file.c
@@ -272,14 +272,23 @@ int os_connect_socket(char *name)
        snprintf(sock.sun_path, sizeof(sock.sun_path), "%s", name);
        fd = socket(AF_UNIX, SOCK_STREAM, 0);
-        if(fd < 0)
+        if(fd < 0) {
-                return(fd);
+                err = -errno;
+                goto out;
+        }
        err = connect(fd, (struct sockaddr *) &sock, sizeof(sock));
-        if(err)
+        if(err) {
-                return(-errno);
+                err = -errno;
+                goto out_close;
+        }
-        return(fd);
+        return fd;
+out_close:
+        close(fd);
+out:
+        return err;
 }
 void os_close_file(int fd)
diff --git a/arch/um/os-Linux/process.c b/arch/um/os-Linux/process.c
index 7f5e2dac2a35..d261888f39c4 100644
--- a/arch/um/os-Linux/process.c
+++ b/arch/um/os-Linux/process.c
@@ -19,6 +19,7 @@
 #include "irq_user.h"
 #include "kern_util.h"
 #include "longjmp.h"
+#include "skas_ptrace.h"
 #define ARBITRARY_ADDR -1
 #define FAILURE_PID    -1
@@ -100,6 +101,21 @@ void os_kill_process(int pid, int reap_child)
                
 }
+/* This is here uniquely to have access to the userspace errno, i.e. the one
+ * used by ptrace in case of error.
+ */
+long os_ptrace_ldt(long pid, long addr, long data)
+{
+        int ret;
+        ret = ptrace(PTRACE_LDT, pid, addr, data);
+        if (ret < 0)
+                return -errno;
+        return ret;
+}
 /* Kill off a ptraced child by all means available.  kill it normally first,
 * then PTRACE_KILL it, then PTRACE_CONT it in case it's in a run state from
 * which it can't exit directly.
diff --git a/arch/um/sys-i386/ldt.c b/arch/um/sys-i386/ldt.c
index 1fa09a79a10b..fe0877b3509c 100644
--- a/arch/um/sys-i386/ldt.c
+++ b/arch/um/sys-i386/ldt.c
@@ -107,7 +107,7 @@ long write_ldt_entry(struct mm_id * mm_idp, int func, struct user_desc * desc,
                 * So we need to switch child's mm into our userspace, then
                 * later switch back.
                 *
-                 * Note: I'm unshure: should interrupts be disabled here?
+                 * Note: I'm unsure: should interrupts be disabled here?
                 */
                if(!current->active_mm || current->active_mm == &init_mm ||
                   mm_idp != &current->active_mm->context.skas.id)
@@ -129,9 +129,7 @@ long write_ldt_entry(struct mm_id * mm_idp, int func, struct user_desc * desc,
                        pid = userspace_pid[cpu];
                }
-                res = ptrace(PTRACE_LDT, pid, 0, (unsigned long) &ldt_op);
+                res = os_ptrace_ldt(pid, 0, (unsigned long) &ldt_op);
-                if(res)
-                        res = errno;
                if(proc_mm)
                        put_cpu();
@@ -181,8 +179,7 @@ static long read_ldt_from_host(void __user * ptr, unsigned long bytecount)
         */
        cpu = get_cpu();
-        res = ptrace(PTRACE_LDT, userspace_pid[cpu], 0,
+        res = os_ptrace_ldt(userspace_pid[cpu], 0, (unsigned long) &ptrace_ldt);
-                     (unsigned long) &ptrace_ldt);
        put_cpu();
        if(res < 0)
                goto out;
diff --git a/arch/x86_64/Kconfig b/arch/x86_64/Kconfig
index 2f9deca31cc9..e18eb79bf855 100644
--- a/arch/x86_64/Kconfig
+++ b/arch/x86_64/Kconfig
@@ -354,21 +354,6 @@ config HPET_TIMER
          as it is off-chip.  You can find the HPET spec at
          <http://www.intel.com/hardwaredesign/hpetspec.htm>.
-config X86_PM_TIMER
-        bool "PM timer" if EMBEDDED
-        depends on ACPI
-        default y
-        help
-          Support the ACPI PM timer for time keeping. This is slow,
-          but is useful on some chipsets without HPET on systems with more
-          than one CPU. On a single processor or single socket multi core
-          system it is normally not required.
-          When the PM timer is active 64bit vsyscalls are disabled
-          and should not be enabled (/proc/sys/kernel/vsyscall64 should
-          not be changed).
-          The kernel selects the PM timer only as a last resort, so it is
-          useful to enable just in case.
 config HPET_EMULATE_RTC
        bool "Provide RTC interrupt"
        depends on HPET_TIMER && RTC=y
@@ -592,6 +577,7 @@ source "arch/x86_64/oprofile/Kconfig"
 config KPROBES
        bool "Kprobes (EXPERIMENTAL)"
+        depends on EXPERIMENTAL && MODULES
        help
          Kprobes allows you to trap at almost any kernel address and
          execute a callback function.  register_kprobe() establishes
diff --git a/arch/x86_64/kernel/Makefile b/arch/x86_64/kernel/Makefile
index 72fe60c20d39..a098a11e7755 100644
--- a/arch/x86_64/kernel/Makefile
+++ b/arch/x86_64/kernel/Makefile
@@ -43,7 +43,7 @@ CFLAGS_vsyscall.o		:= $(PROFILING) -g0
 bootflag-y                      += ../../i386/kernel/bootflag.o
 cpuid-$(subst m,y,$(CONFIG_X86_CPUID))  += ../../i386/kernel/cpuid.o
-topology-y                     += ../../i386/mach-default/topology.o
+topology-y                     += ../../i386/kernel/topology.o
 microcode-$(subst m,y,$(CONFIG_MICROCODE))  += ../../i386/kernel/microcode.o
 intel_cacheinfo-y               += ../../i386/kernel/cpu/intel_cacheinfo.o
 quirks-y                        += ../../i386/kernel/quirks.o
diff --git a/arch/x86_64/kernel/aperture.c b/arch/x86_64/kernel/aperture.c
index e4e2b7d01f89..a0f955b9995f 100644
--- a/arch/x86_64/kernel/aperture.c
+++ b/arch/x86_64/kernel/aperture.c
@@ -248,7 +248,7 @@ void __init iommu_hole_init(void)
                /* Got the aperture from the AGP bridge */
        } else if (swiotlb && !valid_agp) {
                /* Do nothing */
-        } else if ((!no_iommu && end_pfn >= MAX_DMA32_PFN) ||
+        } else if ((!no_iommu && end_pfn > MAX_DMA32_PFN) ||
                   force_iommu ||
                   valid_agp ||
                   fallback_aper_force) { 
diff --git a/arch/x86_64/kernel/io_apic.c b/arch/x86_64/kernel/io_apic.c
index 2585c1d92b26..ffed464e6b12 100644
--- a/arch/x86_64/kernel/io_apic.c
+++ b/arch/x86_64/kernel/io_apic.c
@@ -50,6 +50,8 @@ static int no_timer_check;
 int disable_timer_pin_1 __initdata;
+int timer_over_8254 __initdata = 1;
 /* Where if anywhere is the i8259 connect in external int mode */
 static struct { int pin, apic; } ioapic_i8259 = { -1, -1 };
@@ -251,6 +253,20 @@ static int __init enable_ioapic_setup(char *str)
 __setup("noapic", disable_ioapic_setup);
 __setup("apic", enable_ioapic_setup);
+static int __init setup_disable_8254_timer(char *s)
+{
+        timer_over_8254 = -1;
+        return 1;
+}
+static int __init setup_enable_8254_timer(char *s)
+{
+        timer_over_8254 = 2;
+        return 1;
+}
+__setup("disable_8254_timer", setup_disable_8254_timer);
+__setup("enable_8254_timer", setup_enable_8254_timer);
 #include <asm/pci-direct.h>
 #include <linux/pci_ids.h>
 #include <linux/pci.h>
@@ -309,27 +325,20 @@ void __init check_ioapic(void)
 #endif
                                        /* RED-PEN skip them on mptables too? */
                                        return;
+                                /* This should be actually default, but
+                                   for 2.6.16 let's do it for ATI only where
+                                   it's really needed. */
                                case PCI_VENDOR_ID_ATI:
-                                        if (apic_runs_main_timer != 0)
+                                        if (timer_over_8254 == 1) {     
-                                                break;
+                                                timer_over_8254 = 0;    
-#ifdef CONFIG_ACPI
-                                        /* Don't do this for laptops right
-                                           right now because their timer
-                                           doesn't necessarily tick in C2/3 */
-                                        if (acpi_fadt.revision >= 3 &&
-                        (acpi_fadt.plvl2_lat + acpi_fadt.plvl3_lat) < 1100) {
-                                                printk(KERN_INFO
-"ATI board detected, but seems to be a laptop. Timer might be shakey, sorry\n");
-                                                break;
-                                        }
-#endif                                  
                                        printk(KERN_INFO
-             "ATI board detected. Using APIC/PM timer.\n");
+                "ATI board detected. Disabling timer routing over 8254.\n");
-                                        apic_runs_main_timer = 1;
+                                        }       
-                                        nohpet = 1;
                                        return;
                                } 
                                /* No multi-function device? */
                                type = read_pci_config_byte(num,slot,func,
                                                            PCI_HEADER_TYPE);
@@ -1773,6 +1782,8 @@ static inline void unlock_ExtINT_logic(void)
 * a wide range of boards and BIOS bugs.  Fortunately only the timer IRQ
 * is so screwy.  Thanks to Brian Perkins for testing/hacking this beast
 * fanatically on his truly buggy board.
+ *
+ * FIXME: really need to revamp this for modern platforms only.
 */
 static inline void check_timer(void)
 {
@@ -1795,7 +1806,8 @@ static inline void check_timer(void)
         */
        apic_write(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT);
        init_8259A(1);
-        enable_8259A_irq(0);
+        if (timer_over_8254 > 0)
+                enable_8259A_irq(0);
        pin1  = find_isa_irq_pin(0, mp_INT);
        apic1 = find_isa_irq_apic(0, mp_INT);
@@ -1850,7 +1862,7 @@ static inline void check_timer(void)
        }
        printk(" failed.\n");
-        if (nmi_watchdog) {
+        if (nmi_watchdog == NMI_IO_APIC) {
                printk(KERN_WARNING "timer doesn't work through the IO-APIC - disabling NMI Watchdog!\n");
                nmi_watchdog = 0;
        }
diff --git a/arch/x86_64/kernel/pci-gart.c b/arch/x86_64/kernel/pci-gart.c
index dd0718dc178b..0c3f052ba6ce 100644
--- a/arch/x86_64/kernel/pci-gart.c
+++ b/arch/x86_64/kernel/pci-gart.c
@@ -228,11 +228,6 @@ static inline int need_iommu(struct device *dev, unsigned long addr, size_t size
        int mmu = high;
        if (force_iommu) 
                mmu = 1; 
-        if (no_iommu) { 
-                if (high) 
-                        panic("PCI-DMA: high address but no IOMMU.\n"); 
-                mmu = 0; 
-        }       
        return mmu; 
 }
@@ -241,11 +236,6 @@ static inline int nonforced_iommu(struct device *dev, unsigned long addr, size_t
        u64 mask = *dev->dma_mask;
        int high = addr + size >= mask;
        int mmu = high;
-        if (no_iommu) { 
-                if (high) 
-                        panic("PCI-DMA: high address but no IOMMU.\n"); 
-                mmu = 0; 
-        }       
        return mmu; 
 }
@@ -310,7 +300,7 @@ void gart_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, int di
        for (i = 0; i < nents; i++) {
                struct scatterlist *s = &sg[i];
-                if (!s->dma_length)
+                if (!s->dma_length || !s->length)
                        break;
                dma_unmap_single(dev, s->dma_address, s->dma_length, dir);
        }
@@ -364,6 +354,7 @@ static int __dma_map_cont(struct scatterlist *sg, int start, int stopat,
                
                BUG_ON(i > start && s->offset);
                if (i == start) {
+                        *sout = *s; 
                        sout->dma_address = iommu_bus_base;
                        sout->dma_address += iommu_page*PAGE_SIZE + s->offset;
                        sout->dma_length = s->length;
@@ -390,6 +381,7 @@ static inline int dma_map_cont(struct scatterlist *sg, int start, int stopat,
 {
        if (!need) { 
                BUG_ON(stopat - start != 1);
+                *sout = sg[start]; 
                sout->dma_length = sg[start].length; 
                return 0;
        } 
@@ -632,17 +624,13 @@ static int __init pci_iommu_init(void)
                (agp_copy_info(agp_bridge, &info) < 0);
 #endif  
-        if (swiotlb) { 
+        if (swiotlb)
-                no_iommu = 1;
                return -1; 
-        } 
-        
        if (no_iommu ||
            (!force_iommu && end_pfn <= MAX_DMA32_PFN) ||
            !iommu_aperture ||
            (no_agp && init_k8_gatt(&info) < 0)) {
-                no_iommu = 1;
-                no_iommu_init();
                printk(KERN_INFO "PCI-DMA: Disabling IOMMU.\n");
                if (end_pfn > MAX_DMA32_PFN) {
                        printk(KERN_ERR "WARNING more than 4GB of memory "
diff --git a/arch/x86_64/kernel/setup.c b/arch/x86_64/kernel/setup.c
index 9435ab7d6fb8..aa55e3cec665 100644
--- a/arch/x86_64/kernel/setup.c
+++ b/arch/x86_64/kernel/setup.c
@@ -423,6 +423,12 @@ static __init void parse_cmdline_early (char ** cmdline_p)
                else if(!memcmp(from, "elfcorehdr=", 11))
                        elfcorehdr_addr = memparse(from+11, &from);
 #endif
+#ifdef CONFIG_HOTPLUG_CPU
+                else if (!memcmp(from, "additional_cpus=", 16))
+                        setup_additional_cpus(from+16);
+#endif
        next_char:
                c = *(from++);
                if (!c)
diff --git a/arch/x86_64/kernel/smpboot.c b/arch/x86_64/kernel/smpboot.c
index 67e4e28f4df8..66e98659d077 100644
--- a/arch/x86_64/kernel/smpboot.c
+++ b/arch/x86_64/kernel/smpboot.c
@@ -1152,8 +1152,6 @@ void __init smp_cpus_done(unsigned int max_cpus)
        setup_ioapic_dest();
 #endif
-        time_init_gtod();
        check_nmi_watchdog();
 }
@@ -1244,7 +1242,7 @@ void __cpu_die(unsigned int cpu)
        printk(KERN_ERR "CPU %u didn't die...\n", cpu);
 }
-static __init int setup_additional_cpus(char *s)
+__init int setup_additional_cpus(char *s)
 {
        return get_option(&s, &additional_cpus);
 }
diff --git a/arch/x86_64/kernel/time.c b/arch/x86_64/kernel/time.c
index 67841d11ed1f..3080f84bf7b7 100644
--- a/arch/x86_64/kernel/time.c
+++ b/arch/x86_64/kernel/time.c
@@ -48,6 +48,8 @@ static void cpufreq_delayed_get(void);
 extern void i8254_timer_resume(void);
 extern int using_apic_timer;
+static char *time_init_gtod(void);
 DEFINE_SPINLOCK(rtc_lock);
 DEFINE_SPINLOCK(i8253_lock);
@@ -901,6 +903,7 @@ static struct irqaction irq0 = {
 void __init time_init(void)
 {
        char *timename;
+        char *gtod;
 #ifdef HPET_HACK_ENABLE_DANGEROUS
        if (!vxtime.hpet_address) {
@@ -945,21 +948,19 @@ void __init time_init(void)
                timename = "PIT";
        }
-        printk(KERN_INFO "time.c: Using %ld.%06ld MHz %s timer.\n",
+        vxtime.mode = VXTIME_TSC;
-               vxtime_hz / 1000000, vxtime_hz % 1000000, timename);
+        gtod = time_init_gtod();
+        printk(KERN_INFO "time.c: Using %ld.%06ld MHz WALL %s GTOD %s timer.\n",
+               vxtime_hz / 1000000, vxtime_hz % 1000000, timename, gtod);
        printk(KERN_INFO "time.c: Detected %d.%03d MHz processor.\n",
                cpu_khz / 1000, cpu_khz % 1000);
-        vxtime.mode = VXTIME_TSC;
        vxtime.quot = (1000000L << 32) / vxtime_hz;
        vxtime.tsc_quot = (1000L << 32) / cpu_khz;
        vxtime.last_tsc = get_cycles_sync();
        setup_irq(0, &irq0);
        set_cyc2ns_scale(cpu_khz);
-#ifndef CONFIG_SMP
-        time_init_gtod();
-#endif
 }
 /*
@@ -981,9 +982,9 @@ __cpuinit int unsynchronized_tsc(void)
 }
 /*
- * Decide after all CPUs are booted what mode gettimeofday should use.
+ * Decide what mode gettimeofday should use.
 */
-void __init time_init_gtod(void)
+__init static char *time_init_gtod(void)
 {
        char *timetype;
@@ -1011,8 +1012,7 @@ void __init time_init_gtod(void)
                timetype = hpet_use_timer ? "HPET/TSC" : "PIT/TSC";
                vxtime.mode = VXTIME_TSC;
        }
+        return timetype;
-        printk(KERN_INFO "time.c: Using %s based timekeeping.\n", timetype);
 }
 __setup("report_lost_ticks", time_setup);
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index 0cce28c4025b..33e2ca847a26 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -247,7 +247,7 @@ config ACPI_CUSTOM_DSDT_FILE
          Enter the full path name to the file wich includes the AmlCode declaration.
 config ACPI_BLACKLIST_YEAR
-        int "Disable ACPI for systems before Jan 1st this year" if X86
+        int "Disable ACPI for systems before Jan 1st this year" if X86_32
        default 0
        help
          enter a 4-digit year, eg. 2001 to disable ACPI by default
@@ -285,9 +285,8 @@ config ACPI_SYSTEM
          dump your ACPI DSDT table using /proc/acpi/dsdt.
 config X86_PM_TIMER
-        bool "Power Management Timer Support"
+        bool "Power Management Timer Support" if EMBEDDED
        depends on X86
-        depends on !X86_64
        default y
        help
          The Power Management Timer is available on all ACPI-capable,
@@ -298,9 +297,8 @@ config X86_PM_TIMER
          voltage scaling, unlike the commonly used Time Stamp Counter
          (TSC) timing source.
-          So, if you see messages like 'Losing too many ticks!' in the
+          You should nearly always say Y here because many modern
-          kernel logs, and/or you are using this on a notebook which
+          systems require this timer. 
-          does not yet have an HPET, you should say "Y" here.
 config ACPI_CONTAINER
        tristate "ACPI0004,PNP0A05 and PNP0A06 Container Driver (EXPERIMENTAL)"
diff --git a/drivers/char/sx.c b/drivers/char/sx.c
index c2490e270f1f..a6b4f02bdceb 100644
--- a/drivers/char/sx.c
+++ b/drivers/char/sx.c
@@ -1095,17 +1095,17 @@ static inline void sx_receive_chars (struct sx_port *port)
                sx_dprintk (SX_DEBUG_RECEIVE, "rxop=%d, c = %d.\n", rx_op, c); 
+                /* Don't copy past the end of the hardware receive buffer */
+                if (rx_op + c > 0x100) c = 0x100 - rx_op;
+                sx_dprintk (SX_DEBUG_RECEIVE, "c = %d.\n", c);
                /* Don't copy more bytes than there is room for in the buffer */
                c = tty_prepare_flip_string(tty, &rp, c);
                sx_dprintk (SX_DEBUG_RECEIVE, "c = %d.\n", c); 
-                /* Don't copy past the end of the hardware receive buffer */
-                if (rx_op + c > 0x100) c = 0x100 - rx_op;
-                sx_dprintk (SX_DEBUG_RECEIVE, "c = %d.\n", c);
                /* If for one reason or another, we can't copy more data, we're done! */
                if (c == 0) break;
@@ -2173,15 +2173,17 @@ static int probe_si (struct sx_board *board)
        if ( IS_SI1_BOARD(board)) {
                /* This should be an SI1 board, which has this
                   location writable... */
-                if (read_sx_byte (board, SI2_ISA_ID_BASE) != 0x10)
+                if (read_sx_byte (board, SI2_ISA_ID_BASE) != 0x10) {
                        func_exit ();
                        return 0; 
+                }
        } else {
                /* This should be an SI2 board, which has the bottom
                   3 bits non-writable... */
-                if (read_sx_byte (board, SI2_ISA_ID_BASE) == 0x10)
+                if (read_sx_byte (board, SI2_ISA_ID_BASE) == 0x10) {
                        func_exit ();
                        return 0; 
+                }
        }
        /* Now we're pretty much convinced that there is an SI board here, 
@@ -2192,15 +2194,17 @@ static int probe_si (struct sx_board *board)
        if ( IS_SI1_BOARD(board)) {
                /* This should be an SI1 board, which has this
                   location writable... */
-                if (read_sx_byte (board, SI2_ISA_ID_BASE) != 0x10)
+                if (read_sx_byte (board, SI2_ISA_ID_BASE) != 0x10) {
                        func_exit();
                        return 0; 
+                }
        } else {
                /* This should be an SI2 board, which has the bottom
                   3 bits non-writable... */
-                if (read_sx_byte (board, SI2_ISA_ID_BASE) == 0x10)
+                if (read_sx_byte (board, SI2_ISA_ID_BASE) == 0x10) {
                        func_exit ();
                        return 0; 
+                }
        }
        printheader ();
diff --git a/drivers/ieee1394/sbp2.c b/drivers/ieee1394/sbp2.c
index c2c776fbda01..eca92eb475a1 100644
--- a/drivers/ieee1394/sbp2.c
+++ b/drivers/ieee1394/sbp2.c
@@ -137,15 +137,15 @@ MODULE_PARM_DESC(exclusive_login, "Exclusive login to sbp2 device (default = 1)"
 /*
 * SCSI inquiry hack for really badly behaved sbp2 devices. Turn this on
 * if your sbp2 device is not properly handling the SCSI inquiry command.
- * This hack makes the inquiry look more like a typical MS Windows
+ * This hack makes the inquiry look more like a typical MS Windows inquiry
- * inquiry.
+ * by enforcing 36 byte inquiry and avoiding access to mode_sense page 8.
 *
 * If force_inquiry_hack=1 is required for your device to work,
 * please submit the logged sbp2_firmware_revision value of this device to
 * the linux1394-devel mailing list.
 */
 static int force_inquiry_hack;
-module_param(force_inquiry_hack, int, 0444);
+module_param(force_inquiry_hack, int, 0644);
 MODULE_PARM_DESC(force_inquiry_hack, "Force SCSI inquiry hack (default = 0)");
 /*
@@ -264,18 +264,17 @@ static struct hpsb_protocol_driver sbp2_driver = {
        },
 };
+/*
-/* List of device firmware's that require a forced 36 byte inquiry.  */
+ * List of device firmwares that require the inquiry hack.
+ * Yields a few false positives but did not break other devices so far.
+ */
 static u32 sbp2_broken_inquiry_list[] = {
-        0x00002800,     /* Stefan Richter <richtest@bauwesen.tu-cottbus.de> */
+        0x00002800,     /* Stefan Richter <stefanr@s5r6.in-berlin.de> */
                        /* DViCO Momobay CX-1 */
        0x00000200      /* Andreas Plesch <plesch@fas.harvard.edu> */
                        /* QPS Fire DVDBurner */
 };
-#define NUM_BROKEN_INQUIRY_DEVS \
-        (sizeof(sbp2_broken_inquiry_list)/sizeof(*sbp2_broken_inquiry_list))
 /**************************************
 * General utility functions
 **************************************/
@@ -643,9 +642,15 @@ static int sbp2_remove(struct device *dev)
        if (!scsi_id)
                return 0;
-        /* Trigger shutdown functions in scsi's highlevel. */
+        if (scsi_id->scsi_host) {
-        if (scsi_id->scsi_host)
+                /* Get rid of enqueued commands if there is no chance to
+                 * send them. */
+                if (!sbp2util_node_is_available(scsi_id))
+                        sbp2scsi_complete_all_commands(scsi_id, DID_NO_CONNECT);
+                /* scsi_remove_device() will trigger shutdown functions of SCSI
+                 * highlevel drivers which would deadlock if blocked. */
                scsi_unblock_requests(scsi_id->scsi_host);
+        }
        sdev = scsi_id->sdev;
        if (sdev) {
                scsi_id->sdev = NULL;
@@ -742,11 +747,6 @@ static struct scsi_id_instance_data *sbp2_alloc_device(struct unit_directory *ud
                hi->host = ud->ne->host;
                INIT_LIST_HEAD(&hi->scsi_ids);
-                /* Register our sbp2 status address space... */
-                hpsb_register_addrspace(&sbp2_highlevel, ud->ne->host, &sbp2_ops,
-                                        SBP2_STATUS_FIFO_ADDRESS,
-                                        SBP2_STATUS_FIFO_ADDRESS +
-                                        SBP2_STATUS_FIFO_ENTRY_TO_OFFSET(SBP2_MAX_UDS_PER_NODE+1));
 #ifdef CONFIG_IEEE1394_SBP2_PHYS_DMA
                /* Handle data movement if physical dma is not
                 * enabled/supportedon host controller */
@@ -759,6 +759,18 @@ static struct scsi_id_instance_data *sbp2_alloc_device(struct unit_directory *ud
        list_add_tail(&scsi_id->scsi_list, &hi->scsi_ids);
+        /* Register the status FIFO address range. We could use the same FIFO
+         * for targets at different nodes. However we need different FIFOs per
+         * target in order to support multi-unit devices. */
+        scsi_id->status_fifo_addr = hpsb_allocate_and_register_addrspace(
+                        &sbp2_highlevel, ud->ne->host, &sbp2_ops,
+                        sizeof(struct sbp2_status_block), sizeof(quadlet_t),
+                        ~0ULL, ~0ULL);
+        if (!scsi_id->status_fifo_addr) {
+                SBP2_ERR("failed to allocate status FIFO address range");
+                goto failed_alloc;
+        }
        /* Register our host with the SCSI stack. */
        scsi_host = scsi_host_alloc(&scsi_driver_template,
                                    sizeof(unsigned long));
@@ -997,6 +1009,10 @@ static void sbp2_remove_device(struct scsi_id_instance_data *scsi_id)
                SBP2_DMA_FREE("single query logins data");
        }
+        if (scsi_id->status_fifo_addr)
+                hpsb_unregister_addrspace(&sbp2_highlevel, hi->host,
+                        scsi_id->status_fifo_addr);
        scsi_id->ud->device.driver_data = NULL;
        SBP2_DEBUG("SBP-2 device removed, SCSI ID = %d", scsi_id->ud->id);
@@ -1075,11 +1091,10 @@ static int sbp2_query_logins(struct scsi_id_instance_data *scsi_id)
                ORB_SET_QUERY_LOGINS_RESP_LENGTH(sizeof(struct sbp2_query_logins_response));
        SBP2_DEBUG("sbp2_query_logins: reserved_resp_length initialized");
-        scsi_id->query_logins_orb->status_FIFO_lo = SBP2_STATUS_FIFO_ADDRESS_LO +
+        scsi_id->query_logins_orb->status_fifo_hi =
-                                                    SBP2_STATUS_FIFO_ENTRY_TO_OFFSET(scsi_id->ud->id);
+                ORB_SET_STATUS_FIFO_HI(scsi_id->status_fifo_addr, hi->host->node_id);
-        scsi_id->query_logins_orb->status_FIFO_hi = (ORB_SET_NODE_ID(hi->host->node_id) |
+        scsi_id->query_logins_orb->status_fifo_lo =
-                                                     SBP2_STATUS_FIFO_ADDRESS_HI);
+                ORB_SET_STATUS_FIFO_LO(scsi_id->status_fifo_addr);
-        SBP2_DEBUG("sbp2_query_logins: status FIFO initialized");
        sbp2util_cpu_to_be32_buffer(scsi_id->query_logins_orb, sizeof(struct sbp2_query_logins_orb));
@@ -1184,11 +1199,10 @@ static int sbp2_login_device(struct scsi_id_instance_data *scsi_id)
                ORB_SET_LOGIN_RESP_LENGTH(sizeof(struct sbp2_login_response));
        SBP2_DEBUG("sbp2_login_device: passwd_resp_lengths initialized");
-        scsi_id->login_orb->status_FIFO_lo = SBP2_STATUS_FIFO_ADDRESS_LO +
+        scsi_id->login_orb->status_fifo_hi =
-                                             SBP2_STATUS_FIFO_ENTRY_TO_OFFSET(scsi_id->ud->id);
+                ORB_SET_STATUS_FIFO_HI(scsi_id->status_fifo_addr, hi->host->node_id);
-        scsi_id->login_orb->status_FIFO_hi = (ORB_SET_NODE_ID(hi->host->node_id) |
+        scsi_id->login_orb->status_fifo_lo =
-                                              SBP2_STATUS_FIFO_ADDRESS_HI);
+                ORB_SET_STATUS_FIFO_LO(scsi_id->status_fifo_addr);
-        SBP2_DEBUG("sbp2_login_device: status FIFO initialized");
        /*
         * Byte swap ORB if necessary
@@ -1301,10 +1315,10 @@ static int sbp2_logout_device(struct scsi_id_instance_data *scsi_id)
        scsi_id->logout_orb->login_ID_misc |= ORB_SET_NOTIFY(1);
        scsi_id->logout_orb->reserved5 = 0x0;
-        scsi_id->logout_orb->status_FIFO_lo = SBP2_STATUS_FIFO_ADDRESS_LO +
+        scsi_id->logout_orb->status_fifo_hi =
-                                              SBP2_STATUS_FIFO_ENTRY_TO_OFFSET(scsi_id->ud->id);
+                ORB_SET_STATUS_FIFO_HI(scsi_id->status_fifo_addr, hi->host->node_id);
-        scsi_id->logout_orb->status_FIFO_hi = (ORB_SET_NODE_ID(hi->host->node_id) |
+        scsi_id->logout_orb->status_fifo_lo =
-                                               SBP2_STATUS_FIFO_ADDRESS_HI);
+                ORB_SET_STATUS_FIFO_LO(scsi_id->status_fifo_addr);
        /*
         * Byte swap ORB if necessary
@@ -1366,10 +1380,10 @@ static int sbp2_reconnect_device(struct scsi_id_instance_data *scsi_id)
        scsi_id->reconnect_orb->login_ID_misc |= ORB_SET_NOTIFY(1);
        scsi_id->reconnect_orb->reserved5 = 0x0;
-        scsi_id->reconnect_orb->status_FIFO_lo = SBP2_STATUS_FIFO_ADDRESS_LO +
+        scsi_id->reconnect_orb->status_fifo_hi =
-                                                 SBP2_STATUS_FIFO_ENTRY_TO_OFFSET(scsi_id->ud->id);
+                ORB_SET_STATUS_FIFO_HI(scsi_id->status_fifo_addr, hi->host->node_id);
-        scsi_id->reconnect_orb->status_FIFO_hi =
+        scsi_id->reconnect_orb->status_fifo_lo =
-                (ORB_SET_NODE_ID(hi->host->node_id) | SBP2_STATUS_FIFO_ADDRESS_HI);
+                ORB_SET_STATUS_FIFO_LO(scsi_id->status_fifo_addr);
        /*
         * Byte swap ORB if necessary
@@ -1560,7 +1574,7 @@ static void sbp2_parse_unit_directory(struct scsi_id_instance_data *scsi_id,
        /* Check for a blacklisted set of devices that require us to force
         * a 36 byte host inquiry. This can be overriden as a module param
         * (to force all hosts).  */
-        for (i = 0; i < NUM_BROKEN_INQUIRY_DEVS; i++) {
+        for (i = 0; i < ARRAY_SIZE(sbp2_broken_inquiry_list); i++) {
                if ((firmware_revision & 0xffff00) ==
                                sbp2_broken_inquiry_list[i]) {
                        SBP2_WARN("Node " NODE_BUS_FMT ": Using 36byte inquiry workaround",
@@ -2007,18 +2021,6 @@ static int sbp2_send_command(struct scsi_id_instance_data *scsi_id,
        }
        /*
-         * The scsi stack sends down a request_bufflen which does not match the
-         * length field in the scsi cdb. This causes some sbp2 devices to
-         * reject this inquiry command. Fix the request_bufflen.
-         */
-        if (*cmd == INQUIRY) {
-                if (force_inquiry_hack || scsi_id->workarounds & SBP2_BREAKAGE_INQUIRY_HACK)
-                        request_bufflen = cmd[4] = 0x24;
-                else
-                        request_bufflen = cmd[4];
-        }
-        /*
         * Now actually fill in the comamnd orb and sbp2 s/g list
         */
        sbp2_create_command_orb(scsi_id, command, cmd, SCpnt->use_sg,
@@ -2106,7 +2108,6 @@ static int sbp2_handle_status_write(struct hpsb_host *host, int nodeid, int dest
 {
        struct sbp2scsi_host_info *hi;
        struct scsi_id_instance_data *scsi_id = NULL, *scsi_id_tmp;
-        u32 id;
        struct scsi_cmnd *SCpnt = NULL;
        u32 scsi_status = SBP2_SCSI_STATUS_GOOD;
        struct sbp2_command_info *command;
@@ -2129,12 +2130,12 @@ static int sbp2_handle_status_write(struct hpsb_host *host, int nodeid, int dest
        }
        /*
-         * Find our scsi_id structure by looking at the status fifo address written to by
+         * Find our scsi_id structure by looking at the status fifo address
-         * the sbp2 device.
+         * written to by the sbp2 device.
         */
-        id = SBP2_STATUS_FIFO_OFFSET_TO_ENTRY((u32)(addr - SBP2_STATUS_FIFO_ADDRESS));
        list_for_each_entry(scsi_id_tmp, &hi->scsi_ids, scsi_list) {
-                if (scsi_id_tmp->ne->nodeid == nodeid && scsi_id_tmp->ud->id == id) {
+                if (scsi_id_tmp->ne->nodeid == nodeid &&
+                    scsi_id_tmp->status_fifo_addr == addr) {
                        scsi_id = scsi_id_tmp;
                        break;
                }
@@ -2475,7 +2476,16 @@ static void sbp2scsi_complete_command(struct scsi_id_instance_data *scsi_id,
 static int sbp2scsi_slave_alloc(struct scsi_device *sdev)
 {
-        ((struct scsi_id_instance_data *)sdev->host->hostdata[0])->sdev = sdev;
+        struct scsi_id_instance_data *scsi_id =
+                (struct scsi_id_instance_data *)sdev->host->hostdata[0];
+        scsi_id->sdev = sdev;
+        if (force_inquiry_hack ||
+            scsi_id->workarounds & SBP2_BREAKAGE_INQUIRY_HACK) {
+                sdev->inquiry_len = 36;
+                sdev->skip_ms_page_8 = 1;
+        }
        return 0;
 }
diff --git a/drivers/ieee1394/sbp2.h b/drivers/ieee1394/sbp2.h
index 900ea1d25e71..e2d357a9ea3a 100644
--- a/drivers/ieee1394/sbp2.h
+++ b/drivers/ieee1394/sbp2.h
@@ -33,15 +33,17 @@
 #define ORB_DIRECTION_NO_DATA_TRANSFER  0x2
 #define ORB_SET_NULL_PTR(value)                 ((value & 0x1) << 31)
-#define ORB_SET_NOTIFY(value)                   ((value & 0x1) << 31)
+#define ORB_SET_NOTIFY(value)                   ((value & 0x1) << 31)
-#define ORB_SET_RQ_FMT(value)                   ((value & 0x3) << 29)   /* unused ? */
+#define ORB_SET_RQ_FMT(value)                   ((value & 0x3) << 29)   /* unused ? */
 #define ORB_SET_NODE_ID(value)                  ((value & 0xffff) << 16)
-#define ORB_SET_DATA_SIZE(value)                (value & 0xffff)
+#define ORB_SET_STATUS_FIFO_HI(value, id)       (value >> 32 | ORB_SET_NODE_ID(id))
-#define ORB_SET_PAGE_SIZE(value)                ((value & 0x7) << 16)
+#define ORB_SET_STATUS_FIFO_LO(value)           (value & 0xffffffff)
-#define ORB_SET_PAGE_TABLE_PRESENT(value)       ((value & 0x1) << 19)
+#define ORB_SET_DATA_SIZE(value)                (value & 0xffff)
-#define ORB_SET_MAX_PAYLOAD(value)              ((value & 0xf) << 20)
+#define ORB_SET_PAGE_SIZE(value)                ((value & 0x7) << 16)
-#define ORB_SET_SPEED(value)                    ((value & 0x7) << 24)
+#define ORB_SET_PAGE_TABLE_PRESENT(value)       ((value & 0x1) << 19)
-#define ORB_SET_DIRECTION(value)                ((value & 0x1) << 27)
+#define ORB_SET_MAX_PAYLOAD(value)              ((value & 0xf) << 20)
+#define ORB_SET_SPEED(value)                    ((value & 0x7) << 24)
+#define ORB_SET_DIRECTION(value)                ((value & 0x1) << 27)
 struct sbp2_command_orb {
        volatile u32 next_ORB_hi;
@@ -76,8 +78,8 @@ struct sbp2_login_orb {
        u32 login_response_lo;
        u32 lun_misc;
        u32 passwd_resp_lengths;
-        u32 status_FIFO_hi;
+        u32 status_fifo_hi;
-        u32 status_FIFO_lo;
+        u32 status_fifo_lo;
 };
 #define RESPONSE_GET_LOGIN_ID(value)            (value & 0xffff)
@@ -102,8 +104,8 @@ struct sbp2_query_logins_orb {
        u32 query_response_lo;
        u32 lun_misc;
        u32 reserved_resp_length;
-        u32 status_FIFO_hi;
+        u32 status_fifo_hi;
-        u32 status_FIFO_lo;
+        u32 status_fifo_lo;
 };
 #define RESPONSE_GET_MAX_LOGINS(value)          (value & 0xffff)
@@ -123,8 +125,8 @@ struct sbp2_reconnect_orb {
        u32 reserved4;
        u32 login_ID_misc;
        u32 reserved5;
-        u32 status_FIFO_hi;
+        u32 status_fifo_hi;
-        u32 status_FIFO_lo;
+        u32 status_fifo_lo;
 };
 struct sbp2_logout_orb {
@@ -134,8 +136,8 @@ struct sbp2_logout_orb {
        u32 reserved4;
        u32 login_ID_misc;
        u32 reserved5;
-        u32 status_FIFO_hi;
+        u32 status_fifo_hi;
-        u32 status_FIFO_lo;
+        u32 status_fifo_lo;
 };
 #define PAGE_TABLE_SET_SEGMENT_BASE_HI(value)   (value & 0xffff)
@@ -195,30 +197,6 @@ struct sbp2_status_block {
 * Miscellaneous SBP2 related config rom defines
 */
-/* The status fifo address definition below is used as a base for each
- * node, which a chunk seperately assigned to each unit directory in the
- * node.  For example, 0xfffe00000000ULL is used for the first sbp2 device
- * detected on node 0, 0xfffe00000020ULL for the next sbp2 device on node
- * 0, and so on.
- *
- * Note: We could use a single status fifo address for all sbp2 devices,
- * and figure out which sbp2 device the status belongs to by looking at
- * the source node id of the status write... but, using separate addresses
- * for each sbp2 unit directory allows for better code and the ability to
- * support multiple luns within a single 1394 node.
- *
- * Also note that we choose the address range below as it is a region
- * specified for write posting, where the ohci controller will
- * automatically send an ack_complete when the status is written by the
- * sbp2 device... saving a split transaction.   =)
- */
-#define SBP2_STATUS_FIFO_ADDRESS                                0xfffe00000000ULL
-#define SBP2_STATUS_FIFO_ADDRESS_HI                             0xfffe
-#define SBP2_STATUS_FIFO_ADDRESS_LO                             0x0
-#define SBP2_STATUS_FIFO_ENTRY_TO_OFFSET(entry)                 ((entry) << 5)
-#define SBP2_STATUS_FIFO_OFFSET_TO_ENTRY(offset)                ((offset) >> 5)
 #define SBP2_UNIT_DIRECTORY_OFFSET_KEY                          0xd1
 #define SBP2_CSR_OFFSET_KEY                                     0x54
 #define SBP2_UNIT_SPEC_ID_KEY                                   0x12
@@ -258,7 +236,6 @@ struct sbp2_status_block {
 */
 #define SBP2_MAX_SG_ELEMENT_LENGTH      0xf000
-#define SBP2_MAX_UDS_PER_NODE           16      /* Maximum scsi devices per node */
 #define SBP2_MAX_SECTORS                255     /* Max sectors supported */
 #define SBP2_MAX_CMDS                   8       /* This should be safe */
@@ -338,6 +315,11 @@ struct scsi_id_instance_data {
        u32 sbp2_firmware_revision;
        /*
+         * Address for the device to write status blocks to
+         */
+        u64 status_fifo_addr;
+        /*
         * Variable used for logins, reconnects, logouts, query logins
         */
        atomic_t sbp2_login_complete;
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index e9adeb9d172f..745ca1f67b14 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -849,10 +849,16 @@ static struct mapped_device *alloc_dev(unsigned int minor, int persistent)
 static void free_dev(struct mapped_device *md)
 {
-        free_minor(md->disk->first_minor);
+        unsigned int minor = md->disk->first_minor;
+        if (md->suspended_bdev) {
+                thaw_bdev(md->suspended_bdev, NULL);
+                bdput(md->suspended_bdev);
+        }
        mempool_destroy(md->tio_pool);
        mempool_destroy(md->io_pool);
        del_gendisk(md->disk);
+        free_minor(minor);
        put_disk(md->disk);
        blk_put_queue(md->queue);
        kfree(md);
diff --git a/drivers/mtd/chips/cfi_cmdset_0001.c b/drivers/mtd/chips/cfi_cmdset_0001.c
index ded2c33f5b85..1c074d63ff3a 100644
--- a/drivers/mtd/chips/cfi_cmdset_0001.c
+++ b/drivers/mtd/chips/cfi_cmdset_0001.c
@@ -408,6 +408,7 @@ struct mtd_info *cfi_cmdset_0001(struct map_info *map, int primary)
                cfi->chips[i].buffer_write_time = 1<<cfi->cfiq->BufWriteTimeoutTyp;
                cfi->chips[i].erase_time = 1<<cfi->cfiq->BlockEraseTimeoutTyp;
                cfi->chips[i].ref_point_counter = 0;
+                init_waitqueue_head(&(cfi->chips[i].wq));
        }
        map->fldrv = &cfi_intelext_chipdrv;
diff --git a/drivers/net/ifb.c b/drivers/net/ifb.c
index 1b699259b4ec..31fb2d75dc44 100644
--- a/drivers/net/ifb.c
+++ b/drivers/net/ifb.c
@@ -57,7 +57,7 @@ struct ifb_private {
        struct sk_buff_head     tq;
 };
-static int numifbs = 1;
+static int numifbs = 2;
 static void ri_tasklet(unsigned long dev);
 static int ifb_xmit(struct sk_buff *skb, struct net_device *dev);
diff --git a/drivers/net/r8169.c b/drivers/net/r8169.c
index 6e1018448eea..8cc0d0bbdf50 100644
--- a/drivers/net/r8169.c
+++ b/drivers/net/r8169.c
@@ -287,6 +287,20 @@ enum RTL8169_register_content {
        TxInterFrameGapShift = 24,
        TxDMAShift = 8, /* DMA burst value (0-7) is shift this many bits */
+        /* Config1 register p.24 */
+        PMEnable        = (1 << 0),     /* Power Management Enable */
+        /* Config3 register p.25 */
+        MagicPacket     = (1 << 5),     /* Wake up when receives a Magic Packet */
+        LinkUp          = (1 << 4),     /* Wake up when the cable connection is re-established */
+        /* Config5 register p.27 */
+        BWF             = (1 << 6),     /* Accept Broadcast wakeup frame */
+        MWF             = (1 << 5),     /* Accept Multicast wakeup frame */
+        UWF             = (1 << 4),     /* Accept Unicast wakeup frame */
+        LanWake         = (1 << 1),     /* LanWake enable/disable */
+        PMEStatus       = (1 << 0),     /* PME status can be reset by PCI RST# */
        /* TBICSR p.28 */
        TBIReset        = 0x80000000,
        TBILoopback     = 0x40000000,
@@ -433,6 +447,7 @@ struct rtl8169_private {
        unsigned int (*phy_reset_pending)(void __iomem *);
        unsigned int (*link_ok)(void __iomem *);
        struct work_struct task;
+        unsigned wol_enabled : 1;
 };
 MODULE_AUTHOR("Realtek and the Linux r8169 crew <netdev@vger.kernel.org>");
@@ -607,6 +622,80 @@ static void rtl8169_link_option(int idx, u8 *autoneg, u16 *speed, u8 *duplex)
        *duplex = p->duplex;
 }
+static void rtl8169_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
+{
+        struct rtl8169_private *tp = netdev_priv(dev);
+        void __iomem *ioaddr = tp->mmio_addr;
+        u8 options;
+        wol->wolopts = 0;
+#define WAKE_ANY (WAKE_PHY | WAKE_MAGIC | WAKE_UCAST | WAKE_BCAST | WAKE_MCAST)
+        wol->supported = WAKE_ANY;
+        spin_lock_irq(&tp->lock);
+        options = RTL_R8(Config1);
+        if (!(options & PMEnable))
+                goto out_unlock;
+        options = RTL_R8(Config3);
+        if (options & LinkUp)
+                wol->wolopts |= WAKE_PHY;
+        if (options & MagicPacket)
+                wol->wolopts |= WAKE_MAGIC;
+        options = RTL_R8(Config5);
+        if (options & UWF)
+                wol->wolopts |= WAKE_UCAST;
+        if (options & BWF)
+                wol->wolopts |= WAKE_BCAST;
+        if (options & MWF)
+                wol->wolopts |= WAKE_MCAST;
+out_unlock:
+        spin_unlock_irq(&tp->lock);
+}
+static int rtl8169_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
+{
+        struct rtl8169_private *tp = netdev_priv(dev);
+        void __iomem *ioaddr = tp->mmio_addr;
+        int i;
+        static struct {
+                u32 opt;
+                u16 reg;
+                u8  mask;
+        } cfg[] = {
+                { WAKE_ANY,   Config1, PMEnable },
+                { WAKE_PHY,   Config3, LinkUp },
+                { WAKE_MAGIC, Config3, MagicPacket },
+                { WAKE_UCAST, Config5, UWF },
+                { WAKE_BCAST, Config5, BWF },
+                { WAKE_MCAST, Config5, MWF },
+                { WAKE_ANY,   Config5, LanWake }
+        };
+        spin_lock_irq(&tp->lock);
+        RTL_W8(Cfg9346, Cfg9346_Unlock);
+        for (i = 0; i < ARRAY_SIZE(cfg); i++) {
+                u8 options = RTL_R8(cfg[i].reg) & ~cfg[i].mask;
+                if (wol->wolopts & cfg[i].opt)
+                        options |= cfg[i].mask;
+                RTL_W8(cfg[i].reg, options);
+        }
+        RTL_W8(Cfg9346, Cfg9346_Lock);
+        tp->wol_enabled = (wol->wolopts) ? 1 : 0;
+        spin_unlock_irq(&tp->lock);
+        return 0;
+}
 static void rtl8169_get_drvinfo(struct net_device *dev,
                                struct ethtool_drvinfo *info)
 {
@@ -1025,6 +1114,8 @@ static struct ethtool_ops rtl8169_ethtool_ops = {
        .get_tso                = ethtool_op_get_tso,
        .set_tso                = ethtool_op_set_tso,
        .get_regs               = rtl8169_get_regs,
+        .get_wol                = rtl8169_get_wol,
+        .set_wol                = rtl8169_set_wol,
        .get_strings            = rtl8169_get_strings,
        .get_stats_count        = rtl8169_get_stats_count,
        .get_ethtool_stats      = rtl8169_get_ethtool_stats,
@@ -1442,6 +1533,11 @@ rtl8169_init_board(struct pci_dev *pdev, struct net_device **dev_out,
        }
        tp->chipset = i;
+        RTL_W8(Cfg9346, Cfg9346_Unlock);
+        RTL_W8(Config1, RTL_R8(Config1) | PMEnable);
+        RTL_W8(Config5, RTL_R8(Config5) & PMEStatus);
+        RTL_W8(Cfg9346, Cfg9346_Lock);
        *ioaddr_out = ioaddr;
        *dev_out = dev;
 out:
@@ -1612,49 +1708,6 @@ rtl8169_remove_one(struct pci_dev *pdev)
        pci_set_drvdata(pdev, NULL);
 }
-#ifdef CONFIG_PM
-static int rtl8169_suspend(struct pci_dev *pdev, pm_message_t state)
-{
-        struct net_device *dev = pci_get_drvdata(pdev);
-        struct rtl8169_private *tp = netdev_priv(dev);
-        void __iomem *ioaddr = tp->mmio_addr;
-        unsigned long flags;
-        if (!netif_running(dev))
-                return 0;
-        
-        netif_device_detach(dev);
-        netif_stop_queue(dev);
-        spin_lock_irqsave(&tp->lock, flags);
-        /* Disable interrupts, stop Rx and Tx */
-        RTL_W16(IntrMask, 0);
-        RTL_W8(ChipCmd, 0);
-                
-        /* Update the error counts. */
-        tp->stats.rx_missed_errors += RTL_R32(RxMissed);
-        RTL_W32(RxMissed, 0);
-        spin_unlock_irqrestore(&tp->lock, flags);
-        
-        return 0;
-}
-static int rtl8169_resume(struct pci_dev *pdev)
-{
-        struct net_device *dev = pci_get_drvdata(pdev);
-        if (!netif_running(dev))
-            return 0;
-        netif_device_attach(dev);
-        rtl8169_hw_start(dev);
-        return 0;
-}
-                                                                                
-#endif /* CONFIG_PM */
 static void rtl8169_set_rxbufsize(struct rtl8169_private *tp,
                                  struct net_device *dev)
 {
@@ -2700,6 +2753,56 @@ static struct net_device_stats *rtl8169_get_stats(struct net_device *dev)
        return &tp->stats;
 }
+#ifdef CONFIG_PM
+static int rtl8169_suspend(struct pci_dev *pdev, pm_message_t state)
+{
+        struct net_device *dev = pci_get_drvdata(pdev);
+        struct rtl8169_private *tp = netdev_priv(dev);
+        void __iomem *ioaddr = tp->mmio_addr;
+        if (!netif_running(dev))
+                goto out;
+        netif_device_detach(dev);
+        netif_stop_queue(dev);
+        spin_lock_irq(&tp->lock);
+        rtl8169_asic_down(ioaddr);
+        tp->stats.rx_missed_errors += RTL_R32(RxMissed);
+        RTL_W32(RxMissed, 0);
+        spin_unlock_irq(&tp->lock);
+        pci_save_state(pdev);
+        pci_enable_wake(pdev, pci_choose_state(pdev, state), tp->wol_enabled);
+        pci_set_power_state(pdev, pci_choose_state(pdev, state));
+out:
+        return 0;
+}
+static int rtl8169_resume(struct pci_dev *pdev)
+{
+        struct net_device *dev = pci_get_drvdata(pdev);
+        if (!netif_running(dev))
+                goto out;
+        netif_device_attach(dev);
+        pci_set_power_state(pdev, PCI_D0);
+        pci_restore_state(pdev);
+        pci_enable_wake(pdev, PCI_D0, 0);
+        rtl8169_schedule_work(dev, rtl8169_reset_task);
+out:
+        return 0;
+}
+#endif /* CONFIG_PM */
 static struct pci_driver rtl8169_pci_driver = {
        .name           = MODULENAME,
        .id_table       = rtl8169_pci_tbl,
diff --git a/drivers/net/sis900.c b/drivers/net/sis900.c
index 3d95fa20cd88..7a952fe60be2 100644
--- a/drivers/net/sis900.c
+++ b/drivers/net/sis900.c
@@ -540,7 +540,7 @@ static int __devinit sis900_probe(struct pci_dev *pci_dev,
        printk("%2.2x.\n", net_dev->dev_addr[i]);
        /* Detect Wake on Lan support */
-        ret = inl(CFGPMC & PMESP);
+        ret = (inl(net_dev->base_addr + CFGPMC) & PMESP) >> 27;
        if (netif_msg_probe(sis_priv) && (ret & PME_D3C) == 0)
                printk(KERN_INFO "%s: Wake on LAN only available from suspend to RAM.", net_dev->name);
@@ -2040,7 +2040,7 @@ static int sis900_set_wol(struct net_device *net_dev, struct ethtool_wolinfo *wo
        if (wol->wolopts == 0) {
                pci_read_config_dword(sis_priv->pci_dev, CFGPMCSR, &cfgpmcsr);
-                cfgpmcsr |= ~PME_EN;
+                cfgpmcsr &= ~PME_EN;
                pci_write_config_dword(sis_priv->pci_dev, CFGPMCSR, cfgpmcsr);
                outl(pmctrl_bits, pmctrl_addr);
                if (netif_msg_wol(sis_priv))
diff --git a/drivers/net/skge.c b/drivers/net/skge.c
index 67fb19b8fde9..25e028b7ce48 100644
--- a/drivers/net/skge.c
+++ b/drivers/net/skge.c
@@ -879,13 +879,12 @@ static int __xm_phy_read(struct skge_hw *hw, int port, u16 reg, u16 *val)
        int i;
        xm_write16(hw, port, XM_PHY_ADDR, reg | hw->phy_addr);
-        xm_read16(hw, port, XM_PHY_DATA);
+        *val = xm_read16(hw, port, XM_PHY_DATA);
-        /* Need to wait for external PHY */
        for (i = 0; i < PHY_RETRIES; i++) {
-                udelay(1);
                if (xm_read16(hw, port, XM_MMU_CMD) & XM_MMU_PHY_RDY)
                        goto ready;
+                udelay(1);
        }
        return -ETIMEDOUT;
@@ -918,7 +917,12 @@ static int xm_phy_write(struct skge_hw *hw, int port, u16 reg, u16 val)
 ready:
        xm_write16(hw, port, XM_PHY_DATA, val);
-        return 0;
+        for (i = 0; i < PHY_RETRIES; i++) {
+                if (!(xm_read16(hw, port, XM_MMU_CMD) & XM_MMU_PHY_BUSY))
+                        return 0;
+                udelay(1);
+        }
+        return -ETIMEDOUT;
 }
 static void genesis_init(struct skge_hw *hw)
@@ -1168,13 +1172,17 @@ static void genesis_mac_init(struct skge_hw *hw, int port)
        u32 r;
        const u8 zero[6]  = { 0 };
-        /* Clear MIB counters */
+        for (i = 0; i < 10; i++) {
-        xm_write16(hw, port, XM_STAT_CMD,
+                skge_write16(hw, SK_REG(port, TX_MFF_CTRL1),
-                        XM_SC_CLR_RXC | XM_SC_CLR_TXC);
+                             MFF_SET_MAC_RST);
-        /* Clear two times according to Errata #3 */
+                if (skge_read16(hw, SK_REG(port, TX_MFF_CTRL1)) & MFF_SET_MAC_RST)
-        xm_write16(hw, port, XM_STAT_CMD,
+                        goto reset_ok;
-                        XM_SC_CLR_RXC | XM_SC_CLR_TXC);
+                udelay(1);
+        }
+        printk(KERN_WARNING PFX "%s: genesis reset failed\n", dev->name);
+ reset_ok:
        /* Unreset the XMAC. */
        skge_write16(hw, SK_REG(port, TX_MFF_CTRL1), MFF_CLR_MAC_RST);
@@ -1191,7 +1199,7 @@ static void genesis_mac_init(struct skge_hw *hw, int port)
                r |= GP_DIR_2|GP_IO_2;
        skge_write32(hw, B2_GP_IO, r);
-        skge_read32(hw, B2_GP_IO);
        /* Enable GMII interface */
        xm_write16(hw, port, XM_HW_CFG, XM_HW_GMII_MD);
@@ -1205,6 +1213,13 @@ static void genesis_mac_init(struct skge_hw *hw, int port)
        for (i = 1; i < 16; i++)
                xm_outaddr(hw, port, XM_EXM(i), zero);
+        /* Clear MIB counters */
+        xm_write16(hw, port, XM_STAT_CMD,
+                        XM_SC_CLR_RXC | XM_SC_CLR_TXC);
+        /* Clear two times according to Errata #3 */
+        xm_write16(hw, port, XM_STAT_CMD,
+                        XM_SC_CLR_RXC | XM_SC_CLR_TXC);
        /* configure Rx High Water Mark (XM_RX_HI_WM) */
        xm_write16(hw, port, XM_RX_HI_WM, 1450);
@@ -2170,8 +2185,10 @@ static int skge_up(struct net_device *dev)
        skge->tx_avail = skge->tx_ring.count - 1;
        /* Enable IRQ from port */
+        spin_lock_irq(&hw->hw_lock);
        hw->intr_mask |= portirqmask[port];
        skge_write32(hw, B0_IMSK, hw->intr_mask);
+        spin_unlock_irq(&hw->hw_lock);
        /* Initialize MAC */
        spin_lock_bh(&hw->phy_lock);
@@ -2229,8 +2246,10 @@ static int skge_down(struct net_device *dev)
        else
                yukon_stop(skge);
+        spin_lock_irq(&hw->hw_lock);
        hw->intr_mask &= ~portirqmask[skge->port];
        skge_write32(hw, B0_IMSK, hw->intr_mask);
+        spin_unlock_irq(&hw->hw_lock);
        /* Stop transmitter */
        skge_write8(hw, Q_ADDR(txqaddr[port], Q_CSR), CSR_STOP);
@@ -2678,8 +2697,7 @@ static int skge_poll(struct net_device *dev, int *budget)
        /* restart receiver */
        wmb();
-        skge_write8(hw, Q_ADDR(rxqaddr[skge->port], Q_CSR),
+        skge_write8(hw, Q_ADDR(rxqaddr[skge->port], Q_CSR), CSR_START);
-                    CSR_START | CSR_IRQ_CL_F);
        *budget -= work_done;
        dev->quota -= work_done;
@@ -2687,10 +2705,11 @@ static int skge_poll(struct net_device *dev, int *budget)
        if (work_done >=  to_do)
                return 1; /* not done */
-        netif_rx_complete(dev);
+        spin_lock_irq(&hw->hw_lock);
-        hw->intr_mask |= portirqmask[skge->port];
+        __netif_rx_complete(dev);
-        skge_write32(hw, B0_IMSK, hw->intr_mask);
+        hw->intr_mask |= portirqmask[skge->port];
-        skge_read32(hw, B0_IMSK);
+        skge_write32(hw, B0_IMSK, hw->intr_mask);
+        spin_unlock_irq(&hw->hw_lock);
        return 0;
 }
@@ -2850,18 +2869,10 @@ static void skge_extirq(unsigned long data)
        }
        spin_unlock(&hw->phy_lock);
-        local_irq_disable();
+        spin_lock_irq(&hw->hw_lock);
        hw->intr_mask |= IS_EXT_REG;
        skge_write32(hw, B0_IMSK, hw->intr_mask);
-        local_irq_enable();
+        spin_unlock_irq(&hw->hw_lock);
-}
-static inline void skge_wakeup(struct net_device *dev)
-{
-        struct skge_port *skge = netdev_priv(dev);
-        prefetch(skge->rx_ring.to_clean);
-        netif_rx_schedule(dev);
 }
 static irqreturn_t skge_intr(int irq, void *dev_id, struct pt_regs *regs)
@@ -2872,15 +2883,17 @@ static irqreturn_t skge_intr(int irq, void *dev_id, struct pt_regs *regs)
        if (status == 0 || status == ~0) /* hotplug or shared irq */
                return IRQ_NONE;
-        status &= hw->intr_mask;
+        spin_lock(&hw->hw_lock);
        if (status & IS_R1_F) {
+                skge_write8(hw, Q_ADDR(Q_R1, Q_CSR), CSR_IRQ_CL_F);
                hw->intr_mask &= ~IS_R1_F;
-                skge_wakeup(hw->dev[0]);
+                netif_rx_schedule(hw->dev[0]);
        }
        if (status & IS_R2_F) {
+                skge_write8(hw, Q_ADDR(Q_R2, Q_CSR), CSR_IRQ_CL_F);
                hw->intr_mask &= ~IS_R2_F;
-                skge_wakeup(hw->dev[1]);
+                netif_rx_schedule(hw->dev[1]);
        }
        if (status & IS_XA1_F)
@@ -2922,6 +2935,7 @@ static irqreturn_t skge_intr(int irq, void *dev_id, struct pt_regs *regs)
        }
        skge_write32(hw, B0_IMSK, hw->intr_mask);
+        spin_unlock(&hw->hw_lock);
        return IRQ_HANDLED;
 }
@@ -3290,6 +3304,7 @@ static int __devinit skge_probe(struct pci_dev *pdev,
        hw->pdev = pdev;
        spin_lock_init(&hw->phy_lock);
+        spin_lock_init(&hw->hw_lock);
        tasklet_init(&hw->ext_tasklet, skge_extirq, (unsigned long) hw);
        hw->regs = ioremap_nocache(pci_resource_start(pdev, 0), 0x4000);
diff --git a/drivers/net/skge.h b/drivers/net/skge.h
index 2efdacc290e5..941f12a333b6 100644
--- a/drivers/net/skge.h
+++ b/drivers/net/skge.h
@@ -2402,6 +2402,7 @@ struct skge_hw {
        struct tasklet_struct ext_tasklet;
        spinlock_t           phy_lock;
+        spinlock_t           hw_lock;
 };
 enum {
diff --git a/drivers/net/sky2.c b/drivers/net/sky2.c
index bfeba5b9cd7a..ca8160d68229 100644
--- a/drivers/net/sky2.c
+++ b/drivers/net/sky2.c
@@ -195,11 +195,11 @@ static int sky2_set_power_state(struct sky2_hw *hw, pci_power_t state)
        pr_debug("sky2_set_power_state %d\n", state);
        sky2_write8(hw, B2_TST_CTRL1, TST_CFG_WRITE_ON);
-        pci_read_config_word(hw->pdev, hw->pm_cap + PCI_PM_PMC, &power_control);
+        power_control = sky2_pci_read16(hw, hw->pm_cap + PCI_PM_PMC);
        vaux = (sky2_read16(hw, B0_CTST) & Y2_VAUX_AVAIL) &&
                (power_control & PCI_PM_CAP_PME_D3cold);
-        pci_read_config_word(hw->pdev, hw->pm_cap + PCI_PM_CTRL, &power_control);
+        power_control = sky2_pci_read16(hw, hw->pm_cap + PCI_PM_CTRL);
        power_control |= PCI_PM_CTRL_PME_STATUS;
        power_control &= ~(PCI_PM_CTRL_STATE_MASK);
@@ -223,7 +223,7 @@ static int sky2_set_power_state(struct sky2_hw *hw, pci_power_t state)
                        sky2_write8(hw, B2_Y2_CLK_GATE, 0);
                /* Turn off phy power saving */
-                pci_read_config_dword(hw->pdev, PCI_DEV_REG1, &reg1);
+                reg1 = sky2_pci_read32(hw, PCI_DEV_REG1);
                reg1 &= ~(PCI_Y2_PHY1_POWD | PCI_Y2_PHY2_POWD);
                /* looks like this XL is back asswards .. */
@@ -232,18 +232,28 @@ static int sky2_set_power_state(struct sky2_hw *hw, pci_power_t state)
                        if (hw->ports > 1)
                                reg1 |= PCI_Y2_PHY2_COMA;
                }
-                pci_write_config_dword(hw->pdev, PCI_DEV_REG1, reg1);
+                if (hw->chip_id == CHIP_ID_YUKON_EC_U) {
+                        sky2_pci_write32(hw, PCI_DEV_REG3, 0);
+                        reg1 = sky2_pci_read32(hw, PCI_DEV_REG4);
+                        reg1 &= P_ASPM_CONTROL_MSK;
+                        sky2_pci_write32(hw, PCI_DEV_REG4, reg1);
+                        sky2_pci_write32(hw, PCI_DEV_REG5, 0);
+                }
+                sky2_pci_write32(hw, PCI_DEV_REG1, reg1);
                break;
        case PCI_D3hot:
        case PCI_D3cold:
                /* Turn on phy power saving */
-                pci_read_config_dword(hw->pdev, PCI_DEV_REG1, &reg1);
+                reg1 = sky2_pci_read32(hw, PCI_DEV_REG1);
                if (hw->chip_id == CHIP_ID_YUKON_XL && hw->chip_rev > 1)
                        reg1 &= ~(PCI_Y2_PHY1_POWD | PCI_Y2_PHY2_POWD);
                else
                        reg1 |= (PCI_Y2_PHY1_POWD | PCI_Y2_PHY2_POWD);
-                pci_write_config_dword(hw->pdev, PCI_DEV_REG1, reg1);
+                sky2_pci_write32(hw, PCI_DEV_REG1, reg1);
                if (hw->chip_id == CHIP_ID_YUKON_XL && hw->chip_rev > 1)
                        sky2_write8(hw, B2_Y2_CLK_GATE, 0);
@@ -265,7 +275,7 @@ static int sky2_set_power_state(struct sky2_hw *hw, pci_power_t state)
                ret = -1;
        }
-        pci_write_config_byte(hw->pdev, hw->pm_cap + PCI_PM_CTRL, power_control);
+        sky2_pci_write16(hw, hw->pm_cap + PCI_PM_CTRL, power_control);
        sky2_write8(hw, B2_TST_CTRL1, TST_CFG_WRITE_OFF);
        return ret;
 }
@@ -463,16 +473,31 @@ static void sky2_phy_init(struct sky2_hw *hw, unsigned port)
                ledover |= PHY_M_LED_MO_RX(MO_LED_OFF);
        }
-        gm_phy_write(hw, port, PHY_MARV_LED_CTRL, ledctrl);
+        if (hw->chip_id == CHIP_ID_YUKON_EC_U && hw->chip_rev >= 2) {
+                /* apply fixes in PHY AFE */
+                gm_phy_write(hw, port, 22, 255);
+                /* increase differential signal amplitude in 10BASE-T */
+                gm_phy_write(hw, port, 24, 0xaa99);
+                gm_phy_write(hw, port, 23, 0x2011);
-        if (sky2->autoneg == AUTONEG_DISABLE || sky2->speed == SPEED_100) {
+                /* fix for IEEE A/B Symmetry failure in 1000BASE-T */
-                /* turn on 100 Mbps LED (LED_LINK100) */
+                gm_phy_write(hw, port, 24, 0xa204);
-                ledover |= PHY_M_LED_MO_100(MO_LED_ON);
+                gm_phy_write(hw, port, 23, 0x2002);
-        }
-        if (ledover)
+                /* set page register to 0 */
-                gm_phy_write(hw, port, PHY_MARV_LED_OVER, ledover);
+                gm_phy_write(hw, port, 22, 0);
+        } else {
+                gm_phy_write(hw, port, PHY_MARV_LED_CTRL, ledctrl);
+                if (sky2->autoneg == AUTONEG_DISABLE || sky2->speed == SPEED_100) {
+                        /* turn on 100 Mbps LED (LED_LINK100) */
+                        ledover |= PHY_M_LED_MO_100(MO_LED_ON);
+                }
+                if (ledover)
+                        gm_phy_write(hw, port, PHY_MARV_LED_OVER, ledover);
+        }
        /* Enable phy interrupt on auto-negotiation complete (or link up) */
        if (sky2->autoneg == AUTONEG_ENABLE)
                gm_phy_write(hw, port, PHY_MARV_INT_MASK, PHY_M_IS_AN_COMPL);
@@ -953,6 +978,12 @@ static int sky2_rx_start(struct sky2_port *sky2)
        sky2->rx_put = sky2->rx_next = 0;
        sky2_qset(hw, rxq);
+        if (hw->chip_id == CHIP_ID_YUKON_EC_U && hw->chip_rev >= 2) {
+                /* MAC Rx RAM Read is controlled by hardware */
+                sky2_write32(hw, Q_ADDR(rxq, Q_F), F_M_RX_RAM_DIS);
+        }
        sky2_prefetch_init(hw, rxq, sky2->rx_le_map, RX_LE_SIZE - 1);
        rx_set_checksum(sky2);
@@ -1035,9 +1066,10 @@ static int sky2_up(struct net_device *dev)
                    RB_RST_SET);
        sky2_qset(hw, txqaddr[port]);
-        if (hw->chip_id == CHIP_ID_YUKON_EC_U)
-                sky2_write16(hw, Q_ADDR(txqaddr[port], Q_AL), 0x1a0);
+        /* Set almost empty threshold */
+        if (hw->chip_id == CHIP_ID_YUKON_EC_U && hw->chip_rev == 1)
+                sky2_write16(hw, Q_ADDR(txqaddr[port], Q_AL), 0x1a0);
        sky2_prefetch_init(hw, txqaddr[port], sky2->tx_le_map,
                           TX_RING_SIZE - 1);
@@ -1047,8 +1079,10 @@ static int sky2_up(struct net_device *dev)
                goto err_out;
        /* Enable interrupts from phy/mac for port */
+        spin_lock_irq(&hw->hw_lock);
        hw->intr_mask |= (port == 0) ? Y2_IS_PORT_1 : Y2_IS_PORT_2;
        sky2_write32(hw, B0_IMSK, hw->intr_mask);
+        spin_unlock_irq(&hw->hw_lock);
        return 0;
 err_out:
@@ -1348,10 +1382,10 @@ static int sky2_down(struct net_device *dev)
        netif_stop_queue(dev);
        /* Disable port IRQ */
-        local_irq_disable();
+        spin_lock_irq(&hw->hw_lock);
        hw->intr_mask &= ~((sky2->port == 0) ? Y2_IS_IRQ_PHY1 : Y2_IS_IRQ_PHY2);
        sky2_write32(hw, B0_IMSK, hw->intr_mask);
-        local_irq_enable();
+        spin_unlock_irq(&hw->hw_lock);
        flush_scheduled_work();
@@ -1633,10 +1667,10 @@ static void sky2_phy_task(void *arg)
 out:
        up(&sky2->phy_sema);
-        local_irq_disable();
+        spin_lock_irq(&hw->hw_lock);
        hw->intr_mask |= (sky2->port == 0) ? Y2_IS_IRQ_PHY1 : Y2_IS_IRQ_PHY2;
        sky2_write32(hw, B0_IMSK, hw->intr_mask);
-        local_irq_enable();
+        spin_unlock_irq(&hw->hw_lock);
 }
@@ -1863,6 +1897,17 @@ static int sky2_poll(struct net_device *dev0, int *budget)
        sky2_write32(hw, STAT_CTRL, SC_STAT_CLR_IRQ);
+        /*
+         * Kick the STAT_LEV_TIMER_CTRL timer.
+         * This fixes my hangs on Yukon-EC (0xb6) rev 1.
+         * The if clause is there to start the timer only if it has been
+         * configured correctly and not been disabled via ethtool.
+         */
+        if (sky2_read8(hw, STAT_LEV_TIMER_CTRL) == TIM_START) {
+                sky2_write8(hw, STAT_LEV_TIMER_CTRL, TIM_STOP);
+                sky2_write8(hw, STAT_LEV_TIMER_CTRL, TIM_START);
+        }
        hwidx = sky2_read16(hw, STAT_PUT_IDX);
        BUG_ON(hwidx >= STATUS_RING_SIZE);
        rmb();
@@ -1945,16 +1990,19 @@ exit_loop:
        sky2_tx_check(hw, 0, tx_done[0]);
        sky2_tx_check(hw, 1, tx_done[1]);
+        if (sky2_read8(hw, STAT_TX_TIMER_CTRL) == TIM_START) {
+                sky2_write8(hw, STAT_TX_TIMER_CTRL, TIM_STOP);
+                sky2_write8(hw, STAT_TX_TIMER_CTRL, TIM_START);
+        }
        if (likely(work_done < to_do)) {
-                /* need to restart TX timer */
+                spin_lock_irq(&hw->hw_lock);
-                if (is_ec_a1(hw)) {
+                __netif_rx_complete(dev0);
-                        sky2_write8(hw, STAT_TX_TIMER_CTRL, TIM_STOP);
-                        sky2_write8(hw, STAT_TX_TIMER_CTRL, TIM_START);
-                }
-                netif_rx_complete(dev0);
                hw->intr_mask |= Y2_IS_STAT_BMU;
                sky2_write32(hw, B0_IMSK, hw->intr_mask);
+                spin_unlock_irq(&hw->hw_lock);
                return 0;
        } else {
                *budget -= work_done;
@@ -2017,13 +2065,13 @@ static void sky2_hw_intr(struct sky2_hw *hw)
        if (status & (Y2_IS_MST_ERR | Y2_IS_IRQ_STAT)) {
                u16 pci_err;
-                pci_read_config_word(hw->pdev, PCI_STATUS, &pci_err);
+                pci_err = sky2_pci_read16(hw, PCI_STATUS);
                if (net_ratelimit())
                        printk(KERN_ERR PFX "%s: pci hw error (0x%x)\n",
                               pci_name(hw->pdev), pci_err);
                sky2_write8(hw, B2_TST_CTRL1, TST_CFG_WRITE_ON);
-                pci_write_config_word(hw->pdev, PCI_STATUS,
+                sky2_pci_write16(hw, PCI_STATUS,
                                      pci_err | PCI_STATUS_ERROR_BITS);
                sky2_write8(hw, B2_TST_CTRL1, TST_CFG_WRITE_OFF);
        }
@@ -2032,7 +2080,7 @@ static void sky2_hw_intr(struct sky2_hw *hw)
                /* PCI-Express uncorrectable Error occurred */
                u32 pex_err;
-                pci_read_config_dword(hw->pdev, PEX_UNC_ERR_STAT, &pex_err);
+                pex_err = sky2_pci_read32(hw, PEX_UNC_ERR_STAT);
                if (net_ratelimit())
                        printk(KERN_ERR PFX "%s: pci express error (0x%x)\n",
@@ -2040,7 +2088,7 @@ static void sky2_hw_intr(struct sky2_hw *hw)
                /* clear the interrupt */
                sky2_write32(hw, B2_TST_CTRL1, TST_CFG_WRITE_ON);
-                pci_write_config_dword(hw->pdev, PEX_UNC_ERR_STAT,
+                sky2_pci_write32(hw, PEX_UNC_ERR_STAT,
                                       0xffffffffUL);
                sky2_write32(hw, B2_TST_CTRL1, TST_CFG_WRITE_OFF);
@@ -2086,6 +2134,7 @@ static void sky2_phy_intr(struct sky2_hw *hw, unsigned port)
        hw->intr_mask &= ~(port == 0 ? Y2_IS_IRQ_PHY1 : Y2_IS_IRQ_PHY2);
        sky2_write32(hw, B0_IMSK, hw->intr_mask);
        schedule_work(&sky2->phy_task);
 }
@@ -2099,6 +2148,7 @@ static irqreturn_t sky2_intr(int irq, void *dev_id, struct pt_regs *regs)
        if (status == 0 || status == ~0)
                return IRQ_NONE;
+        spin_lock(&hw->hw_lock);
        if (status & Y2_IS_HW_ERR)
                sky2_hw_intr(hw);
@@ -2127,7 +2177,7 @@ static irqreturn_t sky2_intr(int irq, void *dev_id, struct pt_regs *regs)
        sky2_write32(hw, B0_Y2_SP_ICR, 2);
-        sky2_read32(hw, B0_IMSK);
+        spin_unlock(&hw->hw_lock);
        return IRQ_HANDLED;
 }
@@ -2170,7 +2220,7 @@ static int sky2_reset(struct sky2_hw *hw)
 {
        u16 status;
        u8 t8, pmd_type;
-        int i, err;
+        int i;
        sky2_write8(hw, B0_CTST, CS_RST_CLR);
@@ -2192,25 +2242,18 @@ static int sky2_reset(struct sky2_hw *hw)
        sky2_write8(hw, B0_CTST, CS_RST_CLR);
        /* clear PCI errors, if any */
-        err = pci_read_config_word(hw->pdev, PCI_STATUS, &status);
+        status = sky2_pci_read16(hw, PCI_STATUS);
-        if (err)
-                goto pci_err;
        sky2_write8(hw, B2_TST_CTRL1, TST_CFG_WRITE_ON);
-        err = pci_write_config_word(hw->pdev, PCI_STATUS,
+        sky2_pci_write16(hw, PCI_STATUS, status | PCI_STATUS_ERROR_BITS);
-                                    status | PCI_STATUS_ERROR_BITS);
-        if (err)
-                goto pci_err;
        sky2_write8(hw, B0_CTST, CS_MRST_CLR);
        /* clear any PEX errors */
-        if (pci_find_capability(hw->pdev, PCI_CAP_ID_EXP)) {
+        if (pci_find_capability(hw->pdev, PCI_CAP_ID_EXP)) 
-                err = pci_write_config_dword(hw->pdev, PEX_UNC_ERR_STAT,
+                sky2_pci_write32(hw, PEX_UNC_ERR_STAT, 0xffffffffUL);
-                                                 0xffffffffUL);
-                if (err)
-                        goto pci_err;
-        }
        pmd_type = sky2_read8(hw, B2_PMD_TYP);
        hw->copper = !(pmd_type == 'L' || pmd_type == 'S');
@@ -2309,8 +2352,7 @@ static int sky2_reset(struct sky2_hw *hw)
                        sky2_write8(hw, STAT_FIFO_ISR_WM, 16);
                sky2_write32(hw, STAT_TX_TIMER_INI, sky2_us2clk(hw, 1000));
-                sky2_write32(hw, STAT_LEV_TIMER_INI, sky2_us2clk(hw, 100));
+                sky2_write32(hw, STAT_ISR_TIMER_INI, sky2_us2clk(hw, 7));
-                sky2_write32(hw, STAT_ISR_TIMER_INI, sky2_us2clk(hw, 20));
        }
        /* enable status unit */
@@ -2321,14 +2363,6 @@ static int sky2_reset(struct sky2_hw *hw)
        sky2_write8(hw, STAT_ISR_TIMER_CTRL, TIM_START);
        return 0;
-pci_err:
-        /* This is to catch a BIOS bug workaround where
-         * mmconfig table doesn't have other buses.
-         */
-        printk(KERN_ERR PFX "%s: can't access PCI config space\n",
-               pci_name(hw->pdev));
-        return err;
 }
 static u32 sky2_supported_modes(const struct sky2_hw *hw)
@@ -2852,11 +2886,11 @@ static int sky2_set_coalesce(struct net_device *dev,
            (ecmd->rx_coalesce_usecs_irq < tmin || ecmd->rx_coalesce_usecs_irq > tmax))
                return -EINVAL;
-        if (ecmd->tx_max_coalesced_frames > 0xffff)
+        if (ecmd->tx_max_coalesced_frames >= TX_RING_SIZE-1)
                return -EINVAL;
-        if (ecmd->rx_max_coalesced_frames > 0xff)
+        if (ecmd->rx_max_coalesced_frames > RX_MAX_PENDING)
                return -EINVAL;
-        if (ecmd->rx_max_coalesced_frames_irq > 0xff)
+        if (ecmd->rx_max_coalesced_frames_irq >RX_MAX_PENDING)
                return -EINVAL;
        if (ecmd->tx_coalesce_usecs == 0)
@@ -3198,17 +3232,6 @@ static int __devinit sky2_probe(struct pci_dev *pdev,
                }
        }
-#ifdef __BIG_ENDIAN
-        /* byte swap descriptors in hardware */
-        {
-                u32 reg;
-                pci_read_config_dword(pdev, PCI_DEV_REG2, &reg);
-                reg |= PCI_REV_DESC;
-                pci_write_config_dword(pdev, PCI_DEV_REG2, reg);
-        }
-#endif
        err = -ENOMEM;
        hw = kzalloc(sizeof(*hw), GFP_KERNEL);
        if (!hw) {
@@ -3226,6 +3249,18 @@ static int __devinit sky2_probe(struct pci_dev *pdev,
                goto err_out_free_hw;
        }
        hw->pm_cap = pm_cap;
+        spin_lock_init(&hw->hw_lock);
+#ifdef __BIG_ENDIAN
+        /* byte swap descriptors in hardware */
+        {
+                u32 reg;
+                reg = sky2_pci_read32(hw, PCI_DEV_REG2);
+                reg |= PCI_REV_DESC;
+                sky2_pci_write32(hw, PCI_DEV_REG2, reg);
+        }
+#endif
        /* ring for status responses */
        hw->st_le = pci_alloc_consistent(hw->pdev, STATUS_LE_BYTES,
diff --git a/drivers/net/sky2.h b/drivers/net/sky2.h
index fd12c289a238..3edb98075e0a 100644
--- a/drivers/net/sky2.h
+++ b/drivers/net/sky2.h
@@ -5,14 +5,22 @@
 #define _SKY2_H
 /* PCI config registers */
-#define PCI_DEV_REG1    0x40
+enum {
-#define PCI_DEV_REG2    0x44
+        PCI_DEV_REG1    = 0x40,
-#define PCI_DEV_STATUS  0x7c
+        PCI_DEV_REG2    = 0x44,
-#define PCI_OS_PCI_X    (1<<26)
+        PCI_DEV_STATUS  = 0x7c,
+        PCI_DEV_REG3    = 0x80,
+        PCI_DEV_REG4    = 0x84,
+        PCI_DEV_REG5    = 0x88,
+};
-#define PEX_LNK_STAT    0xf2
+enum {
-#define PEX_UNC_ERR_STAT 0x104
+        PEX_DEV_CAP     = 0xe4,
-#define PEX_DEV_CTRL    0xe8
+        PEX_DEV_CTRL    = 0xe8,
+        PEX_DEV_STA     = 0xea,
+        PEX_LNK_STAT    = 0xf2,
+        PEX_UNC_ERR_STAT= 0x104,
+};
 /* Yukon-2 */
 enum pci_dev_reg_1 {
@@ -37,6 +45,25 @@ enum pci_dev_reg_2 {
        PCI_USEDATA64   = 1<<0,         /* Use 64Bit Data bus ext */
 };
+/*      PCI_OUR_REG_4           32 bit  Our Register 4 (Yukon-ECU only) */
+enum pci_dev_reg_4 {
+                                        /* (Link Training & Status State Machine) */
+        P_TIMER_VALUE_MSK       = 0xffL<<16,    /* Bit 23..16:  Timer Value Mask */
+                                        /* (Active State Power Management) */
+        P_FORCE_ASPM_REQUEST    = 1<<15, /* Force ASPM Request (A1 only) */
+        P_ASPM_GPHY_LINK_DOWN   = 1<<14, /* GPHY Link Down (A1 only) */
+        P_ASPM_INT_FIFO_EMPTY   = 1<<13, /* Internal FIFO Empty (A1 only) */
+        P_ASPM_CLKRUN_REQUEST   = 1<<12, /* CLKRUN Request (A1 only) */
+        P_ASPM_FORCE_CLKREQ_ENA = 1<<4, /* Force CLKREQ Enable (A1b only) */
+        P_ASPM_CLKREQ_PAD_CTL   = 1<<3, /* CLKREQ PAD Control (A1 only) */
+        P_ASPM_A1_MODE_SELECT   = 1<<2, /* A1 Mode Select (A1 only) */
+        P_CLK_GATE_PEX_UNIT_ENA = 1<<1, /* Enable Gate PEX Unit Clock */
+        P_CLK_GATE_ROOT_COR_ENA = 1<<0, /* Enable Gate Root Core Clock */
+        P_ASPM_CONTROL_MSK      = P_FORCE_ASPM_REQUEST | P_ASPM_GPHY_LINK_DOWN
+                                  | P_ASPM_CLKRUN_REQUEST | P_ASPM_INT_FIFO_EMPTY,
+};
 #define PCI_STATUS_ERROR_BITS (PCI_STATUS_DETECTED_PARITY | \
                               PCI_STATUS_SIG_SYSTEM_ERROR | \
@@ -507,6 +534,16 @@ enum {
 };
 #define Q_ADDR(reg, offs) (B8_Q_REGS + (reg) + (offs))
+/*      Q_F                             32 bit  Flag Register */
+enum {
+        F_ALM_FULL      = 1<<27, /* Rx FIFO: almost full */
+        F_EMPTY         = 1<<27, /* Tx FIFO: empty flag */
+        F_FIFO_EOF      = 1<<26, /* Tag (EOF Flag) bit in FIFO */
+        F_WM_REACHED    = 1<<25, /* Watermark reached */
+        F_M_RX_RAM_DIS  = 1<<24, /* MAC Rx RAM Read Port disable */
+        F_FIFO_LEVEL    = 0x1fL<<16, /* Bit 23..16:     # of Qwords in FIFO */
+        F_WATER_MARK    = 0x0007ffL, /* Bit 10.. 0:     Watermark */
+};
 /* Queue Prefetch Unit Offsets, use Y2_QADDR() to address (Yukon-2 only)*/
 enum {
@@ -909,10 +946,12 @@ enum {
        PHY_BCOM_ID1_C0 = 0x6044,
        PHY_BCOM_ID1_C5 = 0x6047,
-        PHY_MARV_ID1_B0 = 0x0C23, /* Yukon (PHY 88E1011) */
+        PHY_MARV_ID1_B0 = 0x0C23, /* Yukon      (PHY 88E1011) */
        PHY_MARV_ID1_B2 = 0x0C25, /* Yukon-Plus (PHY 88E1011) */
-        PHY_MARV_ID1_C2 = 0x0CC2, /* Yukon-EC (PHY 88E1111) */
+        PHY_MARV_ID1_C2 = 0x0CC2, /* Yukon-EC   (PHY 88E1111) */
-        PHY_MARV_ID1_Y2 = 0x0C91, /* Yukon-2 (PHY 88E1112) */
+        PHY_MARV_ID1_Y2 = 0x0C91, /* Yukon-2    (PHY 88E1112) */
+        PHY_MARV_ID1_FE = 0x0C83, /* Yukon-FE   (PHY 88E3082 Rev.A1) */
+        PHY_MARV_ID1_ECU= 0x0CB0, /* Yukon-ECU  (PHY 88E1149 Rev.B2?) */
 };
 /* Advertisement register bits */
@@ -1837,8 +1876,9 @@ struct sky2_port {
 struct sky2_hw {
        void __iomem         *regs;
        struct pci_dev       *pdev;
-        u32                  intr_mask;
        struct net_device    *dev[2];
+        spinlock_t           hw_lock;
+        u32                  intr_mask;
        int                  pm_cap;
        int                  msi;
@@ -1912,4 +1952,25 @@ static inline void gma_set_addr(struct sky2_hw *hw, unsigned port, unsigned reg,
        gma_write16(hw, port, reg+4,(u16) addr[2] | ((u16) addr[3] << 8));
        gma_write16(hw, port, reg+8,(u16) addr[4] | ((u16) addr[5] << 8));
 }
+/* PCI config space access */
+static inline u32 sky2_pci_read32(const struct sky2_hw *hw, unsigned reg)
+{
+        return sky2_read32(hw, Y2_CFG_SPC + reg);
+}
+static inline u16 sky2_pci_read16(const struct sky2_hw *hw, unsigned reg)
+{
+        return sky2_read16(hw, Y2_CFG_SPC + reg);
+}
+static inline void sky2_pci_write32(struct sky2_hw *hw, unsigned reg, u32 val)
+{
+        sky2_write32(hw, Y2_CFG_SPC + reg, val);
+}
+static inline void sky2_pci_write16(struct sky2_hw *hw, unsigned reg, u16 val)
+{
+        sky2_write16(hw, Y2_CFG_SPC + reg, val);
+}
 #endif
diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c
index e7dc653d5bd6..e8e92c853e89 100644
--- a/drivers/net/tg3.c
+++ b/drivers/net/tg3.c
@@ -9408,6 +9408,15 @@ static int __devinit tg3_is_sun_570X(struct tg3 *tp)
                        return 0;
                if (venid == PCI_VENDOR_ID_SUN)
                        return 1;
+                /* TG3 chips onboard the SunBlade-2500 don't have the
+                 * subsystem-vendor-id set to PCI_VENDOR_ID_SUN but they
+                 * are distinguishable from non-Sun variants by being
+                 * named "network" by the firmware.  Non-Sun cards will
+                 * show up as being named "ethernet".
+                 */
+                if (!strcmp(pcp->prom_name, "network"))
+                        return 1;
        }
        return 0;
 }
diff --git a/drivers/net/tlan.c b/drivers/net/tlan.c
index c2506b56a186..12076f8f942c 100644
--- a/drivers/net/tlan.c
+++ b/drivers/net/tlan.c
@@ -536,6 +536,7 @@ static int __devinit TLan_probe1(struct pci_dev *pdev,
        u16                device_id;
        int                reg, rc = -ENODEV;
+#ifdef CONFIG_PCI
        if (pdev) {
                rc = pci_enable_device(pdev);
                if (rc)
@@ -547,6 +548,7 @@ static int __devinit TLan_probe1(struct pci_dev *pdev,
                        goto err_out;
                }
        }
+#endif  /*  CONFIG_PCI  */
        dev = alloc_etherdev(sizeof(TLanPrivateInfo));
        if (dev == NULL) {
diff --git a/drivers/scsi/libata-core.c b/drivers/scsi/libata-core.c
index 5f1d7580218d..4f91b0dc572b 100644
--- a/drivers/scsi/libata-core.c
+++ b/drivers/scsi/libata-core.c
@@ -82,6 +82,10 @@ int atapi_enabled = 0;
 module_param(atapi_enabled, int, 0444);
 MODULE_PARM_DESC(atapi_enabled, "Enable discovery of ATAPI devices (0=off, 1=on)");
+int libata_fua = 0;
+module_param_named(fua, libata_fua, int, 0444);
+MODULE_PARM_DESC(fua, "FUA support (0=off, 1=on)");
 MODULE_AUTHOR("Jeff Garzik");
 MODULE_DESCRIPTION("Library module for ATA devices");
 MODULE_LICENSE("GPL");
diff --git a/drivers/scsi/libata-scsi.c b/drivers/scsi/libata-scsi.c
index 07b1e7cc61df..59503c9ccac9 100644
--- a/drivers/scsi/libata-scsi.c
+++ b/drivers/scsi/libata-scsi.c
@@ -1708,6 +1708,8 @@ static int ata_dev_supports_fua(u16 *id)
 {
        unsigned char model[41], fw[9];
+        if (!libata_fua)
+                return 0;
        if (!ata_id_has_fua(id))
                return 0;
diff --git a/drivers/scsi/libata.h b/drivers/scsi/libata.h
index e03ce48b7b4b..fddaf479a544 100644
--- a/drivers/scsi/libata.h
+++ b/drivers/scsi/libata.h
@@ -41,6 +41,7 @@ struct ata_scsi_args {
 /* libata-core.c */
 extern int atapi_enabled;
+extern int libata_fua;
 extern struct ata_queued_cmd *ata_qc_new_init(struct ata_port *ap,
                                      struct ata_device *dev);
 extern int ata_rwcmd_protocol(struct ata_queued_cmd *qc);
diff --git a/drivers/scsi/sata_sil.c b/drivers/scsi/sata_sil.c
index 17f74d3c10e7..9face3c6aa21 100644
--- a/drivers/scsi/sata_sil.c
+++ b/drivers/scsi/sata_sil.c
@@ -49,11 +49,13 @@
 #define DRV_VERSION     "0.9"
 enum {
+        SIL_FLAG_RERR_ON_DMA_ACT = (1 << 29),
        SIL_FLAG_MOD15WRITE     = (1 << 30),
        sil_3112                = 0,
        sil_3112_m15w           = 1,
-        sil_3114                = 2,
+        sil_3512                = 2,
+        sil_3114                = 3,
        SIL_FIFO_R0             = 0x40,
        SIL_FIFO_W0             = 0x41,
@@ -90,7 +92,7 @@ static void sil_post_set_mode (struct ata_port *ap);
 static const struct pci_device_id sil_pci_tbl[] = {
        { 0x1095, 0x3112, PCI_ANY_ID, PCI_ANY_ID, 0, 0, sil_3112_m15w },
        { 0x1095, 0x0240, PCI_ANY_ID, PCI_ANY_ID, 0, 0, sil_3112_m15w },
-        { 0x1095, 0x3512, PCI_ANY_ID, PCI_ANY_ID, 0, 0, sil_3112 },
+        { 0x1095, 0x3512, PCI_ANY_ID, PCI_ANY_ID, 0, 0, sil_3512 },
        { 0x1095, 0x3114, PCI_ANY_ID, PCI_ANY_ID, 0, 0, sil_3114 },
        { 0x1002, 0x436e, PCI_ANY_ID, PCI_ANY_ID, 0, 0, sil_3112_m15w },
        { 0x1002, 0x4379, PCI_ANY_ID, PCI_ANY_ID, 0, 0, sil_3112_m15w },
@@ -185,7 +187,8 @@ static const struct ata_port_info sil_port_info[] = {
                .mwdma_mask     = 0x07,                 /* mwdma0-2 */
                .udma_mask      = 0x3f,                 /* udma0-5 */
                .port_ops       = &sil_ops,
-        }, /* sil_3112_15w - keep it sync'd w/ sil_3112 */
+        },
+        /* sil_3112_15w - keep it sync'd w/ sil_3112 */
        {
                .sht            = &sil_sht,
                .host_flags     = ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY |
@@ -195,11 +198,24 @@ static const struct ata_port_info sil_port_info[] = {
                .mwdma_mask     = 0x07,                 /* mwdma0-2 */
                .udma_mask      = 0x3f,                 /* udma0-5 */
                .port_ops       = &sil_ops,
-        }, /* sil_3114 */
+        },
+        /* sil_3512 */
        {
                .sht            = &sil_sht,
                .host_flags     = ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY |
-                                  ATA_FLAG_SRST | ATA_FLAG_MMIO,
+                                  ATA_FLAG_SRST | ATA_FLAG_MMIO |
+                                  SIL_FLAG_RERR_ON_DMA_ACT,
+                .pio_mask       = 0x1f,                 /* pio0-4 */
+                .mwdma_mask     = 0x07,                 /* mwdma0-2 */
+                .udma_mask      = 0x3f,                 /* udma0-5 */
+                .port_ops       = &sil_ops,
+        },
+        /* sil_3114 */
+        {
+                .sht            = &sil_sht,
+                .host_flags     = ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY |
+                                  ATA_FLAG_SRST | ATA_FLAG_MMIO |
+                                  SIL_FLAG_RERR_ON_DMA_ACT,
                .pio_mask       = 0x1f,                 /* pio0-4 */
                .mwdma_mask     = 0x07,                 /* mwdma0-2 */
                .udma_mask      = 0x3f,                 /* udma0-5 */
@@ -216,12 +232,13 @@ static const struct {
        unsigned long scr;      /* SATA control register block */
        unsigned long sien;     /* SATA Interrupt Enable register */
        unsigned long xfer_mode;/* data transfer mode register */
+        unsigned long sfis_cfg; /* SATA FIS reception config register */
 } sil_port[] = {
        /* port 0 ... */
-        { 0x80, 0x8A, 0x00, 0x100, 0x148, 0xb4 },
+        { 0x80, 0x8A, 0x00, 0x100, 0x148, 0xb4, 0x14c },
-        { 0xC0, 0xCA, 0x08, 0x180, 0x1c8, 0xf4 },
+        { 0xC0, 0xCA, 0x08, 0x180, 0x1c8, 0xf4, 0x1cc },
-        { 0x280, 0x28A, 0x200, 0x300, 0x348, 0x2b4 },
+        { 0x280, 0x28A, 0x200, 0x300, 0x348, 0x2b4, 0x34c },
-        { 0x2C0, 0x2CA, 0x208, 0x380, 0x3c8, 0x2f4 },
+        { 0x2C0, 0x2CA, 0x208, 0x380, 0x3c8, 0x2f4, 0x3cc },
        /* ... port 3 */
 };
@@ -471,6 +488,23 @@ static int sil_init_one (struct pci_dev *pdev, const struct pci_device_id *ent)
                dev_printk(KERN_WARNING, &pdev->dev,
                         "cache line size not set.  Driver may not function\n");
+        /* Apply R_ERR on DMA activate FIS errata workaround */
+        if (probe_ent->host_flags & SIL_FLAG_RERR_ON_DMA_ACT) {
+                int cnt;
+                for (i = 0, cnt = 0; i < probe_ent->n_ports; i++) {
+                        tmp = readl(mmio_base + sil_port[i].sfis_cfg);
+                        if ((tmp & 0x3) != 0x01)
+                                continue;
+                        if (!cnt)
+                                dev_printk(KERN_INFO, &pdev->dev,
+                                           "Applying R_ERR on DMA activate "
+                                           "FIS errata fix\n");
+                        writel(tmp & ~0x3, mmio_base + sil_port[i].sfis_cfg);
+                        cnt++;
+                }
+        }
        if (ent->driver_data == sil_3114) {
                irq_mask = SIL_MASK_4PORT;
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 930db398d107..9d9872347f56 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -89,6 +89,11 @@
 #define SD_MAX_RETRIES          5
 #define SD_PASSTHROUGH_RETRIES  1
+/*
+ * Size of the initial data buffer for mode and read capacity data
+ */
+#define SD_BUF_SIZE             512
 static void scsi_disk_release(struct kref *kref);
 struct scsi_disk {
@@ -1239,7 +1244,7 @@ sd_do_mode_sense(struct scsi_device *sdp, int dbd, int modepage,
 /*
 * read write protect setting, if possible - called only in sd_revalidate_disk()
- * called with buffer of length 512
+ * called with buffer of length SD_BUF_SIZE
 */
 static void
 sd_read_write_protect_flag(struct scsi_disk *sdkp, char *diskname,
@@ -1297,7 +1302,7 @@ sd_read_write_protect_flag(struct scsi_disk *sdkp, char *diskname,
 /*
 * sd_read_cache_type - called only from sd_revalidate_disk()
- * called with buffer of length 512
+ * called with buffer of length SD_BUF_SIZE
 */
 static void
 sd_read_cache_type(struct scsi_disk *sdkp, char *diskname,
@@ -1342,6 +1347,8 @@ sd_read_cache_type(struct scsi_disk *sdkp, char *diskname,
        /* Take headers and block descriptors into account */
        len += data.header_length + data.block_descriptor_length;
+        if (len > SD_BUF_SIZE)
+                goto bad_sense;
        /* Get the data */
        res = sd_do_mode_sense(sdp, dbd, modepage, buffer, len, &data, &sshdr);
@@ -1354,6 +1361,12 @@ sd_read_cache_type(struct scsi_disk *sdkp, char *diskname,
                int ct = 0;
                int offset = data.header_length + data.block_descriptor_length;
+                if (offset >= SD_BUF_SIZE - 2) {
+                        printk(KERN_ERR "%s: malformed MODE SENSE response",
+                                diskname);
+                        goto defaults;
+                }
                if ((buffer[offset] & 0x3f) != modepage) {
                        printk(KERN_ERR "%s: got wrong page\n", diskname);
                        goto defaults;
@@ -1398,6 +1411,7 @@ defaults:
               diskname);
        sdkp->WCE = 0;
        sdkp->RCD = 0;
+        sdkp->DPOFUA = 0;
 }
 /**
@@ -1421,7 +1435,7 @@ static int sd_revalidate_disk(struct gendisk *disk)
        if (!scsi_device_online(sdp))
                goto out;
-        buffer = kmalloc(512, GFP_KERNEL | __GFP_DMA);
+        buffer = kmalloc(SD_BUF_SIZE, GFP_KERNEL | __GFP_DMA);
        if (!buffer) {
                printk(KERN_WARNING "(sd_revalidate_disk:) Memory allocation "
                       "failure.\n");
diff --git a/drivers/serial/8250.c b/drivers/serial/8250.c
index 244e8ff11977..7aca22c9976d 100644
--- a/drivers/serial/8250.c
+++ b/drivers/serial/8250.c
@@ -2326,6 +2326,12 @@ static struct uart_driver serial8250_reg = {
        .cons                   = SERIAL8250_CONSOLE,
 };
+/*
+ * early_serial_setup - early registration for 8250 ports
+ *
+ * Setup an 8250 port structure prior to console initialisation.  Use
+ * after console initialisation will cause undefined behaviour.
+ */
 int __init early_serial_setup(struct uart_port *port)
 {
        if (port->line >= ARRAY_SIZE(serial8250_ports))
diff --git a/drivers/video/Kconfig b/drivers/video/Kconfig
index e64ed16bd42f..f5079c78ba4e 100644
--- a/drivers/video/Kconfig
+++ b/drivers/video/Kconfig
@@ -520,7 +520,7 @@ config FB_GBE
 config FB_GBE_MEM
        int "Video memory size in MB"
        depends on FB_GBE
-        default 8
+        default 4
        help
          This is the amount of memory reserved for the framebuffer,
          which can be any value between 1MB and 8MB.
diff --git a/drivers/video/asiliantfb.c b/drivers/video/asiliantfb.c
index 69f75547865d..c924d81f7978 100644
--- a/drivers/video/asiliantfb.c
+++ b/drivers/video/asiliantfb.c
@@ -322,32 +322,29 @@ static int asiliantfb_setcolreg(u_int regno, u_int red, u_int green, u_int blue,
        writeb(green, mmio_base + 0x791);
        writeb(blue, mmio_base + 0x791);
-        switch(p->var.bits_per_pixel) {
+        if (regno < 16) {
-        case 15:
+                switch(p->var.red.offset) {
-                if (regno < 16) {
+                case 10: /* RGB 555 */
                        ((u32 *)(p->pseudo_palette))[regno] =
                                ((red & 0xf8) << 7) |
                                ((green & 0xf8) << 2) |
                                ((blue & 0xf8) >> 3);
-                }
+                        break;
-                break;
+                case 11: /* RGB 565 */
-        case 16:
-                if (regno < 16) {
                        ((u32 *)(p->pseudo_palette))[regno] =
                                ((red & 0xf8) << 8) |
                                ((green & 0xfc) << 3) |
                                ((blue & 0xf8) >> 3);
-                }
+                        break;
-                break;
+                case 16: /* RGB 888 */
-        case 24:
-                if (regno < 24) {
                        ((u32 *)(p->pseudo_palette))[regno] =
                                (red << 16)  |
                                (green << 8) |
                                (blue);
+                        break;
                }
-                break;
        }
        return 0;
 }
diff --git a/drivers/video/au1100fb.c b/drivers/video/au1100fb.c
index 2406899f1207..3d04b2def0f1 100644
--- a/drivers/video/au1100fb.c
+++ b/drivers/video/au1100fb.c
@@ -49,6 +49,7 @@
 #include <linux/interrupt.h>
 #include <linux/ctype.h>
 #include <linux/dma-mapping.h>
+#include <linux/platform_device.h>
 #include <asm/mach-au1x00/au1000.h>
@@ -406,7 +407,7 @@ int au1100fb_fb_mmap(struct fb_info *fbi, struct vm_area_struct *vma)
        vma->vm_flags |= VM_IO;
-        if (io_remap_page_range(vma, vma->vm_start, off,
+        if (io_remap_pfn_range(vma, vma->vm_start, off >> PAGE_SHIFT,
                                vma->vm_end - vma->vm_start,
                                vma->vm_page_prot)) {
                return -EAGAIN;
diff --git a/drivers/video/console/vgacon.c b/drivers/video/console/vgacon.c
index 12d9329d1408..5a86978537d2 100644
--- a/drivers/video/console/vgacon.c
+++ b/drivers/video/console/vgacon.c
@@ -509,57 +509,60 @@ static int vgacon_doresize(struct vc_data *c,
 {
        unsigned long flags;
        unsigned int scanlines = height * c->vc_font.height;
-        u8 scanlines_lo, r7, vsync_end, mode, max_scan;
+        u8 scanlines_lo = 0, r7 = 0, vsync_end = 0, mode, max_scan;
        spin_lock_irqsave(&vga_lock, flags);
-        outb_p(VGA_CRTC_MAX_SCAN, vga_video_port_reg);
-        max_scan = inb_p(vga_video_port_val);
-        if (max_scan & 0x80)
-                scanlines <<= 1;
        vgacon_xres = width * VGA_FONTWIDTH;
        vgacon_yres = height * c->vc_font.height;
-        outb_p(VGA_CRTC_MODE, vga_video_port_reg);
+        if (vga_video_type >= VIDEO_TYPE_VGAC) {
-        mode = inb_p(vga_video_port_val);
+                outb_p(VGA_CRTC_MAX_SCAN, vga_video_port_reg);
+                max_scan = inb_p(vga_video_port_val);
-        if (mode & 0x04)
+                if (max_scan & 0x80)
-                scanlines >>= 1;
+                        scanlines <<= 1;
-        scanlines -= 1;
+                outb_p(VGA_CRTC_MODE, vga_video_port_reg);
-        scanlines_lo = scanlines & 0xff;
+                mode = inb_p(vga_video_port_val);
-        outb_p(VGA_CRTC_OVERFLOW, vga_video_port_reg);
+                if (mode & 0x04)
-        r7 = inb_p(vga_video_port_val) & ~0x42;
+                        scanlines >>= 1;
-        if (scanlines & 0x100)
+                scanlines -= 1;
-                r7 |= 0x02;
+                scanlines_lo = scanlines & 0xff;
-        if (scanlines & 0x200)
-                r7 |= 0x40;
-        /* deprotect registers */
+                outb_p(VGA_CRTC_OVERFLOW, vga_video_port_reg);
-        outb_p(VGA_CRTC_V_SYNC_END, vga_video_port_reg);
+                r7 = inb_p(vga_video_port_val) & ~0x42;
-        vsync_end = inb_p(vga_video_port_val);
-        outb_p(VGA_CRTC_V_SYNC_END, vga_video_port_reg);
+                if (scanlines & 0x100)
-        outb_p(vsync_end & ~0x80, vga_video_port_val);
+                        r7 |= 0x02;
+                if (scanlines & 0x200)
+                        r7 |= 0x40;
+                /* deprotect registers */
+                outb_p(VGA_CRTC_V_SYNC_END, vga_video_port_reg);
+                vsync_end = inb_p(vga_video_port_val);
+                outb_p(VGA_CRTC_V_SYNC_END, vga_video_port_reg);
+                outb_p(vsync_end & ~0x80, vga_video_port_val);
+        }
        outb_p(VGA_CRTC_H_DISP, vga_video_port_reg);
        outb_p(width - 1, vga_video_port_val);
        outb_p(VGA_CRTC_OFFSET, vga_video_port_reg);
        outb_p(width >> 1, vga_video_port_val);
-        outb_p(VGA_CRTC_V_DISP_END, vga_video_port_reg);
+        if (vga_video_type >= VIDEO_TYPE_VGAC) {
-        outb_p(scanlines_lo, vga_video_port_val);
+                outb_p(VGA_CRTC_V_DISP_END, vga_video_port_reg);
-        outb_p(VGA_CRTC_OVERFLOW, vga_video_port_reg);
+                outb_p(scanlines_lo, vga_video_port_val);
-        outb_p(r7,vga_video_port_val);
+                outb_p(VGA_CRTC_OVERFLOW, vga_video_port_reg);
+                outb_p(r7,vga_video_port_val);
-        /* reprotect registers */
+                /* reprotect registers */
-        outb_p(VGA_CRTC_V_SYNC_END, vga_video_port_reg);
+                outb_p(VGA_CRTC_V_SYNC_END, vga_video_port_reg);
-        outb_p(vsync_end, vga_video_port_val);
+                outb_p(vsync_end, vga_video_port_val);
+        }
        spin_unlock_irqrestore(&vga_lock, flags);
        return 0;
 }
diff --git a/drivers/video/gbefb.c b/drivers/video/gbefb.c
index c9a7cdf6d543..5e25b9860196 100644
--- a/drivers/video/gbefb.c
+++ b/drivers/video/gbefb.c
@@ -656,12 +656,15 @@ static int gbefb_set_par(struct fb_info *info)
        switch (bytesPerPixel) {
        case 1:
                SET_GBE_FIELD(WID, TYP, val, GBE_CMODE_I8);
+                info->fix.visual = FB_VISUAL_PSEUDOCOLOR;
                break;
        case 2:
                SET_GBE_FIELD(WID, TYP, val, GBE_CMODE_ARGB5);
+                info->fix.visual = FB_VISUAL_TRUECOLOR;
                break;
        case 4:
                SET_GBE_FIELD(WID, TYP, val, GBE_CMODE_RGB8);
+                info->fix.visual = FB_VISUAL_TRUECOLOR;
                break;
        }
        SET_GBE_FIELD(WID, BUF, val, GBE_BMODE_BOTH);
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 1b117a441298..c2eac2a50bd2 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -938,6 +938,11 @@ static int load_elf_binary(struct linux_binprm * bprm, struct pt_regs * regs)
                kfree(elf_interpreter);
        } else {
                elf_entry = loc->elf_ex.e_entry;
+                if (BAD_ADDR(elf_entry)) {
+                        send_sig(SIGSEGV, current, 0);
+                        retval = -ENOEXEC; /* Nobody gets to see this, but.. */
+                        goto out_free_dentry;
+                }
        }
        kfree(elf_phdata);
diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index 057e60217fc5..537ac70edfe5 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -2531,18 +2531,9 @@ static int rtc_ioctl(unsigned fd, unsigned cmd, unsigned long arg)
                val32 = kval;
                return put_user(val32, (unsigned int __user *)arg);
        case RTC_IRQP_SET32:
+                return sys_ioctl(fd, RTC_IRQP_SET, arg); 
        case RTC_EPOCH_SET32:
-                ret = get_user(val32, (unsigned int __user *)arg);
+                return sys_ioctl(fd, RTC_EPOCH_SET, arg);
-                if (ret)
-                        return ret;
-                kval = val32;
-                set_fs(KERNEL_DS);
-                ret = sys_ioctl(fd, (cmd == RTC_IRQP_SET32) ?
-                                RTC_IRQP_SET : RTC_EPOCH_SET,
-                                (unsigned long)&kval);
-                set_fs(oldfs);
-                return ret;
        default:
                /* unreached */
                return -ENOIOCTLCMD;
diff --git a/fs/namei.c b/fs/namei.c
index e28de846c591..557dcf395ca1 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -2224,13 +2224,17 @@ int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_de
 * and other special files.  --ADM
 */
 asmlinkage long sys_linkat(int olddfd, const char __user *oldname,
-                           int newdfd, const char __user *newname)
+                           int newdfd, const char __user *newname,
+                           int flags)
 {
        struct dentry *new_dentry;
        struct nameidata nd, old_nd;
        int error;
        char * to;
+        if (flags != 0)
+                return -EINVAL;
        to = getname(newname);
        if (IS_ERR(to))
                return PTR_ERR(to);
@@ -2263,7 +2267,7 @@ exit:
 asmlinkage long sys_link(const char __user *oldname, const char __user *newname)
 {
-        return sys_linkat(AT_FDCWD, oldname, AT_FDCWD, newname);
+        return sys_linkat(AT_FDCWD, oldname, AT_FDCWD, newname, 0);
 }
 /*
diff --git a/fs/ntfs/ChangeLog b/fs/ntfs/ChangeLog
index 02f44094bda9..9d8ffa89e2c2 100644
--- a/fs/ntfs/ChangeLog
+++ b/fs/ntfs/ChangeLog
@@ -1,9 +1,9 @@
 ToDo/Notes:
        - Find and fix bugs.
        - The only places in the kernel where a file is resized are
-          ntfs_file_write*() and ntfs_truncate() for both of which i_sem is
+          ntfs_file_write*() and ntfs_truncate() for both of which i_mutex is
          held.  Just have to be careful in read-/writepage and other helpers
-          not running under i_sem that we play nice...  Also need to be careful
+          not running under i_mutex that we play nice.  Also need to be careful
          with initialized_size extension in ntfs_file_write*() and writepage.
          UPDATE: The only things that need to be checked are the compressed
          write and the other attribute resize/write cases like index
@@ -19,6 +19,24 @@ ToDo/Notes:
        - Enable the code for setting the NT4 compatibility flag when we start
          making NTFS 1.2 specific modifications.
+2.1.26 - Minor bug fixes and updates.
+        - Fix a potential overflow in file.c where a cast to s64 was missing in
+          a left shift of a page index.
+        - The struct inode has had its i_sem semaphore changed to a mutex named
+          i_mutex.
+        - We have struct kmem_cache now so use it instead of the typedef
+          kmem_cache_t.  (Pekka Enberg)
+        - Implement support for sector sizes above 512 bytes (up to the maximum
+          supported by NTFS which is 4096 bytes).
+        - Do more detailed reporting of why we cannot mount read-write by
+          special casing the VOLUME_MODIFIED_BY_CHKDSK flag.
+        - Miscellaneous updates to layout.h.
+        - Cope with attribute list attribute having invalid flags.  Windows
+          copes with this and even chkdsk does not detect or fix this so we
+          have to cope with it, too.  Thanks to Pawel Kot for reporting the
+          problem.
 2.1.25 - (Almost) fully implement write(2) and truncate(2).
        - Change ntfs_map_runlist_nolock(), ntfs_attr_find_vcn_nolock() and
@@ -373,7 +391,7 @@ ToDo/Notes:
          single one of them had an mst error.  (Thanks to Ken MacFerrin for
          the bug report.)
        - Fix error handling in fs/ntfs/quota.c::ntfs_mark_quotas_out_of_date()
-          where we failed to release i_sem on the $Quota/$Q attribute inode.
+          where we failed to release i_mutex on the $Quota/$Q attribute inode.
        - Fix bug in handling of bad inodes in fs/ntfs/namei.c::ntfs_lookup().
        - Add mapping of unmapped buffers to all remaining code paths, i.e.
          fs/ntfs/aops.c::ntfs_write_mst_block(), mft.c::ntfs_sync_mft_mirror(),
@@ -874,7 +892,7 @@ ToDo/Notes:
          clusters. (Philipp Thomas)
        - attrib.c::load_attribute_list(): Fix bug when initialized_size is a
          multiple of the block_size but not the cluster size. (Szabolcs
-          Szakacsits <szaka@sienet.hu>)
+          Szakacsits)
 2.1.2 - Important bug fixes aleviating the hangs in statfs.
@@ -884,7 +902,7 @@ ToDo/Notes:
        - Add handling for initialized_size != data_size in compressed files.
        - Reduce function local stack usage from 0x3d4 bytes to just noise in
-          fs/ntfs/upcase.c. (Randy Dunlap <rdunlap@xenotime.net>)
+          fs/ntfs/upcase.c. (Randy Dunlap)
        - Remove compiler warnings for newer gcc.
        - Pages are no longer kmapped by mm/filemap.c::generic_file_write()
          around calls to ->{prepare,commit}_write.  Adapt NTFS appropriately
@@ -1201,11 +1219,11 @@ ToDo/Notes:
          the kernel. We probably want a kernel generic init_address_space()
          function...
        - Drop BKL from ntfs_readdir() after consultation with Al Viro. The
-          only caller of ->readdir() is vfs_readdir() which holds i_sem during
+          only caller of ->readdir() is vfs_readdir() which holds i_mutex
-          the call, and i_sem is sufficient protection against changes in the
+          during the call, and i_mutex is sufficient protection against changes
-          directory inode (including ->i_size).
+          in the directory inode (including ->i_size).
        - Use generic_file_llseek() for directories (as opposed to
-          default_llseek()) as this downs i_sem instead of the BKL which is
+          default_llseek()) as this downs i_mutex instead of the BKL which is
          what we now need for exclusion against ->f_pos changes considering we
          no longer take the BKL in ntfs_readdir().
diff --git a/fs/ntfs/Makefile b/fs/ntfs/Makefile
index d0d45d1c853a..d95fac7fdeb6 100644
--- a/fs/ntfs/Makefile
+++ b/fs/ntfs/Makefile
@@ -6,7 +6,7 @@ ntfs-objs := aops.o attrib.o collate.o compress.o debug.o dir.o file.o \
             index.o inode.o mft.o mst.o namei.o runlist.o super.o sysctl.o \
             unistr.o upcase.o
-EXTRA_CFLAGS = -DNTFS_VERSION=\"2.1.25\"
+EXTRA_CFLAGS = -DNTFS_VERSION=\"2.1.26\"
 ifeq ($(CONFIG_NTFS_DEBUG),y)
 EXTRA_CFLAGS += -DDEBUG
diff --git a/fs/ntfs/aops.c b/fs/ntfs/aops.c
index 1c0a4315876a..7e361da770b3 100644
--- a/fs/ntfs/aops.c
+++ b/fs/ntfs/aops.c
@@ -2,7 +2,7 @@
 * aops.c - NTFS kernel address space operations and page cache handling.
 *          Part of the Linux-NTFS project.
 *
- * Copyright (c) 2001-2005 Anton Altaparmakov
+ * Copyright (c) 2001-2006 Anton Altaparmakov
 * Copyright (c) 2002 Richard Russon
 *
 * This program/include file is free software; you can redistribute it and/or
@@ -200,8 +200,8 @@ static int ntfs_read_block(struct page *page)
        /* $MFT/$DATA must have its complete runlist in memory at all times. */
        BUG_ON(!ni->runlist.rl && !ni->mft_no && !NInoAttr(ni));
-        blocksize_bits = VFS_I(ni)->i_blkbits;
+        blocksize = vol->sb->s_blocksize;
-        blocksize = 1 << blocksize_bits;
+        blocksize_bits = vol->sb->s_blocksize_bits;
        if (!page_has_buffers(page)) {
                create_empty_buffers(page, blocksize, 0);
@@ -569,10 +569,8 @@ static int ntfs_write_block(struct page *page, struct writeback_control *wbc)
        BUG_ON(!NInoNonResident(ni));
        BUG_ON(NInoMstProtected(ni));
+        blocksize = vol->sb->s_blocksize;
-        blocksize_bits = vi->i_blkbits;
+        blocksize_bits = vol->sb->s_blocksize_bits;
-        blocksize = 1 << blocksize_bits;
        if (!page_has_buffers(page)) {
                BUG_ON(!PageUptodate(page));
                create_empty_buffers(page, blocksize,
@@ -949,8 +947,8 @@ static int ntfs_write_mst_block(struct page *page,
         */
        BUG_ON(!(is_mft || S_ISDIR(vi->i_mode) ||
                        (NInoAttr(ni) && ni->type == AT_INDEX_ALLOCATION)));
-        bh_size_bits = vi->i_blkbits;
+        bh_size = vol->sb->s_blocksize;
-        bh_size = 1 << bh_size_bits;
+        bh_size_bits = vol->sb->s_blocksize_bits;
        max_bhs = PAGE_CACHE_SIZE / bh_size;
        BUG_ON(!max_bhs);
        BUG_ON(max_bhs > MAX_BUF_PER_PAGE);
@@ -1596,7 +1594,7 @@ void mark_ntfs_record_dirty(struct page *page, const unsigned int ofs) {
        BUG_ON(!PageUptodate(page));
        end = ofs + ni->itype.index.block_size;
-        bh_size = 1 << VFS_I(ni)->i_blkbits;
+        bh_size = VFS_I(ni)->i_sb->s_blocksize;
        spin_lock(&mapping->private_lock);
        if (unlikely(!page_has_buffers(page))) {
                spin_unlock(&mapping->private_lock);
diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c
index fb413d3d8618..5027d3d1b3fe 100644
--- a/fs/ntfs/file.c
+++ b/fs/ntfs/file.c
@@ -1,7 +1,7 @@
 /*
 * file.c - NTFS kernel file operations.  Part of the Linux-NTFS project.
 *
- * Copyright (c) 2001-2005 Anton Altaparmakov
+ * Copyright (c) 2001-2006 Anton Altaparmakov
 *
 * This program/include file is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License as published
@@ -248,7 +248,7 @@ do_non_resident_extend:
                 * enough to make ntfs_writepage() work.
                 */
                write_lock_irqsave(&ni->size_lock, flags);
-                ni->initialized_size = (index + 1) << PAGE_CACHE_SHIFT;
+                ni->initialized_size = (s64)(index + 1) << PAGE_CACHE_SHIFT;
                if (ni->initialized_size > new_init_size)
                        ni->initialized_size = new_init_size;
                write_unlock_irqrestore(&ni->size_lock, flags);
@@ -529,8 +529,8 @@ static int ntfs_prepare_pages_for_non_resident_write(struct page **pages,
                        "index 0x%lx, nr_pages 0x%x, pos 0x%llx, bytes 0x%zx.",
                        vi->i_ino, ni->type, pages[0]->index, nr_pages,
                        (long long)pos, bytes);
-        blocksize_bits = vi->i_blkbits;
+        blocksize = vol->sb->s_blocksize;
-        blocksize = 1 << blocksize_bits;
+        blocksize_bits = vol->sb->s_blocksize_bits;
        u = 0;
        do {
                struct page *page = pages[u];
@@ -1525,7 +1525,7 @@ static inline int ntfs_commit_pages_after_non_resident_write(
        vi = pages[0]->mapping->host;
        ni = NTFS_I(vi);
-        blocksize = 1 << vi->i_blkbits;
+        blocksize = vi->i_sb->s_blocksize;
        end = pos + bytes;
        u = 0;
        do {
diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c
index ea1bd3feea1b..55263b7de9c0 100644
--- a/fs/ntfs/inode.c
+++ b/fs/ntfs/inode.c
@@ -677,13 +677,28 @@ static int ntfs_read_locked_inode(struct inode *vi)
                ntfs_debug("Attribute list found in inode 0x%lx.", vi->i_ino);
                NInoSetAttrList(ni);
                a = ctx->attr;
-                if (a->flags & ATTR_IS_ENCRYPTED ||
+                if (a->flags & ATTR_COMPRESSION_MASK) {
-                                a->flags & ATTR_COMPRESSION_MASK ||
-                                a->flags & ATTR_IS_SPARSE) {
                        ntfs_error(vi->i_sb, "Attribute list attribute is "
-                                        "compressed/encrypted/sparse.");
+                                        "compressed.");
                        goto unm_err_out;
                }
+                if (a->flags & ATTR_IS_ENCRYPTED ||
+                                a->flags & ATTR_IS_SPARSE) {
+                        if (a->non_resident) {
+                                ntfs_error(vi->i_sb, "Non-resident attribute "
+                                                "list attribute is encrypted/"
+                                                "sparse.");
+                                goto unm_err_out;
+                        }
+                        ntfs_warning(vi->i_sb, "Resident attribute list "
+                                        "attribute in inode 0x%lx is marked "
+                                        "encrypted/sparse which is not true.  "
+                                        "However, Windows allows this and "
+                                        "chkdsk does not detect or correct it "
+                                        "so we will just ignore the invalid "
+                                        "flags and pretend they are not set.",
+                                        vi->i_ino);
+                }
                /* Now allocate memory for the attribute list. */
                ni->attr_list_size = (u32)ntfs_attr_size(a);
                ni->attr_list = ntfs_malloc_nofs(ni->attr_list_size);
@@ -1809,19 +1824,33 @@ int ntfs_read_inode_mount(struct inode *vi)
        } else /* if (!err) */ {
                ATTR_LIST_ENTRY *al_entry, *next_al_entry;
                u8 *al_end;
+                static const char *es = "  Not allowed.  $MFT is corrupt.  "
+                                "You should run chkdsk.";
                ntfs_debug("Attribute list attribute found in $MFT.");
                NInoSetAttrList(ni);
                a = ctx->attr;
-                if (a->flags & ATTR_IS_ENCRYPTED ||
+                if (a->flags & ATTR_COMPRESSION_MASK) {
-                                a->flags & ATTR_COMPRESSION_MASK ||
-                                a->flags & ATTR_IS_SPARSE) {
                        ntfs_error(sb, "Attribute list attribute is "
-                                        "compressed/encrypted/sparse. Not "
+                                        "compressed.%s", es);
-                                        "allowed. $MFT is corrupt. You should "
-                                        "run chkdsk.");
                        goto put_err_out;
                }
+                if (a->flags & ATTR_IS_ENCRYPTED ||
+                                a->flags & ATTR_IS_SPARSE) {
+                        if (a->non_resident) {
+                                ntfs_error(sb, "Non-resident attribute list "
+                                                "attribute is encrypted/"
+                                                "sparse.%s", es);
+                                goto put_err_out;
+                        }
+                        ntfs_warning(sb, "Resident attribute list attribute "
+                                        "in $MFT system file is marked "
+                                        "encrypted/sparse which is not true.  "
+                                        "However, Windows allows this and "
+                                        "chkdsk does not detect or correct it "
+                                        "so we will just ignore the invalid "
+                                        "flags and pretend they are not set.");
+                }
                /* Now allocate memory for the attribute list. */
                ni->attr_list_size = (u32)ntfs_attr_size(a);
                ni->attr_list = ntfs_malloc_nofs(ni->attr_list_size);
diff --git a/fs/ntfs/layout.h b/fs/ntfs/layout.h
index f5678d5d7919..bb408d4dcbb0 100644
--- a/fs/ntfs/layout.h
+++ b/fs/ntfs/layout.h
@@ -838,15 +838,19 @@ enum {
           F_A_DEVICE, F_A_DIRECTORY, F_A_SPARSE_FILE, F_A_REPARSE_POINT,
           F_A_COMPRESSED, and F_A_ENCRYPTED and preserves the rest.  This mask
           is used to to obtain all flags that are valid for setting. */
        /*
-         * The following flags are only present in the FILE_NAME attribute (in
+         * The following flag is only present in the FILE_NAME attribute (in
         * the field file_attributes).
         */
        FILE_ATTR_DUP_FILE_NAME_INDEX_PRESENT   = const_cpu_to_le32(0x10000000),
        /* Note, this is a copy of the corresponding bit from the mft record,
           telling us whether this is a directory or not, i.e. whether it has
           an index root attribute or not. */
+        /*
+         * The following flag is present both in the STANDARD_INFORMATION
+         * attribute and in the FILE_NAME attribute (in the field
+         * file_attributes).
+         */
        FILE_ATTR_DUP_VIEW_INDEX_PRESENT        = const_cpu_to_le32(0x20000000),
        /* Note, this is a copy of the corresponding bit from the mft record,
           telling us whether this file has a view index present (eg. object id
@@ -1071,9 +1075,15 @@ typedef struct {
                                           modified. */
 /* 20*/ sle64 last_access_time;         /* Time this mft record was last
                                           accessed. */
-/* 28*/ sle64 allocated_size;           /* Byte size of allocated space for the
+/* 28*/ sle64 allocated_size;           /* Byte size of on-disk allocated space
-                                           data attribute. NOTE: Is a multiple
+                                           for the data attribute.  So for
-                                           of the cluster size. */
+                                           normal $DATA, this is the
+                                           allocated_size from the unnamed
+                                           $DATA attribute and for compressed
+                                           and/or sparse $DATA, this is the
+                                           compressed_size from the unnamed
+                                           $DATA attribute.  NOTE: This is a
+                                           multiple of the cluster size. */
 /* 30*/ sle64 data_size;                /* Byte size of actual data in data
                                           attribute. */
 /* 38*/ FILE_ATTR_FLAGS file_attributes;        /* Flags describing the file. */
@@ -1904,12 +1914,13 @@ enum {
        VOLUME_DELETE_USN_UNDERWAY      = const_cpu_to_le16(0x0010),
        VOLUME_REPAIR_OBJECT_ID         = const_cpu_to_le16(0x0020),
+        VOLUME_CHKDSK_UNDERWAY          = const_cpu_to_le16(0x4000),
        VOLUME_MODIFIED_BY_CHKDSK       = const_cpu_to_le16(0x8000),
-        VOLUME_FLAGS_MASK               = const_cpu_to_le16(0x803f),
+        VOLUME_FLAGS_MASK               = const_cpu_to_le16(0xc03f),
        /* To make our life easier when checking if we must mount read-only. */
-        VOLUME_MUST_MOUNT_RO_MASK       = const_cpu_to_le16(0x8027),
+        VOLUME_MUST_MOUNT_RO_MASK       = const_cpu_to_le16(0xc027),
 } __attribute__ ((__packed__));
 typedef le16 VOLUME_FLAGS;
diff --git a/fs/ntfs/mft.c b/fs/ntfs/mft.c
index 0c65cbb8c5cf..6499aafc2258 100644
--- a/fs/ntfs/mft.c
+++ b/fs/ntfs/mft.c
@@ -1,7 +1,7 @@
 /**
 * mft.c - NTFS kernel mft record operations. Part of the Linux-NTFS project.
 *
- * Copyright (c) 2001-2005 Anton Altaparmakov
+ * Copyright (c) 2001-2006 Anton Altaparmakov
 * Copyright (c) 2002 Richard Russon
 *
 * This program/include file is free software; you can redistribute it and/or
@@ -473,7 +473,7 @@ int ntfs_sync_mft_mirror(ntfs_volume *vol, const unsigned long mft_no,
        runlist_element *rl;
        unsigned int block_start, block_end, m_start, m_end, page_ofs;
        int i_bhs, nr_bhs, err = 0;
-        unsigned char blocksize_bits = vol->mftmirr_ino->i_blkbits;
+        unsigned char blocksize_bits = vol->sb->s_blocksize_bits;
        ntfs_debug("Entering for inode 0x%lx.", mft_no);
        BUG_ON(!max_bhs);
@@ -672,8 +672,8 @@ int write_mft_record_nolock(ntfs_inode *ni, MFT_RECORD *m, int sync)
 {
        ntfs_volume *vol = ni->vol;
        struct page *page = ni->page;
-        unsigned char blocksize_bits = vol->mft_ino->i_blkbits;
+        unsigned int blocksize = vol->sb->s_blocksize;
-        unsigned int blocksize = 1 << blocksize_bits;
+        unsigned char blocksize_bits = vol->sb->s_blocksize_bits;
        int max_bhs = vol->mft_record_size / blocksize;
        struct buffer_head *bhs[max_bhs];
        struct buffer_head *bh, *head;
diff --git a/fs/ntfs/ntfs.h b/fs/ntfs/ntfs.h
index 446b5014115c..653d2a5c4899 100644
--- a/fs/ntfs/ntfs.h
+++ b/fs/ntfs/ntfs.h
@@ -50,11 +50,11 @@ typedef enum {
 /* Global variables. */
 /* Slab caches (from super.c). */
-extern kmem_cache_t *ntfs_name_cache;
+extern struct kmem_cache *ntfs_name_cache;
-extern kmem_cache_t *ntfs_inode_cache;
+extern struct kmem_cache *ntfs_inode_cache;
-extern kmem_cache_t *ntfs_big_inode_cache;
+extern struct kmem_cache *ntfs_big_inode_cache;
-extern kmem_cache_t *ntfs_attr_ctx_cache;
+extern struct kmem_cache *ntfs_attr_ctx_cache;
-extern kmem_cache_t *ntfs_index_ctx_cache;
+extern struct kmem_cache *ntfs_index_ctx_cache;
 /* The various operations structs defined throughout the driver files. */
 extern struct address_space_operations ntfs_aops;
diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c
index c3a3f1a8310b..368a8ec10668 100644
--- a/fs/ntfs/super.c
+++ b/fs/ntfs/super.c
@@ -1,7 +1,7 @@
 /*
 * super.c - NTFS kernel super block handling. Part of the Linux-NTFS project.
 *
- * Copyright (c) 2001-2005 Anton Altaparmakov
+ * Copyright (c) 2001-2006 Anton Altaparmakov
 * Copyright (c) 2001,2002 Richard Russon
 *
 * This program/include file is free software; you can redistribute it and/or
@@ -22,6 +22,7 @@
 #include <linux/stddef.h>
 #include <linux/init.h>
+#include <linux/slab.h>
 #include <linux/string.h>
 #include <linux/spinlock.h>
 #include <linux/blkdev.h>       /* For bdev_hardsect_size(). */
@@ -471,9 +472,16 @@ static int ntfs_remount(struct super_block *sb, int *flags, char *opt)
                        ntfs_error(sb, "Volume is dirty and read-only%s", es);
                        return -EROFS;
                }
+                if (vol->vol_flags & VOLUME_MODIFIED_BY_CHKDSK) {
+                        ntfs_error(sb, "Volume has been modified by chkdsk "
+                                        "and is read-only%s", es);
+                        return -EROFS;
+                }
                if (vol->vol_flags & VOLUME_MUST_MOUNT_RO_MASK) {
-                        ntfs_error(sb, "Volume has unsupported flags set and "
+                        ntfs_error(sb, "Volume has unsupported flags set "
-                                        "is read-only%s", es);
+                                        "(0x%x) and is read-only%s",
+                                        (unsigned)le16_to_cpu(vol->vol_flags),
+                                        es);
                        return -EROFS;
                }
                if (ntfs_set_volume_flags(vol, VOLUME_IS_DIRTY)) {
@@ -641,7 +649,7 @@ static struct buffer_head *read_ntfs_boot_sector(struct super_block *sb,
 {
        const char *read_err_str = "Unable to read %s boot sector.";
        struct buffer_head *bh_primary, *bh_backup;
-        long nr_blocks = NTFS_SB(sb)->nr_blocks;
+        sector_t nr_blocks = NTFS_SB(sb)->nr_blocks;
        /* Try to read primary boot sector. */
        if ((bh_primary = sb_bread(sb, 0))) {
@@ -688,13 +696,18 @@ hotfix_primary_boot_sector:
                /*
                 * If we managed to read sector zero and the volume is not
                 * read-only, copy the found, valid backup boot sector to the
-                 * primary boot sector.
+                 * primary boot sector.  Note we only copy the actual boot
+                 * sector structure, not the actual whole device sector as that
+                 * may be bigger and would potentially damage the $Boot system
+                 * file (FIXME: Would be nice to know if the backup boot sector
+                 * on a large sector device contains the whole boot loader or
+                 * just the first 512 bytes).
                 */
                if (!(sb->s_flags & MS_RDONLY)) {
                        ntfs_warning(sb, "Hot-fix: Recovering invalid primary "
                                        "boot sector from backup copy.");
                        memcpy(bh_primary->b_data, bh_backup->b_data,
-                                        sb->s_blocksize);
+                                        NTFS_BLOCK_SIZE);
                        mark_buffer_dirty(bh_primary);
                        sync_dirty_buffer(bh_primary);
                        if (buffer_uptodate(bh_primary)) {
@@ -733,9 +746,13 @@ static BOOL parse_ntfs_boot_sector(ntfs_volume *vol, const NTFS_BOOT_SECTOR *b)
                        vol->sector_size);
        ntfs_debug("vol->sector_size_bits = %i (0x%x)", vol->sector_size_bits,
                        vol->sector_size_bits);
-        if (vol->sector_size != vol->sb->s_blocksize)
+        if (vol->sector_size < vol->sb->s_blocksize) {
-                ntfs_warning(vol->sb, "The boot sector indicates a sector size "
+                ntfs_error(vol->sb, "Sector size (%i) is smaller than the "
-                                "different from the device sector size.");
+                                "device block size (%lu).  This is not "
+                                "supported.  Sorry.", vol->sector_size,
+                                vol->sb->s_blocksize);
+                return FALSE;
+        }
        ntfs_debug("sectors_per_cluster = 0x%x", b->bpb.sectors_per_cluster);
        sectors_per_cluster_bits = ffs(b->bpb.sectors_per_cluster) - 1;
        ntfs_debug("sectors_per_cluster_bits = 0x%x",
@@ -748,16 +765,11 @@ static BOOL parse_ntfs_boot_sector(ntfs_volume *vol, const NTFS_BOOT_SECTOR *b)
        ntfs_debug("vol->cluster_size = %i (0x%x)", vol->cluster_size,
                        vol->cluster_size);
        ntfs_debug("vol->cluster_size_mask = 0x%x", vol->cluster_size_mask);
-        ntfs_debug("vol->cluster_size_bits = %i (0x%x)",
+        ntfs_debug("vol->cluster_size_bits = %i", vol->cluster_size_bits);
-                        vol->cluster_size_bits, vol->cluster_size_bits);
+        if (vol->cluster_size < vol->sector_size) {
-        if (vol->sector_size > vol->cluster_size) {
+                ntfs_error(vol->sb, "Cluster size (%i) is smaller than the "
-                ntfs_error(vol->sb, "Sector sizes above the cluster size are "
+                                "sector size (%i).  This is not supported.  "
-                                "not supported.  Sorry.");
+                                "Sorry.", vol->cluster_size, vol->sector_size);
-                return FALSE;
-        }
-        if (vol->sb->s_blocksize > vol->cluster_size) {
-                ntfs_error(vol->sb, "Cluster sizes smaller than the device "
-                                "sector size are not supported.  Sorry.");
                return FALSE;
        }
        clusters_per_mft_record = b->clusters_per_mft_record;
@@ -786,11 +798,18 @@ static BOOL parse_ntfs_boot_sector(ntfs_volume *vol, const NTFS_BOOT_SECTOR *b)
         * we store $MFT/$DATA, the table of mft records in the page cache.
         */
        if (vol->mft_record_size > PAGE_CACHE_SIZE) {
-                ntfs_error(vol->sb, "Mft record size %i (0x%x) exceeds the "
+                ntfs_error(vol->sb, "Mft record size (%i) exceeds the "
-                                "page cache size on your system %lu (0x%lx).  "
+                                "PAGE_CACHE_SIZE on your system (%lu).  "
                                "This is not supported.  Sorry.",
-                                vol->mft_record_size, vol->mft_record_size,
+                                vol->mft_record_size, PAGE_CACHE_SIZE);
-                                PAGE_CACHE_SIZE, PAGE_CACHE_SIZE);
+                return FALSE;
+        }
+        /* We cannot support mft record sizes below the sector size. */
+        if (vol->mft_record_size < vol->sector_size) {
+                ntfs_error(vol->sb, "Mft record size (%i) is smaller than the "
+                                "sector size (%i).  This is not supported.  "
+                                "Sorry.", vol->mft_record_size,
+                                vol->sector_size);
                return FALSE;
        }
        clusters_per_index_record = b->clusters_per_index_record;
@@ -816,6 +835,14 @@ static BOOL parse_ntfs_boot_sector(ntfs_volume *vol, const NTFS_BOOT_SECTOR *b)
        ntfs_debug("vol->index_record_size_bits = %i (0x%x)",
                        vol->index_record_size_bits,
                        vol->index_record_size_bits);
+        /* We cannot support index record sizes below the sector size. */
+        if (vol->index_record_size < vol->sector_size) {
+                ntfs_error(vol->sb, "Index record size (%i) is smaller than "
+                                "the sector size (%i).  This is not "
+                                "supported.  Sorry.", vol->index_record_size,
+                                vol->sector_size);
+                return FALSE;
+        }
        /*
         * Get the size of the volume in clusters and check for 64-bit-ness.
         * Windows currently only uses 32 bits to save the clusters so we do
@@ -845,15 +872,18 @@ static BOOL parse_ntfs_boot_sector(ntfs_volume *vol, const NTFS_BOOT_SECTOR *b)
        }
        ll = sle64_to_cpu(b->mft_lcn);
        if (ll >= vol->nr_clusters) {
-                ntfs_error(vol->sb, "MFT LCN is beyond end of volume.  Weird.");
+                ntfs_error(vol->sb, "MFT LCN (%lli, 0x%llx) is beyond end of "
+                                "volume.  Weird.", (unsigned long long)ll,
+                                (unsigned long long)ll);
                return FALSE;
        }
        vol->mft_lcn = ll;
        ntfs_debug("vol->mft_lcn = 0x%llx", (long long)vol->mft_lcn);
        ll = sle64_to_cpu(b->mftmirr_lcn);
        if (ll >= vol->nr_clusters) {
-                ntfs_error(vol->sb, "MFTMirr LCN is beyond end of volume.  "
+                ntfs_error(vol->sb, "MFTMirr LCN (%lli, 0x%llx) is beyond end "
-                                "Weird.");
+                                "of volume.  Weird.", (unsigned long long)ll,
+                                (unsigned long long)ll);
                return FALSE;
        }
        vol->mftmirr_lcn = ll;
@@ -1822,11 +1852,24 @@ get_ctx_vol_failed:
        /* Make sure that no unsupported volume flags are set. */
        if (vol->vol_flags & VOLUME_MUST_MOUNT_RO_MASK) {
                static const char *es1a = "Volume is dirty";
-                static const char *es1b = "Volume has unsupported flags set";
+                static const char *es1b = "Volume has been modified by chkdsk";
-                static const char *es2 = ".  Run chkdsk and mount in Windows.";
+                static const char *es1c = "Volume has unsupported flags set";
-                const char *es1;
+                static const char *es2a = ".  Run chkdsk and mount in Windows.";
-                
+                static const char *es2b = ".  Mount in Windows.";
-                es1 = vol->vol_flags & VOLUME_IS_DIRTY ? es1a : es1b;
+                const char *es1, *es2;
+                es2 = es2a;
+                if (vol->vol_flags & VOLUME_IS_DIRTY)
+                        es1 = es1a;
+                else if (vol->vol_flags & VOLUME_MODIFIED_BY_CHKDSK) {
+                        es1 = es1b;
+                        es2 = es2b;
+                } else {
+                        es1 = es1c;
+                        ntfs_warning(sb, "Unsupported volume flags 0x%x "
+                                        "encountered.",
+                                        (unsigned)le16_to_cpu(vol->vol_flags));
+                }
                /* If a read-write mount, convert it to a read-only mount. */
                if (!(sb->s_flags & MS_RDONLY)) {
                        if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO |
@@ -2685,7 +2728,7 @@ static int ntfs_fill_super(struct super_block *sb, void *opt, const int silent)
        ntfs_volume *vol;
        struct buffer_head *bh;
        struct inode *tmp_ino;
-        int result;
+        int blocksize, result;
        ntfs_debug("Entering.");
 #ifndef NTFS_RW
@@ -2724,60 +2767,85 @@ static int ntfs_fill_super(struct super_block *sb, void *opt, const int silent)
        if (!parse_options(vol, (char*)opt))
                goto err_out_now;
+        /* We support sector sizes up to the PAGE_CACHE_SIZE. */
+        if (bdev_hardsect_size(sb->s_bdev) > PAGE_CACHE_SIZE) {
+                if (!silent)
+                        ntfs_error(sb, "Device has unsupported sector size "
+                                        "(%i).  The maximum supported sector "
+                                        "size on this architecture is %lu "
+                                        "bytes.",
+                                        bdev_hardsect_size(sb->s_bdev),
+                                        PAGE_CACHE_SIZE);
+                goto err_out_now;
+        }
        /*
-         * TODO: Fail safety check. In the future we should really be able to
+         * Setup the device access block size to NTFS_BLOCK_SIZE or the hard
-         * cope with this being the case, but for now just bail out.
+         * sector size, whichever is bigger.
         */
-        if (bdev_hardsect_size(sb->s_bdev) > NTFS_BLOCK_SIZE) {
+        blocksize = sb_min_blocksize(sb, NTFS_BLOCK_SIZE);
+        if (blocksize < NTFS_BLOCK_SIZE) {
                if (!silent)
-                        ntfs_error(sb, "Device has unsupported hardsect_size.");
+                        ntfs_error(sb, "Unable to set device block size.");
                goto err_out_now;
        }
+        BUG_ON(blocksize != sb->s_blocksize);
-        /* Setup the device access block size to NTFS_BLOCK_SIZE. */
+        ntfs_debug("Set device block size to %i bytes (block size bits %i).",
-        if (sb_set_blocksize(sb, NTFS_BLOCK_SIZE) != NTFS_BLOCK_SIZE) {
+                        blocksize, sb->s_blocksize_bits);
+        /* Determine the size of the device in units of block_size bytes. */
+        if (!i_size_read(sb->s_bdev->bd_inode)) {
                if (!silent)
-                        ntfs_error(sb, "Unable to set block size.");
+                        ntfs_error(sb, "Unable to determine device size.");
                goto err_out_now;
        }
-        /* Get the size of the device in units of NTFS_BLOCK_SIZE bytes. */
        vol->nr_blocks = i_size_read(sb->s_bdev->bd_inode) >>
-                        NTFS_BLOCK_SIZE_BITS;
+                        sb->s_blocksize_bits;
        /* Read the boot sector and return unlocked buffer head to it. */
        if (!(bh = read_ntfs_boot_sector(sb, silent))) {
                if (!silent)
                        ntfs_error(sb, "Not an NTFS volume.");
                goto err_out_now;
        }
        /*
-         * Extract the data from the boot sector and setup the ntfs super block
+         * Extract the data from the boot sector and setup the ntfs volume
         * using it.
         */
        result = parse_ntfs_boot_sector(vol, (NTFS_BOOT_SECTOR*)bh->b_data);
-        /* Initialize the cluster and mft allocators. */
-        ntfs_setup_allocators(vol);
        brelse(bh);
        if (!result) {
                if (!silent)
                        ntfs_error(sb, "Unsupported NTFS filesystem.");
                goto err_out_now;
        }
        /*
-         * TODO: When we start coping with sector sizes different from
+         * If the boot sector indicates a sector size bigger than the current
-         * NTFS_BLOCK_SIZE, we now probably need to set the blocksize of the
+         * device block size, switch the device block size to the sector size.
-         * device (probably to NTFS_BLOCK_SIZE).
+         * TODO: It may be possible to support this case even when the set
+         * below fails, we would just be breaking up the i/o for each sector
+         * into multiple blocks for i/o purposes but otherwise it should just
+         * work.  However it is safer to leave disabled until someone hits this
+         * error message and then we can get them to try it without the setting
+         * so we know for sure that it works.
         */
+        if (vol->sector_size > blocksize) {
+                blocksize = sb_set_blocksize(sb, vol->sector_size);
+                if (blocksize != vol->sector_size) {
+                        if (!silent)
+                                ntfs_error(sb, "Unable to set device block "
+                                                "size to sector size (%i).",
+                                                vol->sector_size);
+                        goto err_out_now;
+                }
+                BUG_ON(blocksize != sb->s_blocksize);
+                vol->nr_blocks = i_size_read(sb->s_bdev->bd_inode) >>
+                                sb->s_blocksize_bits;
+                ntfs_debug("Changed device block size to %i bytes (block size "
+                                "bits %i) to match volume sector size.",
+                                blocksize, sb->s_blocksize_bits);
+        }
+        /* Initialize the cluster and mft allocators. */
+        ntfs_setup_allocators(vol);
        /* Setup remaining fields in the super block. */
        sb->s_magic = NTFS_SB_MAGIC;
        /*
         * Ntfs allows 63 bits for the file size, i.e. correct would be:
         *      sb->s_maxbytes = ~0ULL >> 1;
@@ -2787,9 +2855,8 @@ static int ntfs_fill_super(struct super_block *sb, void *opt, const int silent)
         * without overflowing the index or to 2^63 - 1, whichever is smaller.
         */
        sb->s_maxbytes = MAX_LFS_FILESIZE;
+        /* Ntfs measures time in 100ns intervals. */
        sb->s_time_gran = 100;
        /*
         * Now load the metadata required for the page cache and our address
         * space operations to function. We do this by setting up a specialised
@@ -2987,14 +3054,14 @@ err_out_now:
 * strings of the maximum length allowed by NTFS, which is NTFS_MAX_NAME_LEN
 * (255) Unicode characters + a terminating NULL Unicode character.
 */
-kmem_cache_t *ntfs_name_cache;
+struct kmem_cache *ntfs_name_cache;
 /* Slab caches for efficient allocation/deallocation of inodes. */
-kmem_cache_t *ntfs_inode_cache;
+struct kmem_cache *ntfs_inode_cache;
-kmem_cache_t *ntfs_big_inode_cache;
+struct kmem_cache *ntfs_big_inode_cache;
 /* Init once constructor for the inode slab cache. */
-static void ntfs_big_inode_init_once(void *foo, kmem_cache_t *cachep,
+static void ntfs_big_inode_init_once(void *foo, struct kmem_cache *cachep,
                unsigned long flags)
 {
        ntfs_inode *ni = (ntfs_inode *)foo;
@@ -3008,8 +3075,8 @@ static void ntfs_big_inode_init_once(void *foo, kmem_cache_t *cachep,
 * Slab caches to optimize allocations and deallocations of attribute search
 * contexts and index contexts, respectively.
 */
-kmem_cache_t *ntfs_attr_ctx_cache;
+struct kmem_cache *ntfs_attr_ctx_cache;
-kmem_cache_t *ntfs_index_ctx_cache;
+struct kmem_cache *ntfs_index_ctx_cache;
 /* Driver wide semaphore. */
 DECLARE_MUTEX(ntfs_lock);
diff --git a/fs/ntfs/upcase.c b/fs/ntfs/upcase.c
index 879cdf1d5bd3..9101807dc81a 100644
--- a/fs/ntfs/upcase.c
+++ b/fs/ntfs/upcase.c
@@ -3,10 +3,7 @@
 *            Part of the Linux-NTFS project.
 *
 * Copyright (c) 2001 Richard Russon <ntfs@flatcap.org>
- * Copyright (c) 2001-2004 Anton Altaparmakov
+ * Copyright (c) 2001-2006 Anton Altaparmakov
- *
- * Modified for mkntfs inclusion 9 June 2001 by Anton Altaparmakov.
- * Modified for kernel inclusion 10 September 2001 by Anton Altparmakov.
 *
 * 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
@@ -75,12 +72,13 @@ ntfschar *generate_default_upcase(void)
        if (!uc)
                return uc;
        memset(uc, 0, default_upcase_len * sizeof(ntfschar));
+        /* Generate the little endian Unicode upcase table used by ntfs. */
        for (i = 0; i < default_upcase_len; i++)
                uc[i] = cpu_to_le16(i);
        for (r = 0; uc_run_table[r][0]; r++)
                for (i = uc_run_table[r][0]; i < uc_run_table[r][1]; i++)
-                        uc[i] = cpu_to_le16((le16_to_cpu(uc[i]) +
+                        uc[i] = cpu_to_le16(le16_to_cpu(uc[i]) +
-                                        uc_run_table[r][2]));
+                                        uc_run_table[r][2]);
        for (r = 0; uc_dup_table[r][0]; r++)
                for (i = uc_dup_table[r][0]; i < uc_dup_table[r][1]; i += 2)
                        uc[i + 1] = cpu_to_le16(le16_to_cpu(uc[i + 1]) - 1);
diff --git a/fs/ntfs/volume.h b/fs/ntfs/volume.h
index 375cd20a9f61..406ab55dfb32 100644
--- a/fs/ntfs/volume.h
+++ b/fs/ntfs/volume.h
@@ -2,7 +2,7 @@
 * volume.h - Defines for volume structures in NTFS Linux kernel driver. Part
 *            of the Linux-NTFS project.
 *
- * Copyright (c) 2001-2005 Anton Altaparmakov
+ * Copyright (c) 2001-2006 Anton Altaparmakov
 * Copyright (c) 2002 Richard Russon
 *
 * This program/include file is free software; you can redistribute it and/or
@@ -41,10 +41,8 @@ typedef struct {
         * structure has stabilized... (AIA)
         */
        /* Device specifics. */
-        struct super_block *sb;         /* Pointer back to the super_block,
+        struct super_block *sb;         /* Pointer back to the super_block. */
-                                           so we don't have to get the offset
+        LCN nr_blocks;                  /* Number of sb->s_blocksize bytes
-                                           every time. */
-        LCN nr_blocks;                  /* Number of NTFS_BLOCK_SIZE bytes
                                           sized blocks on the device. */
        /* Configuration provided by user at mount time. */
        unsigned long flags;            /* Miscellaneous flags, see below. */
@@ -141,8 +139,8 @@ typedef enum {
        NV_ShowSystemFiles,     /* 1: Return system files in ntfs_readdir(). */
        NV_CaseSensitive,       /* 1: Treat file names as case sensitive and
                                      create filenames in the POSIX namespace.
-                                      Otherwise be case insensitive and create
+                                      Otherwise be case insensitive but still
-                                      file names in WIN32 namespace. */
+                                      create file names in POSIX namespace. */
        NV_LogFileEmpty,        /* 1: $LogFile journal is empty. */
        NV_QuotaOutOfDate,      /* 1: $Quota is out of date. */
        NV_UsnJrnlStamped,      /* 1: $UsnJrnl has been stamped. */
@@ -153,7 +151,7 @@ typedef enum {
 * Macro tricks to expand the NVolFoo(), NVolSetFoo(), and NVolClearFoo()
 * functions.
 */
-#define NVOL_FNS(flag)                                  \
+#define DEFINE_NVOL_BIT_OPS(flag)                                       \
 static inline int NVol##flag(ntfs_volume *vol)          \
 {                                                       \
        return test_bit(NV_##flag, &(vol)->flags);      \
@@ -168,12 +166,12 @@ static inline void NVolClear##flag(ntfs_volume *vol)	\
 }
 /* Emit the ntfs volume bitops functions. */
-NVOL_FNS(Errors)
+DEFINE_NVOL_BIT_OPS(Errors)
-NVOL_FNS(ShowSystemFiles)
+DEFINE_NVOL_BIT_OPS(ShowSystemFiles)
-NVOL_FNS(CaseSensitive)
+DEFINE_NVOL_BIT_OPS(CaseSensitive)
-NVOL_FNS(LogFileEmpty)
+DEFINE_NVOL_BIT_OPS(LogFileEmpty)
-NVOL_FNS(QuotaOutOfDate)
+DEFINE_NVOL_BIT_OPS(QuotaOutOfDate)
-NVOL_FNS(UsnJrnlStamped)
+DEFINE_NVOL_BIT_OPS(UsnJrnlStamped)
-NVOL_FNS(SparseEnabled)
+DEFINE_NVOL_BIT_OPS(SparseEnabled)
 #endif /* _LINUX_NTFS_VOLUME_H */
diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c
index c66bd5e4c05c..cde5d48994ae 100644
--- a/fs/ramfs/inode.c
+++ b/fs/ramfs/inode.c
@@ -27,6 +27,7 @@
 #include <linux/fs.h>
 #include <linux/pagemap.h>
 #include <linux/highmem.h>
+#include <linux/time.h>
 #include <linux/init.h>
 #include <linux/string.h>
 #include <linux/smp_lock.h>
@@ -104,6 +105,7 @@ ramfs_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev)
                d_instantiate(dentry, inode);
                dget(dentry);   /* Extra count - pin the dentry in core */
                error = 0;
+                dir->i_mtime = dir->i_ctime = CURRENT_TIME;
        }
        return error;
 }
diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c
index 8f2beec526cf..74d8be87f983 100644
--- a/fs/xfs/linux-2.6/xfs_aops.c
+++ b/fs/xfs/linux-2.6/xfs_aops.c
@@ -540,7 +540,7 @@ xfs_probe_cluster(
        /* First sum forwards in this page */
        do {
-                if (mapped != buffer_mapped(bh))
+                if (!buffer_uptodate(bh) || (mapped != buffer_mapped(bh)))
                        return total;
                total += bh->b_size;
        } while ((bh = bh->b_this_page) != head);
diff --git a/fs/xfs/quota/xfs_qm.c b/fs/xfs/quota/xfs_qm.c
index 53a00fb217fa..7c0e39dc6189 100644
--- a/fs/xfs/quota/xfs_qm.c
+++ b/fs/xfs/quota/xfs_qm.c
@@ -68,6 +68,9 @@ kmem_zone_t	*qm_dqzone;
 kmem_zone_t     *qm_dqtrxzone;
 STATIC kmem_shaker_t    xfs_qm_shaker;
+STATIC cred_t   xfs_zerocr;
+STATIC xfs_inode_t      xfs_zeroino;
 STATIC void     xfs_qm_list_init(xfs_dqlist_t *, char *, int);
 STATIC void     xfs_qm_list_destroy(xfs_dqlist_t *);
@@ -1393,8 +1396,6 @@ xfs_qm_qino_alloc(
        xfs_trans_t     *tp;
        int             error;
        unsigned long   s;
-        cred_t          zerocr;
-        xfs_inode_t     zeroino;
        int             committed;
        tp = xfs_trans_alloc(mp, XFS_TRANS_QM_QINOCREATE);
@@ -1406,11 +1407,9 @@ xfs_qm_qino_alloc(
                xfs_trans_cancel(tp, 0);
                return error;
        }
-        memset(&zerocr, 0, sizeof(zerocr));
-        memset(&zeroino, 0, sizeof(zeroino));
-        if ((error = xfs_dir_ialloc(&tp, &zeroino, S_IFREG, 1, 0,
+        if ((error = xfs_dir_ialloc(&tp, &xfs_zeroino, S_IFREG, 1, 0,
-                                   &zerocr, 0, 1, ip, &committed))) {
+                                   &xfs_zerocr, 0, 1, ip, &committed))) {
                xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES |
                                 XFS_TRANS_ABORT);
                return error;
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 06fc061c50fc..5b413946b1c5 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -130,7 +130,8 @@ xfs_growfs_rt_alloc(
                /*
                 * Lock the inode.
                 */
-                if ((error = xfs_trans_iget(mp, tp, ino, 0, XFS_ILOCK_EXCL, &ip)))
+                if ((error = xfs_trans_iget(mp, tp, ino, 0,
+                                                XFS_ILOCK_EXCL, &ip)))
                        goto error_exit;
                XFS_BMAP_INIT(&flist, &firstblock);
                /*
@@ -170,8 +171,8 @@ xfs_growfs_rt_alloc(
                        /*
                         * Lock the bitmap inode.
                         */
-                        if ((error = xfs_trans_iget(mp, tp, ino, 0, XFS_ILOCK_EXCL,
+                        if ((error = xfs_trans_iget(mp, tp, ino, 0,
-                                        &ip)))
+                                                        XFS_ILOCK_EXCL, &ip)))
                                goto error_exit;
                        /*
                         * Get a buffer for the block.
@@ -2023,8 +2024,8 @@ xfs_growfs_rt(
                /*
                 * Lock out other callers by grabbing the bitmap inode lock.
                 */
-                if ((error = xfs_trans_iget(mp, tp, 0, mp->m_sb.sb_rbmino,
+                if ((error = xfs_trans_iget(mp, tp, mp->m_sb.sb_rbmino, 0,
-                                XFS_ILOCK_EXCL, &ip)))
+                                                XFS_ILOCK_EXCL, &ip)))
                        goto error_exit;
                ASSERT(ip == mp->m_rbmip);
                /*
@@ -2037,8 +2038,8 @@ xfs_growfs_rt(
                /*
                 * Get the summary inode into the transaction.
                 */
-                if ((error = xfs_trans_iget(mp, tp, mp->m_sb.sb_rsumino,
+                if ((error = xfs_trans_iget(mp, tp, mp->m_sb.sb_rsumino, 0,
-                                0, XFS_ILOCK_EXCL, &ip)))
+                                                XFS_ILOCK_EXCL, &ip)))
                        goto error_exit;
                ASSERT(ip == mp->m_rsumip);
                /*
@@ -2158,10 +2159,9 @@ xfs_rtallocate_extent(
        /*
         * Lock out other callers by grabbing the bitmap inode lock.
         */
-        error = xfs_trans_iget(mp, tp, mp->m_sb.sb_rbmino, 0, XFS_ILOCK_EXCL, &ip);
+        if ((error = xfs_trans_iget(mp, tp, mp->m_sb.sb_rbmino, 0,
-        if (error) {
+                                        XFS_ILOCK_EXCL, &ip)))
                return error;
-        }
        sumbp = NULL;
        /*
         * Allocate by size, or near another block, or exactly at some block.
@@ -2221,10 +2221,9 @@ xfs_rtfree_extent(
        /*
         * Synchronize by locking the bitmap inode.
         */
-        error = xfs_trans_iget(mp, tp, mp->m_sb.sb_rbmino, 0, XFS_ILOCK_EXCL, &ip);
+        if ((error = xfs_trans_iget(mp, tp, mp->m_sb.sb_rbmino, 0,
-        if (error) {
+                                        XFS_ILOCK_EXCL, &ip)))
                return error;
-        }
 #if defined(__KERNEL__) && defined(DEBUG)
        /*
         * Check to see that this whole range is currently allocated.
@@ -2365,8 +2364,8 @@ xfs_rtpick_extent(
        __uint64_t      seq;            /* sequence number of file creation */
        __uint64_t      *seqp;          /* pointer to seqno in inode */
-        error = xfs_trans_iget(mp, tp, mp->m_sb.sb_rbmino, 0, XFS_ILOCK_EXCL, &ip);
+        if ((error = xfs_trans_iget(mp, tp, mp->m_sb.sb_rbmino, 0,
-        if (error)
+                                        XFS_ILOCK_EXCL, &ip)))
                return error;
        ASSERT(ip == mp->m_rbmip);
        seqp = (__uint64_t *)&ip->i_d.di_atime;
diff --git a/include/asm-i386/desc.h b/include/asm-i386/desc.h
index 494e73bca095..89b8b82c82b3 100644
--- a/include/asm-i386/desc.h
+++ b/include/asm-i386/desc.h
@@ -24,11 +24,13 @@ struct Xgt_desc_struct {
        unsigned short pad;
 } __attribute__ ((packed));
-extern struct Xgt_desc_struct idt_descr, cpu_gdt_descr[NR_CPUS];
+extern struct Xgt_desc_struct idt_descr;
+DECLARE_PER_CPU(struct Xgt_desc_struct, cpu_gdt_descr);
 static inline struct desc_struct *get_cpu_gdt_table(unsigned int cpu)
 {
-        return ((struct desc_struct *)cpu_gdt_descr[cpu].address);
+        return (struct desc_struct *)per_cpu(cpu_gdt_descr, cpu).address;
 }
 #define load_TR_desc() __asm__ __volatile__("ltr %w0"::"q" (GDT_ENTRY_TSS*8))
diff --git a/include/asm-i386/kprobes.h b/include/asm-i386/kprobes.h
index 27cac050a60e..a0d2d74a7dda 100644
--- a/include/asm-i386/kprobes.h
+++ b/include/asm-i386/kprobes.h
@@ -27,6 +27,9 @@
 #include <linux/types.h>
 #include <linux/ptrace.h>
+#define  __ARCH_WANT_KPROBES_INSN_SLOT
+struct kprobe;
 struct pt_regs;
 typedef u8 kprobe_opcode_t;
@@ -40,14 +43,14 @@ typedef u8 kprobe_opcode_t;
 #define JPROBE_ENTRY(pentry)    (kprobe_opcode_t *)pentry
 #define ARCH_SUPPORTS_KRETPROBES
-#define arch_remove_kprobe(p)   do {} while (0)
+void arch_remove_kprobe(struct kprobe *p);
 void kretprobe_trampoline(void);
 /* Architecture specific copy of original instruction*/
 struct arch_specific_insn {
        /* copy of the original instruction */
-        kprobe_opcode_t insn[MAX_INSN_SIZE];
+        kprobe_opcode_t *insn;
 };
 struct prev_kprobe {
diff --git a/include/asm-m32r/uaccess.h b/include/asm-m32r/uaccess.h
index 0da7c47d2f01..e8ae61956a51 100644
--- a/include/asm-m32r/uaccess.h
+++ b/include/asm-m32r/uaccess.h
@@ -328,7 +328,7 @@ extern void __put_user_bad(void);
                "       .long 1b,4b\n"                                  \
                "       .long 2b,4b\n"                                  \
                ".previous"                                             \
-                : "=r"(err)                                             \
+                : "=&r"(err)                                             \
                : "r"(x), "r"(addr), "i"(-EFAULT), "0"(err)             \
                : "r14", "memory")
@@ -353,7 +353,7 @@ extern void __put_user_bad(void);
                "       .long 1b,4b\n"                                  \
                "       .long 2b,4b\n"                                  \
                ".previous"                                             \
-                : "=r"(err)                                             \
+                : "=&r"(err)                                            \
                : "r"(x), "r"(addr), "i"(-EFAULT), "0"(err)             \
                : "r14", "memory")
 #else
@@ -398,7 +398,7 @@ struct __large_struct { unsigned long buf[100]; };
                "       .balign 4\n"                                    \
                "       .long 1b,3b\n"                                  \
                ".previous"                                             \
-                : "=r"(err)                                             \
+                : "=&r"(err)                                            \
                : "r"(x), "r"(addr), "i"(-EFAULT), "0"(err)             \
                : "r14", "memory")
@@ -442,7 +442,7 @@ do {									\
                "       .balign 4\n"                                    \
                "       .long 1b,3b\n"                                  \
                ".previous"                                             \
-                : "=r"(err), "=&r"(x)                                   \
+                : "=&r"(err), "=&r"(x)                                  \
                : "r"(addr), "i"(-EFAULT), "0"(err)                     \
                : "r14", "memory")
diff --git a/include/asm-mips/atomic.h b/include/asm-mips/atomic.h
index 654b97d3e13a..2c8b853376c9 100644
--- a/include/asm-mips/atomic.h
+++ b/include/asm-mips/atomic.h
@@ -250,7 +250,10 @@ static __inline__ int atomic_sub_if_positive(int i, atomic_t * v)
                "       subu    %0, %1, %3                              \n"
                "       bltz    %0, 1f                                  \n"
                "       sc      %0, %2                                  \n"
+                "       .set    noreorder                               \n"
                "       beqzl   %0, 1b                                  \n"
+                "        subu   %0, %1, %3                              \n"
+                "       .set    reorder                                 \n"
                "       sync                                            \n"
                "1:                                                     \n"
                "       .set    mips0                                   \n"
@@ -266,7 +269,10 @@ static __inline__ int atomic_sub_if_positive(int i, atomic_t * v)
                "       subu    %0, %1, %3                              \n"
                "       bltz    %0, 1f                                  \n"
                "       sc      %0, %2                                  \n"
+                "       .set    noreorder                               \n"
                "       beqz    %0, 1b                                  \n"
+                "        subu   %0, %1, %3                              \n"
+                "       .set    reorder                                 \n"
                "       sync                                            \n"
                "1:                                                     \n"
                "       .set    mips0                                   \n"
@@ -598,7 +604,10 @@ static __inline__ long atomic64_sub_if_positive(long i, atomic64_t * v)
                "       dsubu   %0, %1, %3                              \n"
                "       bltz    %0, 1f                                  \n"
                "       scd     %0, %2                                  \n"
+                "       .set    noreorder                               \n"
                "       beqzl   %0, 1b                                  \n"
+                "        dsubu  %0, %1, %3                              \n"
+                "       .set    reorder                                 \n"
                "       sync                                            \n"
                "1:                                                     \n"
                "       .set    mips0                                   \n"
@@ -614,7 +623,10 @@ static __inline__ long atomic64_sub_if_positive(long i, atomic64_t * v)
                "       dsubu   %0, %1, %3                              \n"
                "       bltz    %0, 1f                                  \n"
                "       scd     %0, %2                                  \n"
+                "       .set    noreorder                               \n"
                "       beqz    %0, 1b                                  \n"
+                "        dsubu  %0, %1, %3                              \n"
+                "       .set    reorder                                 \n"
                "       sync                                            \n"
                "1:                                                     \n"
                "       .set    mips0                                   \n"
diff --git a/include/asm-mips/smp.h b/include/asm-mips/smp.h
index 5618f1e12f40..75c6fe7c2126 100644
--- a/include/asm-mips/smp.h
+++ b/include/asm-mips/smp.h
@@ -58,7 +58,9 @@ static inline int num_booting_cpus(void)
        return cpus_weight(cpu_callout_map);
 }
-/* These are defined by the board-specific code. */
+/*
+ * These are defined by the board-specific code.
+ */
 /*
 * Cause the function described by call_data to be executed on the passed
@@ -79,7 +81,12 @@ extern void prom_boot_secondary(int cpu, struct task_struct *idle);
 extern void prom_init_secondary(void);
 /*
- * Detect available CPUs, populate phys_cpu_present_map before smp_init
+ * Populate cpu_possible_map before smp_init, called from setup_arch.
+ */
+extern void plat_smp_setup(void);
+/*
+ * Called after init_IRQ but before __cpu_up.
 */
 extern void prom_prepare_cpus(unsigned int max_cpus);
diff --git a/include/asm-mips/system.h b/include/asm-mips/system.h
index e8e5d4143377..ddae9bae31af 100644
--- a/include/asm-mips/system.h
+++ b/include/asm-mips/system.h
@@ -322,7 +322,7 @@ static inline unsigned long __cmpxchg_u32(volatile int * m, unsigned long old,
 #endif
                "2:                                                     \n"
                "       .set    pop                                     \n"
-                : "=&r" (retval), "=m" (*m)
+                : "=&r" (retval), "=R" (*m)
                : "R" (*m), "Jr" (old), "Jr" (new)
                : "memory");
        } else if (cpu_has_llsc) {
@@ -342,7 +342,7 @@ static inline unsigned long __cmpxchg_u32(volatile int * m, unsigned long old,
 #endif
                "2:                                                     \n"
                "       .set    pop                                     \n"
-                : "=&r" (retval), "=m" (*m)
+                : "=&r" (retval), "=R" (*m)
                : "R" (*m), "Jr" (old), "Jr" (new)
                : "memory");
        } else {
@@ -379,7 +379,7 @@ static inline unsigned long __cmpxchg_u64(volatile int * m, unsigned long old,
 #endif
                "2:                                                     \n"
                "       .set    pop                                     \n"
-                : "=&r" (retval), "=m" (*m)
+                : "=&r" (retval), "=R" (*m)
                : "R" (*m), "Jr" (old), "Jr" (new)
                : "memory");
        } else if (cpu_has_llsc) {
@@ -397,7 +397,7 @@ static inline unsigned long __cmpxchg_u64(volatile int * m, unsigned long old,
 #endif
                "2:                                                     \n"
                "       .set    pop                                     \n"
-                : "=&r" (retval), "=m" (*m)
+                : "=&r" (retval), "=R" (*m)
                : "R" (*m), "Jr" (old), "Jr" (new)
                : "memory");
        } else {
diff --git a/include/asm-powerpc/eeh.h b/include/asm-powerpc/eeh.h
index b263fb2fa6e4..7dfb408fe2ca 100644
--- a/include/asm-powerpc/eeh.h
+++ b/include/asm-powerpc/eeh.h
@@ -27,6 +27,7 @@
 #include <linux/string.h>
 struct pci_dev;
+struct pci_bus;
 struct device_node;
 #ifdef CONFIG_EEH
@@ -61,7 +62,7 @@ void __init pci_addr_cache_build(void);
 */
 void eeh_add_device_early(struct device_node *);
 void eeh_add_device_tree_early(struct device_node *);
-void eeh_add_device_late(struct pci_dev *);
+void eeh_add_device_tree_late(struct pci_bus *);
 /**
 * eeh_remove_device - undo EEH setup for the indicated pci device
@@ -116,12 +117,12 @@ static inline void pci_addr_cache_build(void) { }
 static inline void eeh_add_device_early(struct device_node *dn) { }
-static inline void eeh_add_device_late(struct pci_dev *dev) { }
 static inline void eeh_remove_device(struct pci_dev *dev) { }
 static inline void eeh_add_device_tree_early(struct device_node *dn) { }
+static inline void eeh_add_device_tree_late(struct pci_bus *bus) { }
 static inline void eeh_remove_bus_device(struct pci_dev *dev) { }
 #define EEH_POSSIBLE_ERROR(val, type) (0)
 #define EEH_IO_ERROR_VALUE(size) (-1UL)
diff --git a/include/asm-sparc64/futex.h b/include/asm-sparc64/futex.h
index 6a332a9f099c..0caf60147e97 100644
--- a/include/asm-sparc64/futex.h
+++ b/include/asm-sparc64/futex.h
@@ -1,6 +1,86 @@
-#ifndef _ASM_FUTEX_H
+#ifndef _SPARC64_FUTEX_H
-#define _ASM_FUTEX_H
+#define _SPARC64_FUTEX_H
-#include <asm-generic/futex.h>
+#include <linux/futex.h>
+#include <asm/errno.h>
+#include <asm/system.h>
+#include <asm/uaccess.h>
-#endif
+#define __futex_cas_op(insn, ret, oldval, uaddr, oparg) \
+        __asm__ __volatile__(                           \
+        "\n1:   lduwa   [%3] %%asi, %2\n"               \
+        "       " insn "\n"                             \
+        "2:     casa    [%3] %%asi, %2, %1\n"           \
+        "       cmp     %2, %1\n"                       \
+        "       bne,pn  %%icc, 1b\n"                    \
+        "        mov    0, %0\n"                        \
+        "3:\n"                                          \
+        "       .section .fixup,#alloc,#execinstr\n"    \
+        "       .align  4\n"                            \
+        "4:     ba      3b\n"                           \
+        "        mov    %5, %0\n"                       \
+        "       .previous\n"                            \
+        "       .section __ex_table,#alloc\n"           \
+        "       .align  4\n"                            \
+        "       .word   1b, 4b\n"                       \
+        "       .word   2b, 4b\n"                       \
+        "       .previous\n"                            \
+        : "=&r" (ret), "=&r" (oldval), "=&r" (tem)      \
+        : "r" (uaddr), "r" (oparg), "i" (-EFAULT)       \
+        : "memory")
+static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
+{
+        int op = (encoded_op >> 28) & 7;
+        int cmp = (encoded_op >> 24) & 15;
+        int oparg = (encoded_op << 8) >> 20;
+        int cmparg = (encoded_op << 20) >> 20;
+        int oldval = 0, ret, tem;
+        if (unlikely(!access_ok(VERIFY_WRITE, uaddr, sizeof(int))))
+                return -EFAULT;
+        if (unlikely((((unsigned long) uaddr) & 0x3UL)))
+                return -EINVAL;
+        if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
+                oparg = 1 << oparg;
+        inc_preempt_count();
+        switch (op) {
+        case FUTEX_OP_SET:
+                __futex_cas_op("mov\t%4, %1", ret, oldval, uaddr, oparg);
+                break;
+        case FUTEX_OP_ADD:
+                __futex_cas_op("add\t%2, %4, %1", ret, oldval, uaddr, oparg);
+                break;
+        case FUTEX_OP_OR:
+                __futex_cas_op("or\t%2, %4, %1", ret, oldval, uaddr, oparg);
+                break;
+        case FUTEX_OP_ANDN:
+                __futex_cas_op("and\t%2, %4, %1", ret, oldval, uaddr, oparg);
+                break;
+        case FUTEX_OP_XOR:
+                __futex_cas_op("xor\t%2, %4, %1", ret, oldval, uaddr, oparg);
+                break;
+        default:
+                ret = -ENOSYS;
+        }
+        dec_preempt_count();
+        if (!ret) {
+                switch (cmp) {
+                case FUTEX_OP_CMP_EQ: ret = (oldval == cmparg); break;
+                case FUTEX_OP_CMP_NE: ret = (oldval != cmparg); break;
+                case FUTEX_OP_CMP_LT: ret = (oldval < cmparg); break;
+                case FUTEX_OP_CMP_GE: ret = (oldval >= cmparg); break;
+                case FUTEX_OP_CMP_LE: ret = (oldval <= cmparg); break;
+                case FUTEX_OP_CMP_GT: ret = (oldval > cmparg); break;
+                default: ret = -ENOSYS;
+                }
+        }
+        return ret;
+}
+#endif /* !(_SPARC64_FUTEX_H) */
diff --git a/include/asm-sparc64/smp.h b/include/asm-sparc64/smp.h
index 110a2de89123..473edb2603ec 100644
--- a/include/asm-sparc64/smp.h
+++ b/include/asm-sparc64/smp.h
@@ -66,8 +66,14 @@ static __inline__ int hard_smp_processor_id(void)
 #define raw_smp_processor_id() (current_thread_info()->cpu)
+extern void smp_setup_cpu_possible_map(void);
 #endif /* !(__ASSEMBLY__) */
+#else
+#define smp_setup_cpu_possible_map() do { } while (0)
 #endif /* !(CONFIG_SMP) */
 #define NO_PROC_ID              0xFF
diff --git a/include/asm-x86_64/pci.h b/include/asm-x86_64/pci.h
index fd03e15d7ea6..8a05af264d18 100644
--- a/include/asm-x86_64/pci.h
+++ b/include/asm-x86_64/pci.h
@@ -19,8 +19,6 @@ extern unsigned int pcibios_assign_all_busses(void);
 #endif
 #define pcibios_scan_all_fns(a, b)      0
-extern int no_iommu, force_iommu;
 extern unsigned long pci_mem_start;
 #define PCIBIOS_MIN_IO          0x1000
 #define PCIBIOS_MIN_MEM         (pci_mem_start)
diff --git a/include/asm-x86_64/pgtable.h b/include/asm-x86_64/pgtable.h
index 8fbf4dd72115..715fd94cf577 100644
--- a/include/asm-x86_64/pgtable.h
+++ b/include/asm-x86_64/pgtable.h
@@ -131,7 +131,7 @@ static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm, unsigned long
 #define PGDIR_SIZE      (1UL << PGDIR_SHIFT)
 #define PGDIR_MASK      (~(PGDIR_SIZE-1))
-#define USER_PTRS_PER_PGD       (TASK_SIZE/PGDIR_SIZE)
+#define USER_PTRS_PER_PGD       ((TASK_SIZE-1)/PGDIR_SIZE+1)
 #define FIRST_USER_ADDRESS      0
 #ifndef __ASSEMBLY__
diff --git a/include/asm-x86_64/proto.h b/include/asm-x86_64/proto.h
index eca3f2d633db..3ba8fd45fcb3 100644
--- a/include/asm-x86_64/proto.h
+++ b/include/asm-x86_64/proto.h
@@ -39,7 +39,6 @@ extern void config_acpi_tables(void);
 extern void ia32_syscall(void);
 extern void iommu_hole_init(void);
-extern void time_init_gtod(void);
 extern int pmtimer_mark_offset(void);
 extern void pmtimer_resume(void);
 extern void pmtimer_wait(unsigned);
@@ -134,6 +133,7 @@ extern int force_iommu;
 extern int reboot_force;
 extern int notsc_setup(char *);
+extern int setup_additional_cpus(char *);
 extern void smp_local_timer_interrupt(struct pt_regs * regs);
diff --git a/include/linux/netfilter_bridge/ebt_log.h b/include/linux/netfilter_bridge/ebt_log.h
index 358fbc84fb59..96e231ae7554 100644
--- a/include/linux/netfilter_bridge/ebt_log.h
+++ b/include/linux/netfilter_bridge/ebt_log.h
@@ -3,6 +3,7 @@
 #define EBT_LOG_IP 0x01 /* if the frame is made by ip, log the ip information */
 #define EBT_LOG_ARP 0x02
+#define EBT_LOG_NFLOG 0x04
 #define EBT_LOG_MASK (EBT_LOG_IP | EBT_LOG_ARP)
 #define EBT_LOG_PREFIX_SIZE 30
 #define EBT_LOG_WATCHER "log"
diff --git a/include/linux/netfilter_ipv4/ipt_LOG.h b/include/linux/netfilter_ipv4/ipt_LOG.h
index 22d16177319b..892f9a33fea8 100644
--- a/include/linux/netfilter_ipv4/ipt_LOG.h
+++ b/include/linux/netfilter_ipv4/ipt_LOG.h
@@ -6,7 +6,8 @@
 #define IPT_LOG_TCPOPT          0x02    /* Log TCP options */
 #define IPT_LOG_IPOPT           0x04    /* Log IP options */
 #define IPT_LOG_UID             0x08    /* Log UID owning local socket */
-#define IPT_LOG_MASK            0x0f
+#define IPT_LOG_NFLOG           0x10    /* Log using nf_log backend */
+#define IPT_LOG_MASK            0x1f
 struct ipt_log_info {
        unsigned char level;
diff --git a/include/linux/netfilter_ipv6/ip6t_LOG.h b/include/linux/netfilter_ipv6/ip6t_LOG.h
index 9008ff5c40ae..060c1a1c6c60 100644
--- a/include/linux/netfilter_ipv6/ip6t_LOG.h
+++ b/include/linux/netfilter_ipv6/ip6t_LOG.h
@@ -6,7 +6,8 @@
 #define IP6T_LOG_TCPOPT         0x02    /* Log TCP options */
 #define IP6T_LOG_IPOPT          0x04    /* Log IP options */
 #define IP6T_LOG_UID            0x08    /* Log UID owning local socket */
-#define IP6T_LOG_MASK           0x0f
+#define IP6T_LOG_NFLOG          0x10    /* Log using nf_log backend */
+#define IP6T_LOG_MASK           0x1f
 struct ip6t_log_info {
        unsigned char level;
diff --git a/include/linux/serial_reg.h b/include/linux/serial_reg.h
index 6a2bb955844b..3c8a6aa77415 100644
--- a/include/linux/serial_reg.h
+++ b/include/linux/serial_reg.h
@@ -247,10 +247,10 @@
 #define UART_CTR        0xFF
 /*
- * The 16C950 Additional Control Reigster
+ * The 16C950 Additional Control Register
 */
 #define UART_ACR_RXDIS  0x01    /* Receiver disable */
-#define UART_ACR_TXDIS  0x02    /* Receiver disable */
+#define UART_ACR_TXDIS  0x02    /* Transmitter disable */
 #define UART_ACR_DSRFC  0x04    /* DSR Flow Control */
 #define UART_ACR_TLENB  0x20    /* 950 trigger levels enable */
 #define UART_ACR_ICRRD  0x40    /* ICR Read enable */
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index d73501ba7e44..b9ea44ac0ddb 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -543,7 +543,7 @@ asmlinkage long sys_unlinkat(int dfd, const char __user * pathname, int flag);
 asmlinkage long sys_symlinkat(const char __user * oldname,
                              int newdfd, const char __user * newname);
 asmlinkage long sys_linkat(int olddfd, const char __user *oldname,
-                           int newdfd, const char __user *newname);
+                           int newdfd, const char __user *newname, int flags);
 asmlinkage long sys_renameat(int olddfd, const char __user * oldname,
                             int newdfd, const char __user * newname);
 asmlinkage long sys_futimesat(int dfd, char __user *filename,
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index d6111a2f0a23..8d362c49b8a9 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -233,7 +233,6 @@ struct xfrm_type
        int                     (*init_state)(struct xfrm_state *x);
        void                    (*destructor)(struct xfrm_state *);
        int                     (*input)(struct xfrm_state *, struct xfrm_decap_state *, struct sk_buff *skb);
-        int                     (*post_input)(struct xfrm_state *, struct xfrm_decap_state *, struct sk_buff *skb);
        int                     (*output)(struct xfrm_state *, struct sk_buff *pskb);
        /* Estimate maximal size of result of transformation of a dgram */
        u32                     (*get_max_size)(struct xfrm_state *, int size);
@@ -403,6 +402,11 @@ unsigned xfrm_spi_hash(xfrm_address_t *addr, u32 spi, u8 proto, unsigned short f
 extern void __xfrm_state_destroy(struct xfrm_state *);
+static inline void __xfrm_state_put(struct xfrm_state *x)
+{
+        atomic_dec(&x->refcnt);
+}
 static inline void xfrm_state_put(struct xfrm_state *x)
 {
        if (atomic_dec_and_test(&x->refcnt))
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 880831bd3003..67af4cea1e23 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -552,7 +552,7 @@ static void migrate_page_add(struct page *page, struct list_head *pagelist,
         */
        if ((flags & MPOL_MF_MOVE_ALL) || page_mapcount(page) == 1) {
                if (isolate_lru_page(page))
-                        list_add(&page->lru, pagelist);
+                        list_add_tail(&page->lru, pagelist);
        }
 }
@@ -569,6 +569,7 @@ static int migrate_pages_to(struct list_head *pagelist,
        LIST_HEAD(moved);
        LIST_HEAD(failed);
        int err = 0;
+        unsigned long offset = 0;
        int nr_pages;
        struct page *page;
        struct list_head *p;
@@ -576,8 +577,21 @@ static int migrate_pages_to(struct list_head *pagelist,
 redo:
        nr_pages = 0;
        list_for_each(p, pagelist) {
-                if (vma)
+                if (vma) {
-                        page = alloc_page_vma(GFP_HIGHUSER, vma, vma->vm_start);
+                        /*
+                         * The address passed to alloc_page_vma is used to
+                         * generate the proper interleave behavior. We fake
+                         * the address here by an increasing offset in order
+                         * to get the proper distribution of pages.
+                         *
+                         * No decision has been made as to which page
+                         * a certain old page is moved to so we cannot
+                         * specify the correct address.
+                         */
+                        page = alloc_page_vma(GFP_HIGHUSER, vma,
+                                        offset + vma->vm_start);
+                        offset += PAGE_SIZE;
+                }
                else
                        page = alloc_pages_node(dest, GFP_HIGHUSER, 0);
@@ -585,7 +599,7 @@ redo:
                        err = -ENOMEM;
                        goto out;
                }
-                list_add(&page->lru, &newlist);
+                list_add_tail(&page->lru, &newlist);
                nr_pages++;
                if (nr_pages > MIGRATE_CHUNK_SIZE)
                        break;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 1838c15ca4fd..b0af7593d01e 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1908,7 +1908,12 @@ int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
                sc.swap_cluster_max = SWAP_CLUSTER_MAX;
        cond_resched();
-        p->flags |= PF_MEMALLOC;
+        /*
+         * We need to be able to allocate from the reserves for RECLAIM_SWAP
+         * and we also need to be able to write out pages for RECLAIM_WRITE
+         * and RECLAIM_SWAP.
+         */
+        p->flags |= PF_MEMALLOC | PF_SWAPWRITE;
        reclaim_state.reclaimed_slab = 0;
        p->reclaim_state = &reclaim_state;
@@ -1932,11 +1937,10 @@ int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
                 * a long time.
                 */
                shrink_slab(sc.nr_scanned, gfp_mask, order);
-                sc.nr_reclaimed = 1;    /* Avoid getting the off node timeout */
        }
        p->reclaim_state = NULL;
-        current->flags &= ~PF_MEMALLOC;
+        current->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE);
        if (sc.nr_reclaimed == 0)
                zone->last_unsuccessful_zone_reclaim = jiffies;
diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c
index 6bb0c7eb1ef0..e060aad8624d 100644
--- a/net/bridge/br_netfilter.c
+++ b/net/bridge/br_netfilter.c
@@ -90,6 +90,7 @@ static struct rtable __fake_rtable = {
                        .dev                    = &__fake_net_device,
                        .path                   = &__fake_rtable.u.dst,
                        .metrics                = {[RTAX_MTU - 1] = 1500},
+                        .flags                  = DST_NOXFRM,
                }
        },
        .rt_flags       = 0,
diff --git a/net/bridge/netfilter/ebt_log.c b/net/bridge/netfilter/ebt_log.c
index 0128fbbe2328..288ff1d4ccc4 100644
--- a/net/bridge/netfilter/ebt_log.c
+++ b/net/bridge/netfilter/ebt_log.c
@@ -166,7 +166,12 @@ static void ebt_log(const struct sk_buff *skb, unsigned int hooknr,
        li.u.log.level = info->loglevel;
        li.u.log.logflags = info->bitmask;
-        nf_log_packet(PF_BRIDGE, hooknr, skb, in, out, &li, info->prefix);
+        if (info->bitmask & EBT_LOG_NFLOG)
+                nf_log_packet(PF_BRIDGE, hooknr, skb, in, out, &li,
+                              info->prefix);
+        else
+                ebt_log_packet(PF_BRIDGE, hooknr, skb, in, out, &li,
+                               info->prefix);
 }
 static struct ebt_watcher log =
diff --git a/net/core/request_sock.c b/net/core/request_sock.c
index b8203de5ff07..98f0fc923f91 100644
--- a/net/core/request_sock.c
+++ b/net/core/request_sock.c
@@ -52,7 +52,6 @@ int reqsk_queue_alloc(struct request_sock_queue *queue,
        get_random_bytes(&lopt->hash_rnd, sizeof(lopt->hash_rnd));
        rwlock_init(&queue->syn_wait_lock);
        queue->rskq_accept_head = queue->rskq_accept_head = NULL;
-        queue->rskq_defer_accept = 0;
        lopt->nr_table_entries = nr_table_entries;
        write_lock_bh(&queue->syn_wait_lock);
diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c
index 9890fd97e538..c971f14712ec 100644
--- a/net/ethernet/eth.c
+++ b/net/ethernet/eth.c
@@ -95,6 +95,12 @@ int eth_header(struct sk_buff *skb, struct net_device *dev, unsigned short type,
                saddr = dev->dev_addr;
        memcpy(eth->h_source,saddr,dev->addr_len);
+        if(daddr)
+        {
+                memcpy(eth->h_dest,daddr,dev->addr_len);
+                return ETH_HLEN;
+        }
+        
        /*
         *      Anyway, the loopback-device should never use this function... 
         */
@@ -105,12 +111,6 @@ int eth_header(struct sk_buff *skb, struct net_device *dev, unsigned short type,
                return ETH_HLEN;
        }
        
-        if(daddr)
-        {
-                memcpy(eth->h_dest,daddr,dev->addr_len);
-                return ETH_HLEN;
-        }
-        
        return -ETH_HLEN;
 }
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 73bfcae8af9c..09590f356086 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -12,13 +12,6 @@
 #include <net/protocol.h>
 #include <net/udp.h>
-/* decapsulation data for use when post-processing */
-struct esp_decap_data {
-        xfrm_address_t  saddr;
-        __u16           sport;
-        __u8            proto;
-};
 static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 {
        int err;
@@ -150,6 +143,10 @@ static int esp_input(struct xfrm_state *x, struct xfrm_decap_state *decap, struc
        int elen = skb->len - sizeof(struct ip_esp_hdr) - esp->conf.ivlen - alen;
        int nfrags;
        int encap_len = 0;
+        u8 nexthdr[2];
+        struct scatterlist *sg;
+        u8 workbuf[60];
+        int padlen;
        if (!pskb_may_pull(skb, sizeof(struct ip_esp_hdr)))
                goto out;
@@ -185,122 +182,82 @@ static int esp_input(struct xfrm_state *x, struct xfrm_decap_state *decap, struc
        if (esp->conf.ivlen)
                crypto_cipher_set_iv(esp->conf.tfm, esph->enc_data, crypto_tfm_alg_ivsize(esp->conf.tfm));
-        {
+        sg = &esp->sgbuf[0];
-                u8 nexthdr[2];
-                struct scatterlist *sg = &esp->sgbuf[0];
-                u8 workbuf[60];
-                int padlen;
-                if (unlikely(nfrags > ESP_NUM_FAST_SG)) {
-                        sg = kmalloc(sizeof(struct scatterlist)*nfrags, GFP_ATOMIC);
-                        if (!sg)
-                                goto out;
-                }
-                skb_to_sgvec(skb, sg, sizeof(struct ip_esp_hdr) + esp->conf.ivlen, elen);
-                crypto_cipher_decrypt(esp->conf.tfm, sg, sg, elen);
-                if (unlikely(sg != &esp->sgbuf[0]))
-                        kfree(sg);
-                if (skb_copy_bits(skb, skb->len-alen-2, nexthdr, 2))
-                        BUG();
-                padlen = nexthdr[0];
+        if (unlikely(nfrags > ESP_NUM_FAST_SG)) {
-                if (padlen+2 >= elen)
+                sg = kmalloc(sizeof(struct scatterlist)*nfrags, GFP_ATOMIC);
+                if (!sg)
                        goto out;
-                /* ... check padding bits here. Silly. :-) */ 
-                if (x->encap && decap && decap->decap_type) {
-                        struct esp_decap_data *encap_data;
-                        struct udphdr *uh = (struct udphdr *) (iph+1);
-                        encap_data = (struct esp_decap_data *) (decap->decap_data);
-                        encap_data->proto = 0;
-                        switch (decap->decap_type) {
-                        case UDP_ENCAP_ESPINUDP:
-                        case UDP_ENCAP_ESPINUDP_NON_IKE:
-                                encap_data->proto = AF_INET;
-                                encap_data->saddr.a4 = iph->saddr;
-                                encap_data->sport = uh->source;
-                                encap_len = (void*)esph - (void*)uh;
-                                break;
-                        default:
-                                goto out;
-                        }
-                }
-                iph->protocol = nexthdr[1];
-                pskb_trim(skb, skb->len - alen - padlen - 2);
-                memcpy(workbuf, skb->nh.raw, iph->ihl*4);
-                skb->h.raw = skb_pull(skb, sizeof(struct ip_esp_hdr) + esp->conf.ivlen);
-                skb->nh.raw += encap_len + sizeof(struct ip_esp_hdr) + esp->conf.ivlen;
-                memcpy(skb->nh.raw, workbuf, iph->ihl*4);
-                skb->nh.iph->tot_len = htons(skb->len);
        }
+        skb_to_sgvec(skb, sg, sizeof(struct ip_esp_hdr) + esp->conf.ivlen, elen);
+        crypto_cipher_decrypt(esp->conf.tfm, sg, sg, elen);
+        if (unlikely(sg != &esp->sgbuf[0]))
+                kfree(sg);
-        return 0;
+        if (skb_copy_bits(skb, skb->len-alen-2, nexthdr, 2))
+                BUG();
-out:
+        padlen = nexthdr[0];
-        return -EINVAL;
+        if (padlen+2 >= elen)
-}
+                goto out;
-static int esp_post_input(struct xfrm_state *x, struct xfrm_decap_state *decap, struct sk_buff *skb)
+        /* ... check padding bits here. Silly. :-) */ 
-{
-  
-        if (x->encap) {
-                struct xfrm_encap_tmpl *encap;
-                struct esp_decap_data *decap_data;
-                encap = x->encap;
+        if (x->encap) {
-                decap_data = (struct esp_decap_data *)(decap->decap_data);
+                struct xfrm_encap_tmpl *encap = x->encap;
+                struct udphdr *uh;
-                /* first, make sure that the decap type == the encap type */
                if (encap->encap_type != decap->decap_type)
-                        return -EINVAL;
+                        goto out;
-                switch (encap->encap_type) {
+                uh = (struct udphdr *)(iph + 1);
-                default:
+                encap_len = (void*)esph - (void*)uh;
-                case UDP_ENCAP_ESPINUDP:
-                case UDP_ENCAP_ESPINUDP_NON_IKE:
+                /*
-                        /*
+                 * 1) if the NAT-T peer's IP or port changed then
-                         * 1) if the NAT-T peer's IP or port changed then
+                 *    advertize the change to the keying daemon.
-                         *    advertize the change to the keying daemon.
+                 *    This is an inbound SA, so just compare
-                         *    This is an inbound SA, so just compare
+                 *    SRC ports.
-                         *    SRC ports.
+                 */
-                         */
+                if (iph->saddr != x->props.saddr.a4 ||
-                        if (decap_data->proto == AF_INET &&
+                    uh->source != encap->encap_sport) {
-                            (decap_data->saddr.a4 != x->props.saddr.a4 ||
+                        xfrm_address_t ipaddr;
-                             decap_data->sport != encap->encap_sport)) {
-                                xfrm_address_t ipaddr;
+                        ipaddr.a4 = iph->saddr;
+                        km_new_mapping(x, &ipaddr, uh->source);
-                                ipaddr.a4 = decap_data->saddr.a4;
+                                
-                                km_new_mapping(x, &ipaddr, decap_data->sport);
+                        /* XXX: perhaps add an extra
-                                        
+                         * policy check here, to see
-                                /* XXX: perhaps add an extra
+                         * if we should allow or
-                                 * policy check here, to see
+                         * reject a packet from a
-                                 * if we should allow or
+                         * different source
-                                 * reject a packet from a
+                         * address/port.
-                                 * different source
-                                 * address/port.
-                                 */
-                        }
-                
-                        /*
-                         * 2) ignore UDP/TCP checksums in case
-                         *    of NAT-T in Transport Mode, or
-                         *    perform other post-processing fixes
-                         *    as per * draft-ietf-ipsec-udp-encaps-06,
-                         *    section 3.1.2
                         */
-                        if (!x->props.mode)
-                                skb->ip_summed = CHECKSUM_UNNECESSARY;
-                        break;
                }
+        
+                /*
+                 * 2) ignore UDP/TCP checksums in case
+                 *    of NAT-T in Transport Mode, or
+                 *    perform other post-processing fixes
+                 *    as per draft-ietf-ipsec-udp-encaps-06,
+                 *    section 3.1.2
+                 */
+                if (!x->props.mode)
+                        skb->ip_summed = CHECKSUM_UNNECESSARY;
        }
+        iph->protocol = nexthdr[1];
+        pskb_trim(skb, skb->len - alen - padlen - 2);
+        memcpy(workbuf, skb->nh.raw, iph->ihl*4);
+        skb->h.raw = skb_pull(skb, sizeof(struct ip_esp_hdr) + esp->conf.ivlen);
+        skb->nh.raw += encap_len + sizeof(struct ip_esp_hdr) + esp->conf.ivlen;
+        memcpy(skb->nh.raw, workbuf, iph->ihl*4);
+        skb->nh.iph->tot_len = htons(skb->len);
        return 0;
+out:
+        return -EINVAL;
 }
 static u32 esp4_get_max_size(struct xfrm_state *x, int mtu)
@@ -458,7 +415,6 @@ static struct xfrm_type esp_type =
        .destructor     = esp_destroy,
        .get_max_size   = esp4_get_max_size,
        .input          = esp_input,
-        .post_input     = esp_post_input,
        .output         = esp_output
 };
@@ -470,15 +426,6 @@ static struct net_protocol esp4_protocol = {
 static int __init esp4_init(void)
 {
-        struct xfrm_decap_state decap;
-        if (sizeof(struct esp_decap_data)  >
-            sizeof(decap.decap_data)) {
-                extern void decap_data_too_small(void);
-                decap_data_too_small();
-        }
        if (xfrm_register_type(&esp_type, AF_INET) < 0) {
                printk(KERN_INFO "ip esp init: can't add xfrm type\n");
                return -EAGAIN;
diff --git a/net/ipv4/netfilter/ipt_LOG.c b/net/ipv4/netfilter/ipt_LOG.c
index 6606ddb66a29..cc27545ff97f 100644
--- a/net/ipv4/netfilter/ipt_LOG.c
+++ b/net/ipv4/netfilter/ipt_LOG.c
@@ -425,7 +425,12 @@ ipt_log_target(struct sk_buff **pskb,
        li.u.log.level = loginfo->level;
        li.u.log.logflags = loginfo->logflags;
-        nf_log_packet(PF_INET, hooknum, *pskb, in, out, &li, loginfo->prefix);
+        if (loginfo->logflags & IPT_LOG_NFLOG)
+                nf_log_packet(PF_INET, hooknum, *pskb, in, out, &li,
+                              loginfo->prefix);
+        else
+                ipt_log_packet(PF_INET, hooknum, *pskb, in, out, &li,
+                               loginfo->prefix);
        return IPT_CONTINUE;
 }
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index d82c242ea704..fca5fe0cf94a 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -835,7 +835,7 @@ static int rt_garbage_collect(void)
                                        int r;
                                        rthp = rt_remove_balanced_route(
-                                                &rt_hash_table[i].chain,
+                                                &rt_hash_table[k].chain,
                                                rth,
                                                &r);
                                        goal -= r;
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 45f7ae58f2c0..f285bbf296e2 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -35,6 +35,7 @@ __xfrm4_find_bundle(struct flowi *fl, struct xfrm_policy *policy)
                if (xdst->u.rt.fl.oif == fl->oif &&     /*XXX*/
                    xdst->u.rt.fl.fl4_dst == fl->fl4_dst &&
                    xdst->u.rt.fl.fl4_src == fl->fl4_src &&
+                    xdst->u.rt.fl.fl4_tos == fl->fl4_tos &&
                    xfrm_bundle_ok(xdst, fl, AF_INET)) {
                        dst_clone(dst);
                        break;
@@ -61,7 +62,8 @@ __xfrm4_bundle_create(struct xfrm_policy *policy, struct xfrm_state **xfrm, int
                .nl_u = {
                        .ip4_u = {
                                .saddr = local,
-                                .daddr = remote
+                                .daddr = remote,
+                                .tos = fl->fl4_tos
                        }
                }
        };
@@ -230,6 +232,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl)
        fl->proto = iph->protocol;
        fl->fl4_dst = iph->daddr;
        fl->fl4_src = iph->saddr;
+        fl->fl4_tos = iph->tos;
 }
 static inline int xfrm4_garbage_collect(void)
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index efa3e72cfcfa..f999edd846a9 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -494,6 +494,7 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
        struct net_device *dev;
        struct sk_buff *frag;
        struct rt6_info *rt = (struct rt6_info*)skb->dst;
+        struct ipv6_pinfo *np = skb->sk ? inet6_sk(skb->sk) : NULL;
        struct ipv6hdr *tmp_hdr;
        struct frag_hdr *fh;
        unsigned int mtu, hlen, left, len;
@@ -505,7 +506,12 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
        hlen = ip6_find_1stfragopt(skb, &prevhdr);
        nexthdr = *prevhdr;
-        mtu = dst_mtu(&rt->u.dst) - hlen - sizeof(struct frag_hdr);
+        mtu = dst_mtu(&rt->u.dst);
+        if (np && np->frag_size < mtu) {
+                if (np->frag_size)
+                        mtu = np->frag_size;
+        }
+        mtu -= hlen + sizeof(struct frag_hdr);
        if (skb_shinfo(skb)->frag_list) {
                int first_len = skb_pagelen(skb);
@@ -882,7 +888,12 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
                inet->cork.fl = *fl;
                np->cork.hop_limit = hlimit;
                np->cork.tclass = tclass;
-                inet->cork.fragsize = mtu = dst_mtu(rt->u.dst.path);
+                mtu = dst_mtu(rt->u.dst.path);
+                if (np && np->frag_size < mtu) {
+                        if (np->frag_size)
+                                mtu = np->frag_size;
+                }
+                inet->cork.fragsize = mtu;
                if (dst_allfrag(rt->u.dst.path))
                        inet->cork.flags |= IPCORK_ALLFRAG;
                inet->cork.length = 0;
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index faea8a120ee2..48597538db3f 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -884,6 +884,7 @@ ip6ip6_tnl_change(struct ip6_tnl *t, struct ip6_tnl_parm *p)
        t->parms.encap_limit = p->encap_limit;
        t->parms.flowinfo = p->flowinfo;
        t->parms.link = p->link;
+        ip6_tnl_dst_reset(t);
        ip6ip6_tnl_link_config(t);
        return 0;
 }
diff --git a/net/ipv6/netfilter/ip6t_LOG.c b/net/ipv6/netfilter/ip6t_LOG.c
index 77c725832dec..6b930efa9fb9 100644
--- a/net/ipv6/netfilter/ip6t_LOG.c
+++ b/net/ipv6/netfilter/ip6t_LOG.c
@@ -436,7 +436,12 @@ ip6t_log_target(struct sk_buff **pskb,
        li.u.log.level = loginfo->level;
        li.u.log.logflags = loginfo->logflags;
-        nf_log_packet(PF_INET6, hooknum, *pskb, in, out, &li, loginfo->prefix);
+        if (loginfo->logflags & IP6T_LOG_NFLOG)
+                nf_log_packet(PF_INET6, hooknum, *pskb, in, out, &li,
+                              loginfo->prefix);
+        else
+                ip6t_log_packet(PF_INET6, hooknum, *pskb, in, out, &li,
+                                loginfo->prefix);
        return IP6T_CONTINUE;
 }
diff --git a/net/key/af_key.c b/net/key/af_key.c
index ae86d237a456..b2d4d1dd2116 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -1423,7 +1423,7 @@ static int pfkey_add(struct sock *sk, struct sk_buff *skb, struct sadb_msg *hdr,
        if (err < 0) {
                x->km.state = XFRM_STATE_DEAD;
-                xfrm_state_put(x);
+                __xfrm_state_put(x);
                goto out;
        }
diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c
index d3a4f30a7f22..d9f0d7ef103b 100644
--- a/net/netfilter/nf_queue.c
+++ b/net/netfilter/nf_queue.c
@@ -6,6 +6,7 @@
 #include <linux/skbuff.h>
 #include <linux/netfilter.h>
 #include <linux/seq_file.h>
+#include <linux/rcupdate.h>
 #include <net/protocol.h>
 #include "nf_internals.h"
@@ -16,7 +17,7 @@
 * for queueing and must reinject all packets it receives, no matter what.
 */
 static struct nf_queue_handler *queue_handler[NPROTO];
-static struct nf_queue_rerouter *queue_rerouter;
+static struct nf_queue_rerouter *queue_rerouter[NPROTO];
 static DEFINE_RWLOCK(queue_handler_lock);
@@ -64,7 +65,7 @@ int nf_register_queue_rerouter(int pf, struct nf_queue_rerouter *rer)
                return -EINVAL;
        write_lock_bh(&queue_handler_lock);
-        memcpy(&queue_rerouter[pf], rer, sizeof(queue_rerouter[pf]));
+        rcu_assign_pointer(queue_rerouter[pf], rer);
        write_unlock_bh(&queue_handler_lock);
        return 0;
@@ -77,8 +78,9 @@ int nf_unregister_queue_rerouter(int pf)
                return -EINVAL;
        write_lock_bh(&queue_handler_lock);
-        memset(&queue_rerouter[pf], 0, sizeof(queue_rerouter[pf]));
+        rcu_assign_pointer(queue_rerouter[pf], NULL);
        write_unlock_bh(&queue_handler_lock);
+        synchronize_rcu();
        return 0;
 }
 EXPORT_SYMBOL_GPL(nf_unregister_queue_rerouter);
@@ -114,16 +116,17 @@ int nf_queue(struct sk_buff **skb,
        struct net_device *physindev = NULL;
        struct net_device *physoutdev = NULL;
 #endif
+        struct nf_queue_rerouter *rerouter;
        /* QUEUE == DROP if noone is waiting, to be safe. */
        read_lock(&queue_handler_lock);
-        if (!queue_handler[pf] || !queue_handler[pf]->outfn) {
+        if (!queue_handler[pf]) {
                read_unlock(&queue_handler_lock);
                kfree_skb(*skb);
                return 1;
        }
-        info = kmalloc(sizeof(*info)+queue_rerouter[pf].rer_size, GFP_ATOMIC);
+        info = kmalloc(sizeof(*info)+queue_rerouter[pf]->rer_size, GFP_ATOMIC);
        if (!info) {
                if (net_ratelimit())
                        printk(KERN_ERR "OOM queueing packet %p\n",
@@ -155,15 +158,13 @@ int nf_queue(struct sk_buff **skb,
                if (physoutdev) dev_hold(physoutdev);
        }
 #endif
-        if (queue_rerouter[pf].save)
+        rerouter = rcu_dereference(queue_rerouter[pf]);
-                queue_rerouter[pf].save(*skb, info);
+        if (rerouter)
+                rerouter->save(*skb, info);
        status = queue_handler[pf]->outfn(*skb, info, queuenum,
                                          queue_handler[pf]->data);
-        if (status >= 0 && queue_rerouter[pf].reroute)
-                status = queue_rerouter[pf].reroute(skb, info);
        read_unlock(&queue_handler_lock);
        if (status < 0) {
@@ -189,6 +190,7 @@ void nf_reinject(struct sk_buff *skb, struct nf_info *info,
 {
        struct list_head *elem = &info->elem->list;
        struct list_head *i;
+        struct nf_queue_rerouter *rerouter;
        rcu_read_lock();
@@ -212,7 +214,7 @@ void nf_reinject(struct sk_buff *skb, struct nf_info *info,
                        break;
        }
  
-        if (elem == &nf_hooks[info->pf][info->hook]) {
+        if (i == &nf_hooks[info->pf][info->hook]) {
                /* The module which sent it to userspace is gone. */
                NFDEBUG("%s: module disappeared, dropping packet.\n",
                        __FUNCTION__);
@@ -226,6 +228,12 @@ void nf_reinject(struct sk_buff *skb, struct nf_info *info,
        }
        if (verdict == NF_ACCEPT) {
+                rerouter = rcu_dereference(queue_rerouter[info->pf]);
+                if (rerouter && rerouter->reroute(&skb, info) < 0)
+                        verdict = NF_DROP;
+        }
+        if (verdict == NF_ACCEPT) {
        next_hook:
                verdict = nf_iterate(&nf_hooks[info->pf][info->hook],
                                     &skb, info->hook, 
@@ -322,22 +330,12 @@ int __init netfilter_queue_init(void)
 {
 #ifdef CONFIG_PROC_FS
        struct proc_dir_entry *pde;
-#endif
-        queue_rerouter = kmalloc(NPROTO * sizeof(struct nf_queue_rerouter),
-                                 GFP_KERNEL);
-        if (!queue_rerouter)
-                return -ENOMEM;
-#ifdef CONFIG_PROC_FS
        pde = create_proc_entry("nf_queue", S_IRUGO, proc_net_netfilter);
-        if (!pde) {
+        if (!pde)
-                kfree(queue_rerouter);
                return -1;
-        }
        pde->proc_fops = &nfqueue_file_ops;
 #endif
-        memset(queue_rerouter, 0, NPROTO * sizeof(struct nf_queue_rerouter));
        return 0;
 }
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 5e6b05ac1260..ae62054a9fc4 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -782,7 +782,7 @@ int xfrm_lookup(struct dst_entry **dst_p, struct flowi *fl,
        int nx = 0;
        int err;
        u32 genid;
-        u16 family = dst_orig->ops->family;
+        u16 family;
        u8 dir = policy_to_flow_dir(XFRM_POLICY_OUT);
        u32 sk_sid = security_sk_sid(sk, fl, dir);
 restart:
@@ -796,13 +796,14 @@ restart:
                if ((dst_orig->flags & DST_NOXFRM) || !xfrm_policy_list[XFRM_POLICY_OUT])
                        return 0;
-                policy = flow_cache_lookup(fl, sk_sid, family, dir,
+                policy = flow_cache_lookup(fl, sk_sid, dst_orig->ops->family,
-                                           xfrm_policy_lookup);
+                                           dir, xfrm_policy_lookup);
        }
        if (!policy)
                return 0;
+        family = dst_orig->ops->family;
        policy->curlft.use_time = (unsigned long)xtime.tv_sec;
        switch (policy->action) {
@@ -995,13 +996,6 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
                        struct sec_decap_state *xvec = &(skb->sp->x[i]);
                        if (!xfrm_selector_match(&xvec->xvec->sel, &fl, family))
                                return 0;
-                        /* If there is a post_input processor, try running it */
-                        if (xvec->xvec->type->post_input &&
-                            (xvec->xvec->type->post_input)(xvec->xvec,
-                                                           &(xvec->decap),
-                                                           skb) != 0)
-                                return 0;
                }
        }
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index e12d0be5f976..c656cbaf35e8 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -220,14 +220,14 @@ static int __xfrm_state_delete(struct xfrm_state *x)
                x->km.state = XFRM_STATE_DEAD;
                spin_lock(&xfrm_state_lock);
                list_del(&x->bydst);
-                atomic_dec(&x->refcnt);
+                __xfrm_state_put(x);
                if (x->id.spi) {
                        list_del(&x->byspi);
-                        atomic_dec(&x->refcnt);
+                        __xfrm_state_put(x);
                }
                spin_unlock(&xfrm_state_lock);
                if (del_timer(&x->timer))
-                        atomic_dec(&x->refcnt);
+                        __xfrm_state_put(x);
                /* The number two in this test is the reference
                 * mentioned in the comment below plus the reference
@@ -243,7 +243,7 @@ static int __xfrm_state_delete(struct xfrm_state *x)
                 * The xfrm_state_alloc call gives a reference, and that
                 * is what we are dropping here.
                 */
-                atomic_dec(&x->refcnt);
+                __xfrm_state_put(x);
                err = 0;
        }
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index ac87a09ba83e..7de17559249a 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -345,7 +345,7 @@ static int xfrm_add_sa(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfrma)
        if (err < 0) {
                x->km.state = XFRM_STATE_DEAD;
-                xfrm_state_put(x);
+                __xfrm_state_put(x);
                goto out;
        }
diff --git a/sound/drivers/opl3/opl3_oss.c b/sound/drivers/opl3/opl3_oss.c
index 31f1f2e25aa0..0345ae647681 100644
--- a/sound/drivers/opl3/opl3_oss.c
+++ b/sound/drivers/opl3/opl3_oss.c
@@ -146,7 +146,7 @@ void snd_opl3_init_seq_oss(struct snd_opl3 *opl3, char *name)
 void snd_opl3_free_seq_oss(struct snd_opl3 *opl3)
 {
        if (opl3->oss_seq_dev) {
-                snd_device_free(opl3->card, opl3->oss_seq_dev);
+                /* The instance should have been released in prior */
                opl3->oss_seq_dev = NULL;
        }
 }
diff --git a/sound/isa/cs423x/cs4236.c b/sound/isa/cs423x/cs4236.c
index 4fa431040564..99a42138bea0 100644
--- a/sound/isa/cs423x/cs4236.c
+++ b/sound/isa/cs423x/cs4236.c
@@ -414,7 +414,7 @@ static int __devinit snd_card_cs423x_pnpc(int dev, struct snd_card_cs4236 *acard
        }
        /* MPU initialization */
        if (acard->mpu && mpu_port[dev] > 0) {
-                if (snd_cs423x_pnp_init_mpu(dev, acard->ctrl, cfg) < 0)
+                if (snd_cs423x_pnp_init_mpu(dev, acard->mpu, cfg) < 0)
                        goto error;
        }
        kfree(cfg);