12 files changed, 113 insertions, 24 deletions

diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index 6e8f05c8a1c8..d7575554e407 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -215,7 +215,7 @@
         @ Slightly optimised to avoid incrementing the pointer twice
         usraccoff \instr, \reg, \ptr, \inc, 0, \cond, \abort
         .if     \rept == 2
-        usraccoff \instr, \reg, \ptr, \inc, 4, \cond, \abort
+        usraccoff \instr, \reg, \ptr, \inc, \inc, \cond, \abort
         .endif
 
         add\cond \ptr, #\rept * \inc
diff --git a/arch/arm/include/asm/kgdb.h b/arch/arm/include/asm/kgdb.h
index 08265993227f..48066ce9ea34 100644
--- a/arch/arm/include/asm/kgdb.h
+++ b/arch/arm/include/asm/kgdb.h
@@ -70,7 +70,8 @@ extern int kgdb_fault_expected;
 #define _GP_REGS                16
 #define _FP_REGS                8
 #define _EXTRA_REGS             2
-#define DBG_MAX_REG_NUM         (_GP_REGS + (_FP_REGS * 3) + _EXTRA_REGS)
+#define GDB_MAX_REGS            (_GP_REGS + (_FP_REGS * 3) + _EXTRA_REGS)
+#define DBG_MAX_REG_NUM         (_GP_REGS + _FP_REGS + _EXTRA_REGS)
 
 #define KGDB_MAX_NO_CPUS        1
 #define BUFMAX                  400
@@ -93,7 +94,7 @@ extern int kgdb_fault_expected;
 #define _SPT                    13
 #define _LR                     14
 #define _PC                     15
-#define _CPSR                   (DBG_MAX_REG_NUM - 1)
+#define _CPSR                   (GDB_MAX_REGS - 1)
 
 /*
  * So that we can denote the end of a frame for tracing,
diff --git a/arch/arm/kernel/kgdb.c b/arch/arm/kernel/kgdb.c
index d6e8b4d2e60d..778c2f7024ff 100644
--- a/arch/arm/kernel/kgdb.c
+++ b/arch/arm/kernel/kgdb.c
@@ -79,7 +79,7 @@ sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *task)
                 return;
 
         /* Initialize to zero */
-        for (regno = 0; regno < DBG_MAX_REG_NUM; regno++)
+        for (regno = 0; regno < GDB_MAX_REGS; regno++)
                 gdb_regs[regno] = 0;
 
         /* Otherwise, we have only some registers from switch_to() */
diff --git a/arch/arm/lib/findbit.S b/arch/arm/lib/findbit.S
index 1e4cbd4e7be9..64f6bc1a9132 100644
--- a/arch/arm/lib/findbit.S
+++ b/arch/arm/lib/findbit.S
@@ -174,8 +174,8 @@ ENDPROC(_find_next_bit_be)
  */
 .L_found:
 #if __LINUX_ARM_ARCH__ >= 5
-                rsb     r1, r3, #0
-                and     r3, r3, r1
+                rsb     r0, r3, #0
+                and     r3, r3, r0
                 clz     r3, r3
                 rsb     r3, r3, #31
                 add     r0, r2, r3
@@ -190,5 +190,7 @@ ENDPROC(_find_next_bit_be)
                 addeq   r2, r2, #1
                 mov     r0, r2
 #endif
+                cmp     r1, r0                  @ Clamp to maxbit
+                movlo   r0, r1
                 mov     pc, lr
 
diff --git a/arch/arm/mach-at91/include/mach/at91_mci.h b/arch/arm/mach-at91/include/mach/at91_mci.h
index 57f8ee154943..27ac6f550fe3 100644
--- a/arch/arm/mach-at91/include/mach/at91_mci.h
+++ b/arch/arm/mach-at91/include/mach/at91_mci.h
@@ -74,6 +74,8 @@
 #define                 AT91_MCI_TRTYP_BLOCK    (0 << 19)
 #define                 AT91_MCI_TRTYP_MULTIPLE (1 << 19)
 #define                 AT91_MCI_TRTYP_STREAM   (2 << 19)
+#define                 AT91_MCI_TRTYP_SDIO_BYTE        (4 << 19)
+#define                 AT91_MCI_TRTYP_SDIO_BLOCK       (5 << 19)
 
 #define AT91_MCI_BLKR           0x18            /* Block Register */
 #define         AT91_MCI_BLKR_BCNT(n)   ((0xffff & (n)) << 0)   /* Block count */
diff --git a/arch/arm/mach-cns3xxx/include/mach/debug-macro.S b/arch/arm/mach-cns3xxx/include/mach/debug-macro.S
index d16ce7eb00e9..9b50442d4b9b 100644
--- a/arch/arm/mach-cns3xxx/include/mach/debug-macro.S
+++ b/arch/arm/mach-cns3xxx/include/mach/debug-macro.S
@@ -10,7 +10,7 @@
  * published by the Free Software Foundation.
  */
 
-                .macro  addruart,rx
+                .macro  addruart,rx,rtmp
                 mrc     p15, 0, \rx, c1, c0
                 tst     \rx, #1                 @ MMU enabled?
                 moveq   \rx,      #0x10000000
diff --git a/arch/arm/mach-cns3xxx/pcie.c b/arch/arm/mach-cns3xxx/pcie.c
index 38088c36936c..78defd71a829 100644
--- a/arch/arm/mach-cns3xxx/pcie.c
+++ b/arch/arm/mach-cns3xxx/pcie.c
@@ -369,7 +369,7 @@ static int __init cns3xxx_pcie_init(void)
 {
         int i;
 
-        hook_fault_code(16 + 6, cns3xxx_pcie_abort_handler, SIGBUS,
+        hook_fault_code(16 + 6, cns3xxx_pcie_abort_handler, SIGBUS, 0,
                         "imprecise external abort");
 
         for (i = 0; i < ARRAY_SIZE(cns3xxx_pcie); i++) {
diff --git a/arch/arm/mm/cache-v6.S b/arch/arm/mm/cache-v6.S
index 86aa689ef1aa..47010d8114b0 100644
--- a/arch/arm/mm/cache-v6.S
+++ b/arch/arm/mm/cache-v6.S
@@ -196,6 +196,10 @@ ENTRY(v6_flush_kern_dcache_area)
  *      - end     - virtual end address of region
  */
 v6_dma_inv_range:
+#ifdef CONFIG_DMA_CACHE_RWFO
+        ldrb    r2, [r0]                        @ read for ownership
+        strb    r2, [r0]                        @ write for ownership
+#endif
         tst     r0, #D_CACHE_LINE_SIZE - 1
         bic     r0, r0, #D_CACHE_LINE_SIZE - 1
 #ifdef HARVARD_CACHE
@@ -204,6 +208,10 @@ v6_dma_inv_range:
         mcrne   p15, 0, r0, c7, c11, 1          @ clean unified line
 #endif
         tst     r1, #D_CACHE_LINE_SIZE - 1
+#ifdef CONFIG_DMA_CACHE_RWFO
+        ldrneb  r2, [r1, #-1]                   @ read for ownership
+        strneb  r2, [r1, #-1]                   @ write for ownership
+#endif
         bic     r1, r1, #D_CACHE_LINE_SIZE - 1
 #ifdef HARVARD_CACHE
         mcrne   p15, 0, r1, c7, c14, 1          @ clean & invalidate D line
@@ -211,10 +219,6 @@ v6_dma_inv_range:
         mcrne   p15, 0, r1, c7, c15, 1          @ clean & invalidate unified line
 #endif
 1:
-#ifdef CONFIG_DMA_CACHE_RWFO
-        ldr     r2, [r0]                        @ read for ownership
-        str     r2, [r0]                        @ write for ownership
-#endif
 #ifdef HARVARD_CACHE
         mcr     p15, 0, r0, c7, c6, 1           @ invalidate D line
 #else
@@ -222,6 +226,10 @@ v6_dma_inv_range:
 #endif
         add     r0, r0, #D_CACHE_LINE_SIZE
         cmp     r0, r1
+#ifdef CONFIG_DMA_CACHE_RWFO
+        ldrlo   r2, [r0]                        @ read for ownership
+        strlo   r2, [r0]                        @ write for ownership
+#endif
         blo     1b
         mov     r0, #0
         mcr     p15, 0, r0, c7, c10, 4          @ drain write buffer
@@ -256,12 +264,12 @@ v6_dma_clean_range:
  *      - end     - virtual end address of region
  */
 ENTRY(v6_dma_flush_range)
-        bic     r0, r0, #D_CACHE_LINE_SIZE - 1
-1:
 #ifdef CONFIG_DMA_CACHE_RWFO
-        ldr     r2, [r0]                        @ read for ownership
-        str     r2, [r0]                        @ write for ownership
+        ldrb    r2, [r0]                @ read for ownership
+        strb    r2, [r0]                @ write for ownership
 #endif
+        bic     r0, r0, #D_CACHE_LINE_SIZE - 1
+1:
 #ifdef HARVARD_CACHE
         mcr     p15, 0, r0, c7, c14, 1          @ clean & invalidate D line
 #else
@@ -269,6 +277,10 @@ ENTRY(v6_dma_flush_range)
 #endif
         add     r0, r0, #D_CACHE_LINE_SIZE
         cmp     r0, r1
+#ifdef CONFIG_DMA_CACHE_RWFO
+        ldrlob  r2, [r0]                        @ read for ownership
+        strlob  r2, [r0]                        @ write for ownership
+#endif
         blo     1b
         mov     r0, #0
         mcr     p15, 0, r0, c7, c10, 4          @ drain write buffer
diff --git a/arch/arm/mm/fault-armv.c b/arch/arm/mm/fault-armv.c
index 9b906dec1ca1..56036ff04deb 100644
--- a/arch/arm/mm/fault-armv.c
+++ b/arch/arm/mm/fault-armv.c
@@ -65,6 +65,30 @@ static int do_adjust_pte(struct vm_area_struct *vma, unsigned long address,
         return ret;
 }
 
+#if USE_SPLIT_PTLOCKS
+/*
+ * If we are using split PTE locks, then we need to take the page
+ * lock here.  Otherwise we are using shared mm->page_table_lock
+ * which is already locked, thus cannot take it.
+ */
+static inline void do_pte_lock(spinlock_t *ptl)
+{
+        /*
+         * Use nested version here to indicate that we are already
+         * holding one similar spinlock.
+         */
+        spin_lock_nested(ptl, SINGLE_DEPTH_NESTING);
+}
+
+static inline void do_pte_unlock(spinlock_t *ptl)
+{
+        spin_unlock(ptl);
+}
+#else /* !USE_SPLIT_PTLOCKS */
+static inline void do_pte_lock(spinlock_t *ptl) {}
+static inline void do_pte_unlock(spinlock_t *ptl) {}
+#endif /* USE_SPLIT_PTLOCKS */
+
 static int adjust_pte(struct vm_area_struct *vma, unsigned long address,
         unsigned long pfn)
 {
@@ -89,11 +113,11 @@ static int adjust_pte(struct vm_area_struct *vma, unsigned long address,
          */
         ptl = pte_lockptr(vma->vm_mm, pmd);
         pte = pte_offset_map_nested(pmd, address);
-        spin_lock(ptl);
+        do_pte_lock(ptl);
 
         ret = do_adjust_pte(vma, address, pfn, pte);
 
-        spin_unlock(ptl);
+        do_pte_unlock(ptl);
         pte_unmap_nested(pte);
 
         return ret;
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 7185b00650fe..4e2f620de09b 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -282,6 +282,12 @@ void __init arm_memblock_init(struct meminfo *mi, struct machine_desc *mdesc)
         memblock_reserve(__pa(_stext), _end - _stext);
 #endif
 #ifdef CONFIG_BLK_DEV_INITRD
+        if (phys_initrd_size &&
+            memblock_is_region_reserved(phys_initrd_start, phys_initrd_size)) {
+                pr_err("INITRD: 0x%08lx+0x%08lx overlaps in-use memory region - disabling initrd\n",
+                       phys_initrd_start, phys_initrd_size);
+                phys_initrd_start = phys_initrd_size = 0;
+        }
         if (phys_initrd_size) {
                 memblock_reserve(phys_initrd_start, phys_initrd_size);
 
diff --git a/arch/arm/plat-omap/dma.c b/arch/arm/plat-omap/dma.c
index ec7eddf9e525..f5c5b8da9a87 100644
--- a/arch/arm/plat-omap/dma.c
+++ b/arch/arm/plat-omap/dma.c
@@ -30,6 +30,7 @@
 #include <linux/irq.h>
 #include <linux/io.h>
 #include <linux/slab.h>
+#include <linux/delay.h>
 
 #include <asm/system.h>
 #include <mach/hardware.h>
@@ -996,11 +997,17 @@ void omap_start_dma(int lch)
         l = dma_read(CCR(lch));
 
         /*
-         * Errata: On ES2.0 BUFFERING disable must be set.
-         * This will always fail on ES1.0
+         * Errata: Inter Frame DMA buffering issue (All OMAP2420 and
+         * OMAP2430ES1.0): DMA will wrongly buffer elements if packing and
+         * bursting is enabled. This might result in data gets stalled in
+         * FIFO at the end of the block.
+         * Workaround: DMA channels must have BUFFERING_DISABLED bit set to
+         * guarantee no data will stay in the DMA FIFO in case inter frame
+         * buffering occurs.
          */
-        if (cpu_is_omap24xx())
-                l |= OMAP_DMA_CCR_EN;
+        if (cpu_is_omap2420() ||
+            (cpu_is_omap2430() && (omap_type() == OMAP2430_REV_ES1_0)))
+                l |= OMAP_DMA_CCR_BUFFERING_DISABLE;
 
         l |= OMAP_DMA_CCR_EN;
         dma_write(l, CCR(lch));
@@ -1018,8 +1025,39 @@ void omap_stop_dma(int lch)
                 dma_write(0, CICR(lch));
 
         l = dma_read(CCR(lch));
-        l &= ~OMAP_DMA_CCR_EN;
-        dma_write(l, CCR(lch));
+        /* OMAP3 Errata i541: sDMA FIFO draining does not finish */
+        if (cpu_is_omap34xx() && (l & OMAP_DMA_CCR_SEL_SRC_DST_SYNC)) {
+                int i = 0;
+                u32 sys_cf;
+
+                /* Configure No-Standby */
+                l = dma_read(OCP_SYSCONFIG);
+                sys_cf = l;
+                l &= ~DMA_SYSCONFIG_MIDLEMODE_MASK;
+                l |= DMA_SYSCONFIG_MIDLEMODE(DMA_IDLEMODE_NO_IDLE);
+                dma_write(l , OCP_SYSCONFIG);
+
+                l = dma_read(CCR(lch));
+                l &= ~OMAP_DMA_CCR_EN;
+                dma_write(l, CCR(lch));
+
+                /* Wait for sDMA FIFO drain */
+                l = dma_read(CCR(lch));
+                while (i < 100 && (l & (OMAP_DMA_CCR_RD_ACTIVE |
+                                        OMAP_DMA_CCR_WR_ACTIVE))) {
+                        udelay(5);
+                        i++;
+                        l = dma_read(CCR(lch));
+                }
+                if (i >= 100)
+                        printk(KERN_ERR "DMA drain did not complete on "
+                                        "lch %d\n", lch);
+                /* Restore OCP_SYSCONFIG */
+                dma_write(sys_cf, OCP_SYSCONFIG);
+        } else {
+                l &= ~OMAP_DMA_CCR_EN;
+                dma_write(l, CCR(lch));
+        }
 
         if (!omap_dma_in_1510_mode() && dma_chan[lch].next_lch != -1) {
                 int next_lch, cur_lch = lch;
diff --git a/arch/arm/plat-omap/include/plat/dma.h b/arch/arm/plat-omap/include/plat/dma.h
index af3a03941add..cf66f85a011c 100644
--- a/arch/arm/plat-omap/include/plat/dma.h
+++ b/arch/arm/plat-omap/include/plat/dma.h
@@ -335,6 +335,10 @@
 #define OMAP2_DMA_MISALIGNED_ERR_IRQ    (1 << 11)
 
 #define OMAP_DMA_CCR_EN                 (1 << 7)
+#define OMAP_DMA_CCR_RD_ACTIVE          (1 << 9)
+#define OMAP_DMA_CCR_WR_ACTIVE          (1 << 10)
+#define OMAP_DMA_CCR_SEL_SRC_DST_SYNC   (1 << 24)
+#define OMAP_DMA_CCR_BUFFERING_DISABLE  (1 << 25)
 
 #define OMAP_DMA_DATA_TYPE_S8           0x00
 #define OMAP_DMA_DATA_TYPE_S16          0x01