16 files changed, 440 insertions, 88 deletions

diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index 3213c9382b17..79087dd6d869 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -2,7 +2,8 @@
 # Makefile for the linux kernel.
 #
 
-AFLAGS_head.o := -DTEXT_OFFSET=$(TEXT_OFFSET)
+CPPFLAGS_vmlinux.lds := -DTEXT_OFFSET=$(TEXT_OFFSET)
+AFLAGS_head.o        := -DTEXT_OFFSET=$(TEXT_OFFSET)
 
 ifdef CONFIG_DYNAMIC_FTRACE
 CFLAGS_REMOVE_ftrace.o = -pg
@@ -34,6 +35,7 @@ obj-$(CONFIG_OABI_COMPAT)	+= sys_oabi-compat.o
 obj-$(CONFIG_ARM_THUMBEE)       += thumbee.o
 obj-$(CONFIG_KGDB)              += kgdb.o
 obj-$(CONFIG_ARM_UNWIND)        += unwind.o
+obj-$(CONFIG_HAVE_TCM)          += tcm.o
 
 obj-$(CONFIG_CRUNCH)            += crunch.o crunch-bits.o
 AFLAGS_crunch-bits.o            := -Wa,-mcpu=ep9312
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index 3d727a8a23bc..322410be573c 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -272,7 +272,15 @@ __und_svc:
         @
         @  r0 - instruction
         @
+#ifndef CONFIG_THUMB2_KERNEL
         ldr     r0, [r2, #-4]
+#else
+        ldrh    r0, [r2, #-2]                   @ Thumb instruction at LR - 2
+        and     r9, r0, #0xf800
+        cmp     r9, #0xe800                     @ 32-bit instruction if xx >= 0
+        ldrhhs  r9, [r2]                        @ bottom 16 bits
+        orrhs   r0, r9, r0, lsl #16
+#endif
         adr     r9, BSYM(1f)
         bl      call_fpe
 
@@ -303,22 +311,16 @@ __pabt_svc:
         tst     r3, #PSR_I_BIT
         biceq   r9, r9, #PSR_I_BIT
 
-        @
-        @ set args, then call main handler
-        @
-        @  r0 - address of faulting instruction
-        @  r1 - pointer to registers on stack
-        @
-#ifdef MULTI_PABORT
         mov     r0, r2                  @ pass address of aborted instruction.
+#ifdef MULTI_PABORT
         ldr     r4, .LCprocfns
         mov     lr, pc
         ldr     pc, [r4, #PROCESSOR_PABT_FUNC]
 #else
-        CPU_PABORT_HANDLER(r0, r2)
+        bl      CPU_PABORT_HANDLER
 #endif
         msr     cpsr_c, r9                      @ Maybe enable interrupts
-        mov     r1, sp                          @ regs
+        mov     r2, sp                          @ regs
         bl      do_PrefetchAbort                @ call abort handler
 
         @
@@ -678,7 +680,9 @@ ENTRY(fp_enter)
         .word   no_fp
         .previous
 
-no_fp:  mov     pc, lr
+ENTRY(no_fp)
+        mov     pc, lr
+ENDPROC(no_fp)
 
 __und_usr_unknown:
         enable_irq
@@ -691,16 +695,16 @@ ENDPROC(__und_usr_unknown)
 __pabt_usr:
         usr_entry
 
-#ifdef MULTI_PABORT
         mov     r0, r2                  @ pass address of aborted instruction.
+#ifdef MULTI_PABORT
         ldr     r4, .LCprocfns
         mov     lr, pc
         ldr     pc, [r4, #PROCESSOR_PABT_FUNC]
 #else
-        CPU_PABORT_HANDLER(r0, r2)
+        bl      CPU_PABORT_HANDLER
 #endif
         enable_irq                              @ Enable interrupts
-        mov     r1, sp                          @ regs
+        mov     r2, sp                          @ regs
         bl      do_PrefetchAbort                @ call abort handler
  UNWIND(.fnend          )
         /* fall through */
@@ -734,13 +738,6 @@ ENTRY(__switch_to)
 #ifdef CONFIG_MMU
         ldr     r6, [r2, #TI_CPU_DOMAIN]
 #endif
-#if __LINUX_ARM_ARCH__ >= 6
-#ifdef CONFIG_CPU_32v6K
-        clrex
-#else
-        strex   r5, r4, [ip]                    @ Clear exclusive monitor
-#endif
-#endif
 #if defined(CONFIG_HAS_TLS_REG)
         mcr     p15, 0, r3, c13, c0, 3          @ set TLS register
 #elif !defined(CONFIG_TLS_REG_EMUL)
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 807cfebb0f44..f0fe95b7085d 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -126,7 +126,7 @@ ENTRY(__gnu_mcount_nc)
         cmp r0, r2
         bne gnu_trace
         ldmia sp!, {r0-r3, ip, lr}
-        bx ip
+        mov pc, ip
 
 gnu_trace:
         ldr r1, [sp, #20]                       @ lr of instrumented routine
@@ -135,7 +135,7 @@ gnu_trace:
         mov lr, pc
         mov pc, r2
         ldmia sp!, {r0-r3, ip, lr}
-        bx ip
+        mov pc, ip
 
 ENTRY(mcount)
         stmdb sp!, {r0-r3, lr}
@@ -425,13 +425,6 @@ sys_mmap2:
 #endif
 ENDPROC(sys_mmap2)
 
-ENTRY(pabort_ifar)
-                mrc     p15, 0, r0, cr6, cr0, 2
-ENTRY(pabort_noifar)
-                mov     pc, lr
-ENDPROC(pabort_ifar)
-ENDPROC(pabort_noifar)
-
 #ifdef CONFIG_OABI_COMPAT
 
 /*
diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S
index a4eaf4f920c5..ac34c0d9384b 100644
--- a/arch/arm/kernel/entry-header.S
+++ b/arch/arm/kernel/entry-header.S
@@ -76,13 +76,27 @@
 #ifndef CONFIG_THUMB2_KERNEL
         .macro  svc_exit, rpsr
         msr     spsr_cxsf, \rpsr
+#if defined(CONFIG_CPU_32v6K)
+        clrex                                   @ clear the exclusive monitor
         ldmia   sp, {r0 - pc}^                  @ load r0 - pc, cpsr
+#elif defined (CONFIG_CPU_V6)
+        ldr     r0, [sp]
+        strex   r1, r2, [sp]                    @ clear the exclusive monitor
+        ldmib   sp, {r1 - pc}^                  @ load r1 - pc, cpsr
+#else
+        ldmia   sp, {r0 - pc}^                  @ load r0 - pc, cpsr
+#endif
         .endm
 
         .macro  restore_user_regs, fast = 0, offset = 0
         ldr     r1, [sp, #\offset + S_PSR]      @ get calling cpsr
         ldr     lr, [sp, #\offset + S_PC]!      @ get pc
         msr     spsr_cxsf, r1                   @ save in spsr_svc
+#if defined(CONFIG_CPU_32v6K)
+        clrex                                   @ clear the exclusive monitor
+#elif defined (CONFIG_CPU_V6)
+        strex   r1, r2, [sp]                    @ clear the exclusive monitor
+#endif
         .if     \fast
         ldmdb   sp, {r1 - lr}^                  @ get calling r1 - lr
         .else
@@ -98,6 +112,7 @@
         .endm
 #else   /* CONFIG_THUMB2_KERNEL */
         .macro  svc_exit, rpsr
+        clrex                                   @ clear the exclusive monitor
         ldr     r0, [sp, #S_SP]                 @ top of the stack
         ldr     r1, [sp, #S_PC]                 @ return address
         tst     r0, #4                          @ orig stack 8-byte aligned?
@@ -110,6 +125,7 @@
         .endm
 
         .macro  restore_user_regs, fast = 0, offset = 0
+        clrex                                   @ clear the exclusive monitor
         mov     r2, sp
         load_user_sp_lr r2, r3, \offset + S_SP  @ calling sp, lr
         ldr     r1, [sp, #\offset + S_PSR]      @ get calling cpsr
diff --git a/arch/arm/kernel/head-common.S b/arch/arm/kernel/head-common.S
index 93ad576b2d74..885a7214418d 100644
--- a/arch/arm/kernel/head-common.S
+++ b/arch/arm/kernel/head-common.S
@@ -13,6 +13,7 @@
 
 #define ATAG_CORE 0x54410001
 #define ATAG_CORE_SIZE ((2*4 + 3*4) >> 2)
+#define ATAG_CORE_SIZE_EMPTY ((2*4) >> 2)
 
         .align  2
         .type   __switch_data, %object
@@ -251,7 +252,8 @@ __vet_atags:
         bne     1f
 
         ldr     r5, [r2, #0]                    @ is first tag ATAG_CORE?
-        subs    r5, r5, #ATAG_CORE_SIZE
+        cmp     r5, #ATAG_CORE_SIZE
+        cmpne   r5, #ATAG_CORE_SIZE_EMPTY
         bne     1f
         ldr     r5, [r2, #4]
         ldr     r6, =ATAG_CORE
diff --git a/arch/arm/kernel/init_task.c b/arch/arm/kernel/init_task.c
index 3f470866bb89..e7cbb50dc356 100644
--- a/arch/arm/kernel/init_task.c
+++ b/arch/arm/kernel/init_task.c
@@ -24,9 +24,8 @@ static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand);
  *
  * The things we do for performance..
  */
-union thread_union init_thread_union
-        __attribute__((__section__(".data.init_task"))) =
-                { INIT_THREAD_INFO(init_task) };
+union thread_union init_thread_union __init_task_data =
+        { INIT_THREAD_INFO(init_task) };
 
 /*
  * Initial task structure.
diff --git a/arch/arm/kernel/kprobes.c b/arch/arm/kernel/kprobes.c
index f692efddd449..60c62c377fa9 100644
--- a/arch/arm/kernel/kprobes.c
+++ b/arch/arm/kernel/kprobes.c
@@ -22,6 +22,7 @@
 #include <linux/kernel.h>
 #include <linux/kprobes.h>
 #include <linux/module.h>
+#include <linux/stop_machine.h>
 #include <linux/stringify.h>
 #include <asm/traps.h>
 #include <asm/cacheflush.h>
@@ -83,10 +84,24 @@ void __kprobes arch_arm_kprobe(struct kprobe *p)
         flush_insns(p->addr, 1);
 }
 
+/*
+ * The actual disarming is done here on each CPU and synchronized using
+ * stop_machine. This synchronization is necessary on SMP to avoid removing
+ * a probe between the moment the 'Undefined Instruction' exception is raised
+ * and the moment the exception handler reads the faulting instruction from
+ * memory.
+ */
+int __kprobes __arch_disarm_kprobe(void *p)
+{
+        struct kprobe *kp = p;
+        *kp->addr = kp->opcode;
+        flush_insns(kp->addr, 1);
+        return 0;
+}
+
 void __kprobes arch_disarm_kprobe(struct kprobe *p)
 {
-        *p->addr = p->opcode;
-        flush_insns(p->addr, 1);
+        stop_machine(__arch_disarm_kprobe, p, &cpu_online_map);
 }
 
 void __kprobes arch_remove_kprobe(struct kprobe *p)
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index d4d4f77c91b2..c6c57b640b6b 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -45,6 +45,7 @@
 
 #include "compat.h"
 #include "atags.h"
+#include "tcm.h"
 
 #ifndef MEM_SIZE
 #define MEM_SIZE        (16*1024*1024)
@@ -749,6 +750,7 @@ void __init setup_arch(char **cmdline_p)
 #endif
 
         cpu_init();
+        tcm_init();
 
         /*
          * Set up various architecture-specific pointers
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index de885fd256c5..57162af53dc9 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -36,6 +36,7 @@
 #include <asm/tlbflush.h>
 #include <asm/ptrace.h>
 #include <asm/localtimer.h>
+#include <asm/smp_plat.h>
 
 /*
  * as from 2.5, kernels no longer have an init_tasks structure
@@ -153,7 +154,7 @@ int __cpuinit __cpu_up(unsigned int cpu)
 /*
  * __cpu_disable runs on the processor to be shutdown.
  */
-int __cpuexit __cpu_disable(void)
+int __cpu_disable(void)
 {
         unsigned int cpu = smp_processor_id();
         struct task_struct *p;
@@ -189,7 +190,7 @@ int __cpuexit __cpu_disable(void)
         read_lock(&tasklist_lock);
         for_each_process(p) {
                 if (p->mm)
-                        cpu_clear(cpu, p->mm->cpu_vm_mask);
+                        cpumask_clear_cpu(cpu, mm_cpumask(p->mm));
         }
         read_unlock(&tasklist_lock);
 
@@ -200,7 +201,7 @@ int __cpuexit __cpu_disable(void)
  * called on the thread which is asking for a CPU to be shutdown -
  * waits until shutdown has completed, or it is timed out.
  */
-void __cpuexit __cpu_die(unsigned int cpu)
+void __cpu_die(unsigned int cpu)
 {
         if (!platform_cpu_kill(cpu))
                 printk("CPU%u: unable to kill\n", cpu);
@@ -214,7 +215,7 @@ void __cpuexit __cpu_die(unsigned int cpu)
  * of the other hotplug-cpu capable cores, so presumably coming
  * out of idle fixes this.
  */
-void __cpuexit cpu_die(void)
+void __ref cpu_die(void)
 {
         unsigned int cpu = smp_processor_id();
 
@@ -257,7 +258,7 @@ asmlinkage void __cpuinit secondary_start_kernel(void)
         atomic_inc(&mm->mm_users);
         atomic_inc(&mm->mm_count);
         current->active_mm = mm;
-        cpu_set(cpu, mm->cpu_vm_mask);
+        cpumask_set_cpu(cpu, mm_cpumask(mm));
         cpu_switch_mm(mm->pgd, mm);
         enter_lazy_tlb(mm, current);
         local_flush_tlb_all();
@@ -586,12 +587,6 @@ struct tlb_args {
         unsigned long ta_end;
 };
 
-/* all SMP configurations have the extended CPUID registers */
-static inline int tlb_ops_need_broadcast(void)
-{
-        return ((read_cpuid_ext(CPUID_EXT_MMFR3) >> 12) & 0xf) < 2;
-}
-
 static inline void ipi_flush_tlb_all(void *ignored)
 {
         local_flush_tlb_all();
@@ -643,7 +638,7 @@ void flush_tlb_all(void)
 void flush_tlb_mm(struct mm_struct *mm)
 {
         if (tlb_ops_need_broadcast())
-                on_each_cpu_mask(ipi_flush_tlb_mm, mm, 1, &mm->cpu_vm_mask);
+                on_each_cpu_mask(ipi_flush_tlb_mm, mm, 1, mm_cpumask(mm));
         else
                 local_flush_tlb_mm(mm);
 }
@@ -654,7 +649,7 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
                 struct tlb_args ta;
                 ta.ta_vma = vma;
                 ta.ta_start = uaddr;
-                on_each_cpu_mask(ipi_flush_tlb_page, &ta, 1, &vma->vm_mm->cpu_vm_mask);
+                on_each_cpu_mask(ipi_flush_tlb_page, &ta, 1, mm_cpumask(vma->vm_mm));
         } else
                 local_flush_tlb_page(vma, uaddr);
 }
@@ -677,7 +672,7 @@ void flush_tlb_range(struct vm_area_struct *vma,
                 ta.ta_vma = vma;
                 ta.ta_start = start;
                 ta.ta_end = end;
-                on_each_cpu_mask(ipi_flush_tlb_range, &ta, 1, &vma->vm_mm->cpu_vm_mask);
+                on_each_cpu_mask(ipi_flush_tlb_range, &ta, 1, mm_cpumask(vma->vm_mm));
         } else
                 local_flush_tlb_range(vma, start, end);
 }
diff --git a/arch/arm/kernel/smp_twd.c b/arch/arm/kernel/smp_twd.c
index d8c88c633c6f..a73a34dccf2a 100644
--- a/arch/arm/kernel/smp_twd.c
+++ b/arch/arm/kernel/smp_twd.c
@@ -166,10 +166,12 @@ void __cpuinit twd_timer_setup(struct clock_event_device *clk)
         clockevents_register_device(clk);
 }
 
+#ifdef CONFIG_HOTPLUG_CPU
 /*
  * take a local timer down
  */
-void __cpuexit twd_timer_stop(void)
+void twd_timer_stop(void)
 {
         __raw_writel(0, twd_base + TWD_TIMER_CONTROL);
 }
+#endif
diff --git a/arch/arm/kernel/sys_arm.c b/arch/arm/kernel/sys_arm.c
index b3ec641b5cf8..78ecaac65206 100644
--- a/arch/arm/kernel/sys_arm.c
+++ b/arch/arm/kernel/sys_arm.c
@@ -25,7 +25,6 @@
 #include <linux/mman.h>
 #include <linux/fs.h>
 #include <linux/file.h>
-#include <linux/utsname.h>
 #include <linux/ipc.h>
 #include <linux/uaccess.h>
 
diff --git a/arch/arm/kernel/tcm.c b/arch/arm/kernel/tcm.c
new file mode 100644
index 000000000000..e50303868f1b
--- /dev/null
+++ b/arch/arm/kernel/tcm.c
@@ -0,0 +1,246 @@
+/*
+ * Copyright (C) 2008-2009 ST-Ericsson AB
+ * License terms: GNU General Public License (GPL) version 2
+ * TCM memory handling for ARM systems
+ *
+ * Author: Linus Walleij <linus.walleij@stericsson.com>
+ * Author: Rickard Andersson <rickard.andersson@stericsson.com>
+ */
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/stddef.h>
+#include <linux/ioport.h>
+#include <linux/genalloc.h>
+#include <linux/string.h> /* memcpy */
+#include <asm/page.h> /* PAGE_SHIFT */
+#include <asm/cputype.h>
+#include <asm/mach/map.h>
+#include <mach/memory.h>
+#include "tcm.h"
+
+/* Scream and warn about misuse */
+#if !defined(ITCM_OFFSET) || !defined(ITCM_END) || \
+    !defined(DTCM_OFFSET) || !defined(DTCM_END)
+#error "TCM support selected but offsets not defined!"
+#endif
+
+static struct gen_pool *tcm_pool;
+
+/* TCM section definitions from the linker */
+extern char __itcm_start, __sitcm_text, __eitcm_text;
+extern char __dtcm_start, __sdtcm_data, __edtcm_data;
+
+/*
+ * TCM memory resources
+ */
+static struct resource dtcm_res = {
+        .name = "DTCM RAM",
+        .start = DTCM_OFFSET,
+        .end = DTCM_END,
+        .flags = IORESOURCE_MEM
+};
+
+static struct resource itcm_res = {
+        .name = "ITCM RAM",
+        .start = ITCM_OFFSET,
+        .end = ITCM_END,
+        .flags = IORESOURCE_MEM
+};
+
+static struct map_desc dtcm_iomap[] __initdata = {
+        {
+                .virtual        = DTCM_OFFSET,
+                .pfn            = __phys_to_pfn(DTCM_OFFSET),
+                .length         = (DTCM_END - DTCM_OFFSET + 1),
+                .type           = MT_UNCACHED
+        }
+};
+
+static struct map_desc itcm_iomap[] __initdata = {
+        {
+                .virtual        = ITCM_OFFSET,
+                .pfn            = __phys_to_pfn(ITCM_OFFSET),
+                .length         = (ITCM_END - ITCM_OFFSET + 1),
+                .type           = MT_UNCACHED
+        }
+};
+
+/*
+ * Allocate a chunk of TCM memory
+ */
+void *tcm_alloc(size_t len)
+{
+        unsigned long vaddr;
+
+        if (!tcm_pool)
+                return NULL;
+
+        vaddr = gen_pool_alloc(tcm_pool, len);
+        if (!vaddr)
+                return NULL;
+
+        return (void *) vaddr;
+}
+EXPORT_SYMBOL(tcm_alloc);
+
+/*
+ * Free a chunk of TCM memory
+ */
+void tcm_free(void *addr, size_t len)
+{
+        gen_pool_free(tcm_pool, (unsigned long) addr, len);
+}
+EXPORT_SYMBOL(tcm_free);
+
+
+static void __init setup_tcm_bank(u8 type, u32 offset, u32 expected_size)
+{
+        const int tcm_sizes[16] = { 0, -1, -1, 4, 8, 16, 32, 64, 128,
+                                    256, 512, 1024, -1, -1, -1, -1 };
+        u32 tcm_region;
+        int tcm_size;
+
+        /* Read the special TCM region register c9, 0 */
+        if (!type)
+                asm("mrc        p15, 0, %0, c9, c1, 0"
+                    : "=r" (tcm_region));
+        else
+                asm("mrc        p15, 0, %0, c9, c1, 1"
+                    : "=r" (tcm_region));
+
+        tcm_size = tcm_sizes[(tcm_region >> 2) & 0x0f];
+        if (tcm_size < 0) {
+                pr_err("CPU: %sTCM of unknown size!\n",
+                        type ? "I" : "D");
+        } else {
+                pr_info("CPU: found %sTCM %dk @ %08x, %senabled\n",
+                        type ? "I" : "D",
+                        tcm_size,
+                        (tcm_region & 0xfffff000U),
+                        (tcm_region & 1) ? "" : "not ");
+        }
+
+        if (tcm_size != expected_size) {
+                pr_crit("CPU: %sTCM was detected %dk but expected %dk!\n",
+                       type ? "I" : "D",
+                       tcm_size,
+                       expected_size);
+                /* Adjust to the expected size? what can we do... */
+        }
+
+        /* Force move the TCM bank to where we want it, enable */
+        tcm_region = offset | (tcm_region & 0x00000ffeU) | 1;
+
+        if (!type)
+                asm("mcr        p15, 0, %0, c9, c1, 0"
+                    : /* No output operands */
+                    : "r" (tcm_region));
+        else
+                asm("mcr        p15, 0, %0, c9, c1, 1"
+                    : /* No output operands */
+                    : "r" (tcm_region));
+
+        pr_debug("CPU: moved %sTCM %dk to %08x, enabled\n",
+                 type ? "I" : "D",
+                 tcm_size,
+                 (tcm_region & 0xfffff000U));
+}
+
+/*
+ * This initializes the TCM memory
+ */
+void __init tcm_init(void)
+{
+        u32 tcm_status = read_cpuid_tcmstatus();
+        char *start;
+        char *end;
+        char *ram;
+
+        /* Setup DTCM if present */
+        if (tcm_status & (1 << 16)) {
+                setup_tcm_bank(0, DTCM_OFFSET,
+                               (DTCM_END - DTCM_OFFSET + 1) >> 10);
+                request_resource(&iomem_resource, &dtcm_res);
+                iotable_init(dtcm_iomap, 1);
+                /* Copy data from RAM to DTCM */
+                start = &__sdtcm_data;
+                end   = &__edtcm_data;
+                ram   = &__dtcm_start;
+                memcpy(start, ram, (end-start));
+                pr_debug("CPU DTCM: copied data from %p - %p\n", start, end);
+        }
+
+        /* Setup ITCM if present */
+        if (tcm_status & 1) {
+                setup_tcm_bank(1, ITCM_OFFSET,
+                               (ITCM_END - ITCM_OFFSET + 1) >> 10);
+                request_resource(&iomem_resource, &itcm_res);
+                iotable_init(itcm_iomap, 1);
+                /* Copy code from RAM to ITCM */
+                start = &__sitcm_text;
+                end   = &__eitcm_text;
+                ram   = &__itcm_start;
+                memcpy(start, ram, (end-start));
+                pr_debug("CPU ITCM: copied code from %p - %p\n", start, end);
+        }
+}
+
+/*
+ * This creates the TCM memory pool and has to be done later,
+ * during the core_initicalls, since the allocator is not yet
+ * up and running when the first initialization runs.
+ */
+static int __init setup_tcm_pool(void)
+{
+        u32 tcm_status = read_cpuid_tcmstatus();
+        u32 dtcm_pool_start = (u32) &__edtcm_data;
+        u32 itcm_pool_start = (u32) &__eitcm_text;
+        int ret;
+
+        /*
+         * Set up malloc pool, 2^2 = 4 bytes granularity since
+         * the TCM is sometimes just 4 KiB. NB: pages and cache
+         * line alignments does not matter in TCM!
+         */
+        tcm_pool = gen_pool_create(2, -1);
+
+        pr_debug("Setting up TCM memory pool\n");
+
+        /* Add the rest of DTCM to the TCM pool */
+        if (tcm_status & (1 << 16)) {
+                if (dtcm_pool_start < DTCM_END) {
+                        ret = gen_pool_add(tcm_pool, dtcm_pool_start,
+                                           DTCM_END - dtcm_pool_start + 1, -1);
+                        if (ret) {
+                                pr_err("CPU DTCM: could not add DTCM " \
+                                       "remainder to pool!\n");
+                                return ret;
+                        }
+                        pr_debug("CPU DTCM: Added %08x bytes @ %08x to " \
+                                 "the TCM memory pool\n",
+                                 DTCM_END - dtcm_pool_start + 1,
+                                 dtcm_pool_start);
+                }
+        }
+
+        /* Add the rest of ITCM to the TCM pool */
+        if (tcm_status & 1) {
+                if (itcm_pool_start < ITCM_END) {
+                        ret = gen_pool_add(tcm_pool, itcm_pool_start,
+                                           ITCM_END - itcm_pool_start + 1, -1);
+                        if (ret) {
+                                pr_err("CPU ITCM: could not add ITCM " \
+                                       "remainder to pool!\n");
+                                return ret;
+                        }
+                        pr_debug("CPU ITCM: Added %08x bytes @ %08x to " \
+                                 "the TCM memory pool\n",
+                                 ITCM_END - itcm_pool_start + 1,
+                                 itcm_pool_start);
+                }
+        }
+        return 0;
+}
+
+core_initcall(setup_tcm_pool);
diff --git a/arch/arm/kernel/tcm.h b/arch/arm/kernel/tcm.h
new file mode 100644
index 000000000000..8015ad434a40
--- /dev/null
+++ b/arch/arm/kernel/tcm.h
@@ -0,0 +1,17 @@
+/*
+ * Copyright (C) 2008-2009 ST-Ericsson AB
+ * License terms: GNU General Public License (GPL) version 2
+ * TCM memory handling for ARM systems
+ *
+ * Author: Linus Walleij <linus.walleij@stericsson.com>
+ * Author: Rickard Andersson <rickard.andersson@stericsson.com>
+ */
+
+#ifdef CONFIG_HAVE_TCM
+void __init tcm_init(void);
+#else
+/* No TCM support, just blank inlines to be optimized out */
+inline void tcm_init(void)
+{
+}
+#endif
diff --git a/arch/arm/kernel/time.c b/arch/arm/kernel/time.c
index 4cdc4a0bd02d..d38cdf2c8276 100644
--- a/arch/arm/kernel/time.c
+++ b/arch/arm/kernel/time.c
@@ -21,6 +21,7 @@
 #include <linux/interrupt.h>
 #include <linux/time.h>
 #include <linux/init.h>
+#include <linux/sched.h>
 #include <linux/smp.h>
 #include <linux/timex.h>
 #include <linux/errno.h>
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index 57eb0f6f6005..f838f36eb702 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -45,21 +45,21 @@ static int __init user_debug_setup(char *str)
 __setup("user_debug=", user_debug_setup);
 #endif
 
-static void dump_mem(const char *str, unsigned long bottom, unsigned long top);
+static void dump_mem(const char *, const char *, unsigned long, unsigned long);
 
 void dump_backtrace_entry(unsigned long where, unsigned long from, unsigned long frame)
 {
 #ifdef CONFIG_KALLSYMS
-        printk("[<%08lx>] ", where);
-        print_symbol("(%s) ", where);
-        printk("from [<%08lx>] ", from);
-        print_symbol("(%s)\n", from);
+        char sym1[KSYM_SYMBOL_LEN], sym2[KSYM_SYMBOL_LEN];
+        sprint_symbol(sym1, where);
+        sprint_symbol(sym2, from);
+        printk("[<%08lx>] (%s) from [<%08lx>] (%s)\n", where, sym1, from, sym2);
 #else
         printk("Function entered at [<%08lx>] from [<%08lx>]\n", where, from);
 #endif
 
         if (in_exception_text(where))
-                dump_mem("Exception stack", frame + 4, frame + 4 + sizeof(struct pt_regs));
+                dump_mem("", "Exception stack", frame + 4, frame + 4 + sizeof(struct pt_regs));
 }
 
 #ifndef CONFIG_ARM_UNWIND
@@ -81,9 +81,10 @@ static int verify_stack(unsigned long sp)
 /*
  * Dump out the contents of some memory nicely...
  */
-static void dump_mem(const char *str, unsigned long bottom, unsigned long top)
+static void dump_mem(const char *lvl, const char *str, unsigned long bottom,
+                     unsigned long top)
 {
-        unsigned long p = bottom & ~31;
+        unsigned long first;
         mm_segment_t fs;
         int i;
 
@@ -95,33 +96,37 @@ static void dump_mem(const char *str, unsigned long bottom, unsigned long top)
         fs = get_fs();
         set_fs(KERNEL_DS);
 
-        printk("%s(0x%08lx to 0x%08lx)\n", str, bottom, top);
+        printk("%s%s(0x%08lx to 0x%08lx)\n", lvl, str, bottom, top);
 
-        for (p = bottom & ~31; p < top;) {
-                printk("%04lx: ", p & 0xffff);
+        for (first = bottom & ~31; first < top; first += 32) {
+                unsigned long p;
+                char str[sizeof(" 12345678") * 8 + 1];
 
-                for (i = 0; i < 8; i++, p += 4) {
-                        unsigned int val;
+                memset(str, ' ', sizeof(str));
+                str[sizeof(str) - 1] = '\0';
 
-                        if (p < bottom || p >= top)
-                                printk("         ");
-                        else {
-                                __get_user(val, (unsigned long *)p);
-                                printk("%08x ", val);
+                for (p = first, i = 0; i < 8 && p < top; i++, p += 4) {
+                        if (p >= bottom && p < top) {
+                                unsigned long val;
+                                if (__get_user(val, (unsigned long *)p) == 0)
+                                        sprintf(str + i * 9, " %08lx", val);
+                                else
+                                        sprintf(str + i * 9, " ????????");
                         }
                 }
-                printk ("\n");
+                printk("%s%04lx:%s\n", lvl, first & 0xffff, str);
         }
 
         set_fs(fs);
 }
 
-static void dump_instr(struct pt_regs *regs)
+static void dump_instr(const char *lvl, struct pt_regs *regs)
 {
         unsigned long addr = instruction_pointer(regs);
         const int thumb = thumb_mode(regs);
         const int width = thumb ? 4 : 8;
         mm_segment_t fs;
+        char str[sizeof("00000000 ") * 5 + 2 + 1], *p = str;
         int i;
 
         /*
@@ -132,7 +137,6 @@ static void dump_instr(struct pt_regs *regs)
         fs = get_fs();
         set_fs(KERNEL_DS);
 
-        printk("Code: ");
         for (i = -4; i < 1; i++) {
                 unsigned int val, bad;
 
@@ -142,13 +146,14 @@ static void dump_instr(struct pt_regs *regs)
                         bad = __get_user(val, &((u32 *)addr)[i]);
 
                 if (!bad)
-                        printk(i == 0 ? "(%0*x) " : "%0*x ", width, val);
+                        p += sprintf(p, i == 0 ? "(%0*x) " : "%0*x ",
+                                        width, val);
                 else {
-                        printk("bad PC value.");
+                        p += sprintf(p, "bad PC value");
                         break;
                 }
         }
-        printk("\n");
+        printk("%sCode: %s\n", lvl, str);
 
         set_fs(fs);
 }
@@ -224,18 +229,19 @@ static void __die(const char *str, int err, struct thread_info *thread, struct p
         struct task_struct *tsk = thread->task;
         static int die_counter;
 
-        printk("Internal error: %s: %x [#%d]" S_PREEMPT S_SMP "\n",
+        printk(KERN_EMERG "Internal error: %s: %x [#%d]" S_PREEMPT S_SMP "\n",
                str, err, ++die_counter);
+        sysfs_printk_last_file();
         print_modules();
         __show_regs(regs);
-        printk("Process %s (pid: %d, stack limit = 0x%p)\n",
-                tsk->comm, task_pid_nr(tsk), thread + 1);
+        printk(KERN_EMERG "Process %.*s (pid: %d, stack limit = 0x%p)\n",
+                TASK_COMM_LEN, tsk->comm, task_pid_nr(tsk), thread + 1);
 
         if (!user_mode(regs) || in_interrupt()) {
-                dump_mem("Stack: ", regs->ARM_sp,
+                dump_mem(KERN_EMERG, "Stack: ", regs->ARM_sp,
                          THREAD_SIZE + (unsigned long)task_stack_page(tsk));
                 dump_backtrace(regs, tsk);
-                dump_instr(regs);
+                dump_instr(KERN_EMERG, regs);
         }
 }
 
@@ -250,13 +256,14 @@ NORET_TYPE void die(const char *str, struct pt_regs *regs, int err)
 
         oops_enter();
 
-        console_verbose();
         spin_lock_irq(&die_lock);
+        console_verbose();
         bust_spinlocks(1);
         __die(str, err, thread, regs);
         bust_spinlocks(0);
         add_taint(TAINT_DIE);
         spin_unlock_irq(&die_lock);
+        oops_exit();
 
         if (in_interrupt())
                 panic("Fatal exception in interrupt");
@@ -264,7 +271,6 @@ NORET_TYPE void die(const char *str, struct pt_regs *regs, int err)
         if (panic_on_oops)
                 panic("Fatal exception");
 
-        oops_exit();
         do_exit(SIGSEGV);
 }
 
@@ -349,7 +355,7 @@ asmlinkage void __exception do_undefinstr(struct pt_regs *regs)
         if (user_debug & UDBG_UNDEFINED) {
                 printk(KERN_INFO "%s (%d): undefined instruction: pc=%p\n",
                         current->comm, task_pid_nr(current), pc);
-                dump_instr(regs);
+                dump_instr(KERN_INFO, regs);
         }
 #endif
 
@@ -400,7 +406,7 @@ static int bad_syscall(int n, struct pt_regs *regs)
         if (user_debug & UDBG_SYSCALL) {
                 printk(KERN_ERR "[%d] %s: obsolete system call %08x.\n",
                         task_pid_nr(current), current->comm, n);
-                dump_instr(regs);
+                dump_instr(KERN_ERR, regs);
         }
 #endif
 
@@ -418,12 +424,14 @@ static int bad_syscall(int n, struct pt_regs *regs)
 static inline void
 do_cache_op(unsigned long start, unsigned long end, int flags)
 {
+        struct mm_struct *mm = current->active_mm;
         struct vm_area_struct *vma;
 
         if (end < start || flags)
                 return;
 
-        vma = find_vma(current->active_mm, start);
+        down_read(&mm->mmap_sem);
+        vma = find_vma(mm, start);
         if (vma && vma->vm_start < end) {
                 if (start < vma->vm_start)
                         start = vma->vm_start;
@@ -432,6 +440,7 @@ do_cache_op(unsigned long start, unsigned long end, int flags)
 
                 flush_cache_user_range(vma, start, end);
         }
+        up_read(&mm->mmap_sem);
 }
 
 /*
@@ -576,7 +585,7 @@ asmlinkage int arm_syscall(int no, struct pt_regs *regs)
         if (user_debug & UDBG_SYSCALL) {
                 printk("[%d] %s: arm syscall %d\n",
                        task_pid_nr(current), current->comm, no);
-                dump_instr(regs);
+                dump_instr("", regs);
                 if (user_mode(regs)) {
                         __show_regs(regs);
                         c_backtrace(regs->ARM_fp, processor_mode(regs));
@@ -653,7 +662,7 @@ baddataabort(int code, unsigned long instr, struct pt_regs *regs)
         if (user_debug & UDBG_BADABORT) {
                 printk(KERN_ERR "[%d] %s: bad data abort: code %d instr 0x%08lx\n",
                         task_pid_nr(current), current->comm, code, instr);
-                dump_instr(regs);
+                dump_instr(KERN_ERR, regs);
                 show_pte(current->mm, addr);
         }
 #endif
diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S
index 5cc4812c9763..aecf87dfbaec 100644
--- a/arch/arm/kernel/vmlinux.lds.S
+++ b/arch/arm/kernel/vmlinux.lds.S
@@ -199,6 +199,63 @@ SECTIONS
         }
         _edata_loc = __data_loc + SIZEOF(.data);
 
+#ifdef CONFIG_HAVE_TCM
+        /*
+         * We align everything to a page boundary so we can
+         * free it after init has commenced and TCM contents have
+         * been copied to its destination.
+         */
+        .tcm_start : {
+                . = ALIGN(PAGE_SIZE);
+                __tcm_start = .;
+                __itcm_start = .;
+        }
+
+        /*
+         * Link these to the ITCM RAM
+         * Put VMA to the TCM address and LMA to the common RAM
+         * and we'll upload the contents from RAM to TCM and free
+         * the used RAM after that.
+         */
+        .text_itcm ITCM_OFFSET : AT(__itcm_start)
+        {
+                __sitcm_text = .;
+                *(.tcm.text)
+                *(.tcm.rodata)
+                . = ALIGN(4);
+                __eitcm_text = .;
+        }
+
+        /*
+         * Reset the dot pointer, this is needed to create the
+         * relative __dtcm_start below (to be used as extern in code).
+         */
+        . = ADDR(.tcm_start) + SIZEOF(.tcm_start) + SIZEOF(.text_itcm);
+
+        .dtcm_start : {
+                __dtcm_start = .;
+        }
+
+        /* TODO: add remainder of ITCM as well, that can be used for data! */
+        .data_dtcm DTCM_OFFSET : AT(__dtcm_start)
+        {
+                . = ALIGN(4);
+                __sdtcm_data = .;
+                *(.tcm.data)
+                . = ALIGN(4);
+                __edtcm_data = .;
+        }
+
+        /* Reset the dot pointer or the linker gets confused */
+        . = ADDR(.dtcm_start) + SIZEOF(.data_dtcm);
+
+        /* End marker for freeing TCM copy in linked object */
+        .tcm_end : AT(ADDR(.dtcm_start) + SIZEOF(.data_dtcm)){
+                . = ALIGN(PAGE_SIZE);
+                __tcm_end = .;
+        }
+#endif
+
         .bss : {
                 __bss_start = .;        /* BSS                          */
                 *(.bss)