Merge tag 'v3.13-rc6' into for-3.14/core

Needed to bring blk-mq uptodate, since changes have been going in
since for-3.14/core was established.

Fixup merge issues related to the immutable biovec changes.

Signed-off-by: Jens Axboe <axboe@kernel.dk>

Conflicts:
	block/blk-flush.c
	fs/btrfs/check-integrity.c
	fs/btrfs/extent_io.c
	fs/btrfs/scrub.c
	fs/logfs/dev_bdev.c

14 files changed, 91 insertions, 96 deletions

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 88c8b6c1341a..6d4dd22ee4b7 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -159,8 +159,7 @@ config NR_CPUS
         range 2 32
         depends on SMP
         # These have to remain sorted largest to smallest
-        default "8" if ARCH_XGENE
-        default "4"
+        default "8"
 
 config HOTPLUG_CPU
         bool "Support for hot-pluggable CPUs"
diff --git a/arch/arm64/boot/dts/foundation-v8.dts b/arch/arm64/boot/dts/foundation-v8.dts
index 84fcc5018284..519c4b2c0687 100644
--- a/arch/arm64/boot/dts/foundation-v8.dts
+++ b/arch/arm64/boot/dts/foundation-v8.dts
@@ -6,6 +6,8 @@
 
 /dts-v1/;
 
+/memreserve/ 0x80000000 0x00010000;
+
 / {
         model = "Foundation-v8A";
         compatible = "arm,foundation-aarch64", "arm,vexpress";
diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h
index 4cc813eddacb..572769727227 100644
--- a/arch/arm64/include/asm/io.h
+++ b/arch/arm64/include/asm/io.h
@@ -229,7 +229,7 @@ extern void __iomem *__ioremap(phys_addr_t phys_addr, size_t size, pgprot_t prot
 extern void __iounmap(volatile void __iomem *addr);
 extern void __iomem *ioremap_cache(phys_addr_t phys_addr, size_t size);
 
-#define PROT_DEFAULT            (PTE_TYPE_PAGE | PTE_AF | PTE_DIRTY)
+#define PROT_DEFAULT            (pgprot_default | PTE_DIRTY)
 #define PROT_DEVICE_nGnRE       (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_DEVICE_nGnRE))
 #define PROT_NORMAL_NC          (PROT_DEFAULT | PTE_ATTRINDX(MT_NORMAL_NC))
 #define PROT_NORMAL             (PROT_DEFAULT | PTE_ATTRINDX(MT_NORMAL))
diff --git a/arch/arm64/include/asm/irqflags.h b/arch/arm64/include/asm/irqflags.h
index aa11943b8502..b2fcfbc51ecc 100644
--- a/arch/arm64/include/asm/irqflags.h
+++ b/arch/arm64/include/asm/irqflags.h
@@ -56,6 +56,9 @@ static inline void arch_local_irq_disable(void)
 #define local_fiq_enable()      asm("msr        daifclr, #1" : : : "memory")
 #define local_fiq_disable()     asm("msr        daifset, #1" : : : "memory")
 
+#define local_async_enable()    asm("msr        daifclr, #4" : : : "memory")
+#define local_async_disable()   asm("msr        daifset, #4" : : : "memory")
+
 /*
  * Save the current interrupt enable state.
  */
diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
index 755f86143320..b1d2e26c3c88 100644
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -43,7 +43,7 @@
  * Section
  */
 #define PMD_SECT_VALID          (_AT(pmdval_t, 1) << 0)
-#define PMD_SECT_PROT_NONE      (_AT(pmdval_t, 1) << 2)
+#define PMD_SECT_PROT_NONE      (_AT(pmdval_t, 1) << 58)
 #define PMD_SECT_USER           (_AT(pmdval_t, 1) << 6)         /* AP[1] */
 #define PMD_SECT_RDONLY         (_AT(pmdval_t, 1) << 7)         /* AP[2] */
 #define PMD_SECT_S              (_AT(pmdval_t, 3) << 8)
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 17bd3af0a117..7f2b60affbb4 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -25,10 +25,11 @@
  * Software defined PTE bits definition.
  */
 #define PTE_VALID               (_AT(pteval_t, 1) << 0)
-#define PTE_PROT_NONE           (_AT(pteval_t, 1) << 2) /* only when !PTE_VALID */
-#define PTE_FILE                (_AT(pteval_t, 1) << 3) /* only when !pte_present() */
+#define PTE_FILE                (_AT(pteval_t, 1) << 2) /* only when !pte_present() */
 #define PTE_DIRTY               (_AT(pteval_t, 1) << 55)
 #define PTE_SPECIAL             (_AT(pteval_t, 1) << 56)
+                                /* bit 57 for PMD_SECT_SPLITTING */
+#define PTE_PROT_NONE           (_AT(pteval_t, 1) << 58) /* only when !PTE_VALID */
 
 /*
  * VMALLOC and SPARSEMEM_VMEMMAP ranges.
@@ -254,7 +255,7 @@ static inline int has_transparent_hugepage(void)
 #define pgprot_noncached(prot) \
         __pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_DEVICE_nGnRnE))
 #define pgprot_writecombine(prot) \
-        __pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_DEVICE_GRE))
+        __pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_NORMAL_NC))
 #define pgprot_dmacoherent(prot) \
         __pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_NORMAL_NC))
 #define __HAVE_PHYS_MEM_ACCESS_PROT
@@ -357,18 +358,20 @@ extern pgd_t idmap_pg_dir[PTRS_PER_PGD];
 
 /*
  * Encode and decode a swap entry:
- *      bits 0, 2:      present (must both be zero)
- *      bit  3:         PTE_FILE
- *      bits 4-8:       swap type
- *      bits 9-63:      swap offset
+ *      bits 0-1:       present (must be zero)
+ *      bit  2:         PTE_FILE
+ *      bits 3-8:       swap type
+ *      bits 9-57:      swap offset
  */
-#define __SWP_TYPE_SHIFT        4
+#define __SWP_TYPE_SHIFT        3
 #define __SWP_TYPE_BITS         6
+#define __SWP_OFFSET_BITS       49
 #define __SWP_TYPE_MASK         ((1 << __SWP_TYPE_BITS) - 1)
 #define __SWP_OFFSET_SHIFT      (__SWP_TYPE_BITS + __SWP_TYPE_SHIFT)
+#define __SWP_OFFSET_MASK       ((1UL << __SWP_OFFSET_BITS) - 1)
 
 #define __swp_type(x)           (((x).val >> __SWP_TYPE_SHIFT) & __SWP_TYPE_MASK)
-#define __swp_offset(x)         ((x).val >> __SWP_OFFSET_SHIFT)
+#define __swp_offset(x)         (((x).val >> __SWP_OFFSET_SHIFT) & __SWP_OFFSET_MASK)
 #define __swp_entry(type,offset) ((swp_entry_t) { ((type) << __SWP_TYPE_SHIFT) | ((offset) << __SWP_OFFSET_SHIFT) })
 
 #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) })
@@ -382,15 +385,15 @@ extern pgd_t idmap_pg_dir[PTRS_PER_PGD];
 
 /*
  * Encode and decode a file entry:
- *      bits 0, 2:      present (must both be zero)
- *      bit  3:         PTE_FILE
- *      bits 4-63:      file offset / PAGE_SIZE
+ *      bits 0-1:       present (must be zero)
+ *      bit  2:         PTE_FILE
+ *      bits 3-57:      file offset / PAGE_SIZE
  */
 #define pte_file(pte)           (pte_val(pte) & PTE_FILE)
-#define pte_to_pgoff(x)         (pte_val(x) >> 4)
-#define pgoff_to_pte(x)         __pte(((x) << 4) | PTE_FILE)
+#define pte_to_pgoff(x)         (pte_val(x) >> 3)
+#define pgoff_to_pte(x)         __pte(((x) << 3) | PTE_FILE)
 
-#define PTE_FILE_MAX_BITS       60
+#define PTE_FILE_MAX_BITS       55
 
 extern int kern_addr_valid(unsigned long addr);
 
diff --git a/arch/arm64/include/asm/xen/page-coherent.h b/arch/arm64/include/asm/xen/page-coherent.h
index 2820f1a6eebe..dde3fc9c49f0 100644
--- a/arch/arm64/include/asm/xen/page-coherent.h
+++ b/arch/arm64/include/asm/xen/page-coherent.h
@@ -23,25 +23,21 @@ static inline void xen_dma_map_page(struct device *hwdev, struct page *page,
              unsigned long offset, size_t size, enum dma_data_direction dir,
              struct dma_attrs *attrs)
 {
-        __generic_dma_ops(hwdev)->map_page(hwdev, page, offset, size, dir, attrs);
 }
 
 static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
                 size_t size, enum dma_data_direction dir,
                 struct dma_attrs *attrs)
 {
-        __generic_dma_ops(hwdev)->unmap_page(hwdev, handle, size, dir, attrs);
 }
 
 static inline void xen_dma_sync_single_for_cpu(struct device *hwdev,
                 dma_addr_t handle, size_t size, enum dma_data_direction dir)
 {
-        __generic_dma_ops(hwdev)->sync_single_for_cpu(hwdev, handle, size, dir);
 }
 
 static inline void xen_dma_sync_single_for_device(struct device *hwdev,
                 dma_addr_t handle, size_t size, enum dma_data_direction dir)
 {
-        __generic_dma_ops(hwdev)->sync_single_for_device(hwdev, handle, size, dir);
 }
 #endif /* _ASM_ARM64_XEN_PAGE_COHERENT_H */
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index 6a0a9b132d7a..4ae68579031d 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -248,7 +248,8 @@ static int brk_handler(unsigned long addr, unsigned int esr,
 int aarch32_break_handler(struct pt_regs *regs)
 {
         siginfo_t info;
-        unsigned int instr;
+        u32 arm_instr;
+        u16 thumb_instr;
         bool bp = false;
         void __user *pc = (void __user *)instruction_pointer(regs);
 
@@ -257,18 +258,21 @@ int aarch32_break_handler(struct pt_regs *regs)
 
         if (compat_thumb_mode(regs)) {
                 /* get 16-bit Thumb instruction */
-                get_user(instr, (u16 __user *)pc);
-                if (instr == AARCH32_BREAK_THUMB2_LO) {
+                get_user(thumb_instr, (u16 __user *)pc);
+                thumb_instr = le16_to_cpu(thumb_instr);
+                if (thumb_instr == AARCH32_BREAK_THUMB2_LO) {
                         /* get second half of 32-bit Thumb-2 instruction */
-                        get_user(instr, (u16 __user *)(pc + 2));
-                        bp = instr == AARCH32_BREAK_THUMB2_HI;
+                        get_user(thumb_instr, (u16 __user *)(pc + 2));
+                        thumb_instr = le16_to_cpu(thumb_instr);
+                        bp = thumb_instr == AARCH32_BREAK_THUMB2_HI;
                 } else {
-                        bp = instr == AARCH32_BREAK_THUMB;
+                        bp = thumb_instr == AARCH32_BREAK_THUMB;
                 }
         } else {
                 /* 32-bit ARM instruction */
-                get_user(instr, (u32 __user *)pc);
-                bp = (instr & ~0xf0000000) == AARCH32_BREAK_ARM;
+                get_user(arm_instr, (u32 __user *)pc);
+                arm_instr = le32_to_cpu(arm_instr);
+                bp = (arm_instr & ~0xf0000000) == AARCH32_BREAK_ARM;
         }
 
         if (!bp)
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index e1166145ca29..4d2c6f3f0c41 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -309,15 +309,12 @@ el1_irq:
 #ifdef CONFIG_TRACE_IRQFLAGS
         bl      trace_hardirqs_off
 #endif
-#ifdef CONFIG_PREEMPT
-        get_thread_info tsk
-        ldr     w24, [tsk, #TI_PREEMPT]         // get preempt count
-        add     w0, w24, #1                     // increment it
-        str     w0, [tsk, #TI_PREEMPT]
-#endif
+
         irq_handler
+
 #ifdef CONFIG_PREEMPT
-        str     w24, [tsk, #TI_PREEMPT]         // restore preempt count
+        get_thread_info tsk
+        ldr     w24, [tsk, #TI_PREEMPT]         // restore preempt count
         cbnz    w24, 1f                         // preempt count != 0
         ldr     x0, [tsk, #TI_FLAGS]            // get flags
         tbz     x0, #TIF_NEED_RESCHED, 1f       // needs rescheduling?
@@ -507,22 +504,10 @@ el0_irq_naked:
 #ifdef CONFIG_TRACE_IRQFLAGS
         bl      trace_hardirqs_off
 #endif
-        get_thread_info tsk
-#ifdef CONFIG_PREEMPT
-        ldr     w24, [tsk, #TI_PREEMPT]         // get preempt count
-        add     w23, w24, #1                    // increment it
-        str     w23, [tsk, #TI_PREEMPT]
-#endif
+
         irq_handler
-#ifdef CONFIG_PREEMPT
-        ldr     w0, [tsk, #TI_PREEMPT]
-        str     w24, [tsk, #TI_PREEMPT]
-        cmp     w0, w23
-        b.eq    1f
-        mov     x1, #0
-        str     x1, [x1]                        // BUG
-1:
-#endif
+        get_thread_info tsk
+
 #ifdef CONFIG_TRACE_IRQFLAGS
         bl      trace_hardirqs_on
 #endif
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 7009387348b7..c68cca5c3523 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -282,8 +282,9 @@ ENDPROC(secondary_holding_pen)
          * be used where CPUs are brought online dynamically by the kernel.
          */
 ENTRY(secondary_entry)
-        bl      __calc_phys_offset              // x2=phys offset
         bl      el2_setup                       // Drop to EL1
+        bl      __calc_phys_offset              // x24=PHYS_OFFSET, x28=PHYS_OFFSET-PAGE_OFFSET
+        bl      set_cpu_boot_mode_flag
         b       secondary_startup
 ENDPROC(secondary_entry)
 
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index fecdbf7de82e..6a8928bba03c 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -214,31 +214,29 @@ static int ptrace_hbp_fill_attr_ctrl(unsigned int note_type,
 {
         int err, len, type, disabled = !ctrl.enabled;
 
-        if (disabled) {
-                len = 0;
-                type = HW_BREAKPOINT_EMPTY;
-        } else {
-                err = arch_bp_generic_fields(ctrl, &len, &type);
-                if (err)
-                        return err;
-
-                switch (note_type) {
-                case NT_ARM_HW_BREAK:
-                        if ((type & HW_BREAKPOINT_X) != type)
-                                return -EINVAL;
-                        break;
-                case NT_ARM_HW_WATCH:
-                        if ((type & HW_BREAKPOINT_RW) != type)
-                                return -EINVAL;
-                        break;
-                default:
+        attr->disabled = disabled;
+        if (disabled)
+                return 0;
+
+        err = arch_bp_generic_fields(ctrl, &len, &type);
+        if (err)
+                return err;
+
+        switch (note_type) {
+        case NT_ARM_HW_BREAK:
+                if ((type & HW_BREAKPOINT_X) != type)
                         return -EINVAL;
-                }
+                break;
+        case NT_ARM_HW_WATCH:
+                if ((type & HW_BREAKPOINT_RW) != type)
+                        return -EINVAL;
+                break;
+        default:
+                return -EINVAL;
         }
 
         attr->bp_len    = len;
         attr->bp_type   = type;
-        attr->disabled  = disabled;
 
         return 0;
 }
@@ -636,28 +634,27 @@ static int compat_gpr_get(struct task_struct *target,
 
         for (i = 0; i < num_regs; ++i) {
                 unsigned int idx = start + i;
-                void *reg;
+                compat_ulong_t reg;
 
                 switch (idx) {
                 case 15:
-                        reg = (void *)&task_pt_regs(target)->pc;
+                        reg = task_pt_regs(target)->pc;
                         break;
                 case 16:
-                        reg = (void *)&task_pt_regs(target)->pstate;
+                        reg = task_pt_regs(target)->pstate;
                         break;
                 case 17:
-                        reg = (void *)&task_pt_regs(target)->orig_x0;
+                        reg = task_pt_regs(target)->orig_x0;
                         break;
                 default:
-                        reg = (void *)&task_pt_regs(target)->regs[idx];
+                        reg = task_pt_regs(target)->regs[idx];
                 }
 
-                ret = copy_to_user(ubuf, reg, sizeof(compat_ulong_t));
-
+                ret = copy_to_user(ubuf, &reg, sizeof(reg));
                 if (ret)
                         break;
-                else
-                        ubuf += sizeof(compat_ulong_t);
+
+                ubuf += sizeof(reg);
         }
 
         return ret;
@@ -685,28 +682,28 @@ static int compat_gpr_set(struct task_struct *target,
 
         for (i = 0; i < num_regs; ++i) {
                 unsigned int idx = start + i;
-                void *reg;
+                compat_ulong_t reg;
+
+                ret = copy_from_user(&reg, ubuf, sizeof(reg));
+                if (ret)
+                        return ret;
+
+                ubuf += sizeof(reg);
 
                 switch (idx) {
                 case 15:
-                        reg = (void *)&newregs.pc;
+                        newregs.pc = reg;
                         break;
                 case 16:
-                        reg = (void *)&newregs.pstate;
+                        newregs.pstate = reg;
                         break;
                 case 17:
-                        reg = (void *)&newregs.orig_x0;
+                        newregs.orig_x0 = reg;
                         break;
                 default:
-                        reg = (void *)&newregs.regs[idx];
+                        newregs.regs[idx] = reg;
                 }
 
-                ret = copy_from_user(reg, ubuf, sizeof(compat_ulong_t));
-
-                if (ret)
-                        goto out;
-                else
-                        ubuf += sizeof(compat_ulong_t);
         }
 
         if (valid_user_regs(&newregs.user_regs))
@@ -714,7 +711,6 @@ static int compat_gpr_set(struct task_struct *target,
         else
                 ret = -EINVAL;
 
-out:
         return ret;
 }
 
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 0bc5e4cbc017..bd9bbd0e44ed 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -205,6 +205,11 @@ u64 __cpu_logical_map[NR_CPUS] = { [0 ... NR_CPUS-1] = INVALID_HWID };
 
 void __init setup_arch(char **cmdline_p)
 {
+        /*
+         * Unmask asynchronous aborts early to catch possible system errors.
+         */
+        local_async_enable();
+
         setup_processor();
 
         setup_machine_fdt(__fdt_pointer);
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index a5aeefab03c3..a0c2ca602cf8 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -160,6 +160,7 @@ asmlinkage void secondary_start_kernel(void)
 
         local_irq_enable();
         local_fiq_enable();
+        local_async_enable();
 
         /*
          * OK, it's off to the idle thread for us
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index 421b99fd635d..0f7fec52c7f8 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -111,12 +111,12 @@ ENTRY(__cpu_setup)
         bl      __flush_dcache_all
         mov     lr, x28
         ic      iallu                           // I+BTB cache invalidate
+        tlbi    vmalle1is                       // invalidate I + D TLBs
         dsb     sy
 
         mov     x0, #3 << 20
         msr     cpacr_el1, x0                   // Enable FP/ASIMD
         msr     mdscr_el1, xzr                  // Reset mdscr_el1
-        tlbi    vmalle1is                       // invalidate I + D TLBs
         /*
          * Memory region attributes for LPAE:
          *