Merge branch 'v2.6.36-rc8' into for-2.6.37/barrier

Conflicts:
	block/blk-core.c
	drivers/block/loop.c
	mm/swapfile.c

Signed-off-by: Jens Axboe <jaxboe@fusionio.com>

6 files changed, 119 insertions, 13 deletions

diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 33c3f570aaa0..a0a2928ae4dd 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -398,7 +398,7 @@ config CPU_V6
 # ARMv6k
 config CPU_32v6K
         bool "Support ARM V6K processor extensions" if !SMP
-        depends on CPU_V6
+        depends on CPU_V6 || CPU_V7
         default y if SMP && !(ARCH_MX3 || ARCH_OMAP2)
         help
           Say Y here if your ARMv6 processor supports the 'K' extension.
diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c
index d073b64ae87e..724ba3bce72c 100644
--- a/arch/arm/mm/alignment.c
+++ b/arch/arm/mm/alignment.c
@@ -885,8 +885,23 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 
         if (ai_usermode & UM_SIGNAL)
                 force_sig(SIGBUS, current);
-        else
-                set_cr(cr_no_alignment);
+        else {
+                /*
+                 * We're about to disable the alignment trap and return to
+                 * user space.  But if an interrupt occurs before actually
+                 * reaching user space, then the IRQ vector entry code will
+                 * notice that we were still in kernel space and therefore
+                 * the alignment trap won't be re-enabled in that case as it
+                 * is presumed to be always on from kernel space.
+                 * Let's prevent that race by disabling interrupts here (they
+                 * are disabled on the way back to user space anyway in
+                 * entry-common.S) and disable the alignment trap only if
+                 * there is no work pending for this thread.
+                 */
+                raw_local_irq_disable();
+                if (!(current_thread_info()->flags & _TIF_WORK_MASK))
+                        set_cr(cr_no_alignment);
+        }
 
         return 0;
 }
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index c704eed63c5d..4bc43e535d3b 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -229,6 +229,8 @@ __dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot)
                         }
                 } while (size -= PAGE_SIZE);
 
+                dsb();
+
                 return (void *)c->vm_start;
         }
         return NULL;
diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c
index ab506272b2d3..17e7b0b57e49 100644
--- a/arch/arm/mm/ioremap.c
+++ b/arch/arm/mm/ioremap.c
@@ -204,8 +204,12 @@ void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn,
         /*
          * Don't allow RAM to be mapped - this causes problems with ARMv6+
          */
-        if (WARN_ON(pfn_valid(pfn)))
-                return NULL;
+        if (pfn_valid(pfn)) {
+                printk(KERN_WARNING "BUG: Your driver calls ioremap() on system memory.  This leads\n"
+                       KERN_WARNING "to architecturally unpredictable behaviour on ARMv6+, and ioremap()\n"
+                       KERN_WARNING "will fail in the next kernel release.  Please fix your driver.\n");
+                WARN_ON(1);
+        }
 
         type = get_mem_type(mtype);
         if (!type)
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 6e1c4f6a2b3f..e8ed9dc461fe 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -15,6 +15,7 @@
 #include <linux/nodemask.h>
 #include <linux/memblock.h>
 #include <linux/sort.h>
+#include <linux/fs.h>
 
 #include <asm/cputype.h>
 #include <asm/sections.h>
@@ -246,6 +247,9 @@ static struct mem_type mem_types[] = {
                 .domain    = DOMAIN_USER,
         },
         [MT_MEMORY] = {
+                .prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
+                                L_PTE_WRITE | L_PTE_EXEC,
+                .prot_l1   = PMD_TYPE_TABLE,
                 .prot_sect = PMD_TYPE_SECT | PMD_SECT_AP_WRITE,
                 .domain    = DOMAIN_KERNEL,
         },
@@ -254,6 +258,9 @@ static struct mem_type mem_types[] = {
                 .domain    = DOMAIN_KERNEL,
         },
         [MT_MEMORY_NONCACHED] = {
+                .prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
+                                L_PTE_WRITE | L_PTE_EXEC | L_PTE_MT_BUFFERABLE,
+                .prot_l1   = PMD_TYPE_TABLE,
                 .prot_sect = PMD_TYPE_SECT | PMD_SECT_AP_WRITE,
                 .domain    = DOMAIN_KERNEL,
         },
@@ -411,9 +418,12 @@ static void __init build_mem_type_table(void)
          * Enable CPU-specific coherency if supported.
          * (Only available on XSC3 at the moment.)
          */
-        if (arch_is_coherent() && cpu_is_xsc3())
+        if (arch_is_coherent() && cpu_is_xsc3()) {
                 mem_types[MT_MEMORY].prot_sect |= PMD_SECT_S;
-
+                mem_types[MT_MEMORY].prot_pte |= L_PTE_SHARED;
+                mem_types[MT_MEMORY_NONCACHED].prot_sect |= PMD_SECT_S;
+                mem_types[MT_MEMORY_NONCACHED].prot_pte |= L_PTE_SHARED;
+        }
         /*
          * ARMv6 and above have extended page tables.
          */
@@ -438,7 +448,9 @@ static void __init build_mem_type_table(void)
                 mem_types[MT_DEVICE_CACHED].prot_sect |= PMD_SECT_S;
                 mem_types[MT_DEVICE_CACHED].prot_pte |= L_PTE_SHARED;
                 mem_types[MT_MEMORY].prot_sect |= PMD_SECT_S;
+                mem_types[MT_MEMORY].prot_pte |= L_PTE_SHARED;
                 mem_types[MT_MEMORY_NONCACHED].prot_sect |= PMD_SECT_S;
+                mem_types[MT_MEMORY_NONCACHED].prot_pte |= L_PTE_SHARED;
 #endif
         }
 
@@ -475,6 +487,8 @@ static void __init build_mem_type_table(void)
         mem_types[MT_LOW_VECTORS].prot_l1 |= ecc_mask;
         mem_types[MT_HIGH_VECTORS].prot_l1 |= ecc_mask;
         mem_types[MT_MEMORY].prot_sect |= ecc_mask | cp->pmd;
+        mem_types[MT_MEMORY].prot_pte |= kern_pgprot;
+        mem_types[MT_MEMORY_NONCACHED].prot_sect |= ecc_mask;
         mem_types[MT_ROM].prot_sect |= cp->pmd;
 
         switch (cp->pmd) {
@@ -498,6 +512,19 @@ static void __init build_mem_type_table(void)
         }
 }
 
+#ifdef CONFIG_ARM_DMA_MEM_BUFFERABLE
+pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
+                              unsigned long size, pgprot_t vma_prot)
+{
+        if (!pfn_valid(pfn))
+                return pgprot_noncached(vma_prot);
+        else if (file->f_flags & O_SYNC)
+                return pgprot_writecombine(vma_prot);
+        return vma_prot;
+}
+EXPORT_SYMBOL(phys_mem_access_prot);
+#endif
+
 #define vectors_base()  (vectors_high() ? 0xffff0000 : 0)
 
 static void __init *early_alloc(unsigned long sz)
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 6a8506d99ee9..197f21bed5e9 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -186,13 +186,14 @@ cpu_v7_name:
  *      It is assumed that:
  *      - cache type register is implemented
  */
-__v7_setup:
+__v7_ca9mp_setup:
 #ifdef CONFIG_SMP
         mrc     p15, 0, r0, c1, c0, 1
         tst     r0, #(1 << 6)                   @ SMP/nAMP mode enabled?
         orreq   r0, r0, #(1 << 6) | (1 << 0)    @ Enable SMP/nAMP mode and
         mcreq   p15, 0, r0, c1, c0, 1           @ TLB ops broadcasting
 #endif
+__v7_setup:
         adr     r12, __v7_setup_stack           @ the local stack
         stmia   r12, {r0-r5, r7, r9, r11, lr}
         bl      v7_flush_dcache_all
@@ -201,11 +202,16 @@ __v7_setup:
         mrc     p15, 0, r0, c0, c0, 0           @ read main ID register
         and     r10, r0, #0xff000000            @ ARM?
         teq     r10, #0x41000000
-        bne     2f
+        bne     3f
         and     r5, r0, #0x00f00000             @ variant
         and     r6, r0, #0x0000000f             @ revision
-        orr     r0, r6, r5, lsr #20-4           @ combine variant and revision
+        orr     r6, r6, r5, lsr #20-4           @ combine variant and revision
+        ubfx    r0, r0, #4, #12                 @ primary part number
 
+        /* Cortex-A8 Errata */
+        ldr     r10, =0x00000c08                @ Cortex-A8 primary part number
+        teq     r0, r10
+        bne     2f
 #ifdef CONFIG_ARM_ERRATA_430973
         teq     r5, #0x00100000                 @ only present in r1p*
         mrceq   p15, 0, r10, c1, c0, 1          @ read aux control register
@@ -213,21 +219,50 @@ __v7_setup:
         mcreq   p15, 0, r10, c1, c0, 1          @ write aux control register
 #endif
 #ifdef CONFIG_ARM_ERRATA_458693
-        teq     r0, #0x20                       @ only present in r2p0
+        teq     r6, #0x20                       @ only present in r2p0
         mrceq   p15, 0, r10, c1, c0, 1          @ read aux control register
         orreq   r10, r10, #(1 << 5)             @ set L1NEON to 1
         orreq   r10, r10, #(1 << 9)             @ set PLDNOP to 1
         mcreq   p15, 0, r10, c1, c0, 1          @ write aux control register
 #endif
 #ifdef CONFIG_ARM_ERRATA_460075
-        teq     r0, #0x20                       @ only present in r2p0
+        teq     r6, #0x20                       @ only present in r2p0
         mrceq   p15, 1, r10, c9, c0, 2          @ read L2 cache aux ctrl register
         tsteq   r10, #1 << 22
         orreq   r10, r10, #(1 << 22)            @ set the Write Allocate disable bit
         mcreq   p15, 1, r10, c9, c0, 2          @ write the L2 cache aux ctrl register
 #endif
+        b       3f
 
-2:      mov     r10, #0
+        /* Cortex-A9 Errata */
+2:      ldr     r10, =0x00000c09                @ Cortex-A9 primary part number
+        teq     r0, r10
+        bne     3f
+#ifdef CONFIG_ARM_ERRATA_742230
+        cmp     r6, #0x22                       @ only present up to r2p2
+        mrcle   p15, 0, r10, c15, c0, 1         @ read diagnostic register
+        orrle   r10, r10, #1 << 4               @ set bit #4
+        mcrle   p15, 0, r10, c15, c0, 1         @ write diagnostic register
+#endif
+#ifdef CONFIG_ARM_ERRATA_742231
+        teq     r6, #0x20                       @ present in r2p0
+        teqne   r6, #0x21                       @ present in r2p1
+        teqne   r6, #0x22                       @ present in r2p2
+        mrceq   p15, 0, r10, c15, c0, 1         @ read diagnostic register
+        orreq   r10, r10, #1 << 12              @ set bit #12
+        orreq   r10, r10, #1 << 22              @ set bit #22
+        mcreq   p15, 0, r10, c15, c0, 1         @ write diagnostic register
+#endif
+#ifdef CONFIG_ARM_ERRATA_743622
+        teq     r6, #0x20                       @ present in r2p0
+        teqne   r6, #0x21                       @ present in r2p1
+        teqne   r6, #0x22                       @ present in r2p2
+        mrceq   p15, 0, r10, c15, c0, 1         @ read diagnostic register
+        orreq   r10, r10, #1 << 6               @ set bit #6
+        mcreq   p15, 0, r10, c15, c0, 1         @ write diagnostic register
+#endif
+
+3:      mov     r10, #0
 #ifdef HARVARD_CACHE
         mcr     p15, 0, r10, c7, c5, 0          @ I+BTB cache invalidate
 #endif
@@ -323,6 +358,29 @@ cpu_elf_name:
 
         .section ".proc.info.init", #alloc, #execinstr
 
+        .type   __v7_ca9mp_proc_info, #object
+__v7_ca9mp_proc_info:
+        .long   0x410fc090              @ Required ID value
+        .long   0xff0ffff0              @ Mask for ID
+        .long   PMD_TYPE_SECT | \
+                PMD_SECT_AP_WRITE | \
+                PMD_SECT_AP_READ | \
+                PMD_FLAGS
+        .long   PMD_TYPE_SECT | \
+                PMD_SECT_XN | \
+                PMD_SECT_AP_WRITE | \
+                PMD_SECT_AP_READ
+        b       __v7_ca9mp_setup
+        .long   cpu_arch_name
+        .long   cpu_elf_name
+        .long   HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP|HWCAP_TLS
+        .long   cpu_v7_name
+        .long   v7_processor_functions
+        .long   v7wbi_tlb_fns
+        .long   v6_user_fns
+        .long   v7_cache_fns
+        .size   __v7_ca9mp_proc_info, . - __v7_ca9mp_proc_info
+
         /*
          * Match any ARMv7 processor core.
          */