8 files changed, 365 insertions, 10 deletions

diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index c446aeff7b89..79087dd6d869 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -35,6 +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..0a2ba51cf35d 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
 
@@ -678,7 +686,9 @@ 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
@@ -734,13 +744,6 @@ 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-header.S b/arch/arm/kernel/entry-header.S
index a4eaf4f920c5..e17e3c30d957 100644
--- a/arch/arm/kernel/entry-header.S
+++ b/arch/arm/kernel/entry-header.S
@@ -76,13 +76,25 @@
 #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
+#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 +110,7 @@
         .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 +123,7 @@
         .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/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/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/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)