7 files changed, 46 insertions, 17 deletions

diff --git a/include/asm-x86/amd_iommu_types.h b/include/asm-x86/amd_iommu_types.h
index 22aa58ca1991..dcc812067394 100644
--- a/include/asm-x86/amd_iommu_types.h
+++ b/include/asm-x86/amd_iommu_types.h
@@ -31,9 +31,6 @@
 #define ALIAS_TABLE_ENTRY_SIZE          2
 #define RLOOKUP_TABLE_ENTRY_SIZE        (sizeof(void *))
 
-/* helper macros */
-#define LOW_U32(x) ((x) & ((1ULL << 32)-1))
-
 /* Length of the MMIO region for the AMD IOMMU */
 #define MMIO_REGION_LENGTH       0x4000
 
@@ -69,6 +66,9 @@
 #define MMIO_EVT_TAIL_OFFSET    0x2018
 #define MMIO_STATUS_OFFSET      0x2020
 
+/* MMIO status bits */
+#define MMIO_STATUS_COM_WAIT_INT_MASK   0x04
+
 /* feature control bits */
 #define CONTROL_IOMMU_EN        0x00ULL
 #define CONTROL_HT_TUN_EN       0x01ULL
@@ -89,6 +89,7 @@
 #define CMD_INV_IOMMU_PAGES     0x03
 
 #define CMD_COMPL_WAIT_STORE_MASK       0x01
+#define CMD_COMPL_WAIT_INT_MASK         0x02
 #define CMD_INV_IOMMU_PAGES_SIZE_MASK   0x01
 #define CMD_INV_IOMMU_PAGES_PDE_MASK    0x02
 
@@ -99,6 +100,7 @@
 #define DEV_ENTRY_TRANSLATION   0x01
 #define DEV_ENTRY_IR            0x3d
 #define DEV_ENTRY_IW            0x3e
+#define DEV_ENTRY_NO_PAGE_FAULT 0x62
 #define DEV_ENTRY_EX            0x67
 #define DEV_ENTRY_SYSMGT1       0x68
 #define DEV_ENTRY_SYSMGT2       0x69
diff --git a/include/asm-x86/i387.h b/include/asm-x86/i387.h
index 6d3b21063419..56d00e31aec0 100644
--- a/include/asm-x86/i387.h
+++ b/include/asm-x86/i387.h
@@ -63,8 +63,6 @@ static inline int restore_fpu_checking(struct i387_fxsave_struct *fx)
 #else
                      : [fx] "cdaSDb" (fx), "m" (*fx), "0" (0));
 #endif
-        if (unlikely(err))
-                init_fpu(current);
         return err;
 }
 
diff --git a/include/asm-x86/io.h b/include/asm-x86/io.h
index bf5d629b3a39..0f954dc89cb3 100644
--- a/include/asm-x86/io.h
+++ b/include/asm-x86/io.h
@@ -21,7 +21,7 @@ extern void __iomem *fix_ioremap(unsigned idx, unsigned long phys);
 
 #define build_mmio_read(name, size, type, reg, barrier) \
 static inline type name(const volatile void __iomem *addr) \
-{ type ret; asm volatile("mov" size " %1,%0":"=" reg (ret) \
+{ type ret; asm volatile("mov" size " %1,%0":reg (ret) \
 :"m" (*(volatile type __force *)addr) barrier); return ret; }
 
 #define build_mmio_write(name, size, type, reg, barrier) \
@@ -29,13 +29,13 @@ static inline void name(type val, volatile void __iomem *addr) \
 { asm volatile("mov" size " %0,%1": :reg (val), \
 "m" (*(volatile type __force *)addr) barrier); }
 
-build_mmio_read(readb, "b", unsigned char, "q", :"memory")
-build_mmio_read(readw, "w", unsigned short, "r", :"memory")
-build_mmio_read(readl, "l", unsigned int, "r", :"memory")
+build_mmio_read(readb, "b", unsigned char, "=q", :"memory")
+build_mmio_read(readw, "w", unsigned short, "=r", :"memory")
+build_mmio_read(readl, "l", unsigned int, "=r", :"memory")
 
-build_mmio_read(__readb, "b", unsigned char, "q", )
-build_mmio_read(__readw, "w", unsigned short, "r", )
-build_mmio_read(__readl, "l", unsigned int, "r", )
+build_mmio_read(__readb, "b", unsigned char, "=q", )
+build_mmio_read(__readw, "w", unsigned short, "=r", )
+build_mmio_read(__readl, "l", unsigned int, "=r", )
 
 build_mmio_write(writeb, "b", unsigned char, "q", :"memory")
 build_mmio_write(writew, "w", unsigned short, "r", :"memory")
@@ -59,8 +59,8 @@ build_mmio_write(__writel, "l", unsigned int, "r", )
 #define mmiowb() barrier()
 
 #ifdef CONFIG_X86_64
-build_mmio_read(readq, "q", unsigned long, "r", :"memory")
-build_mmio_read(__readq, "q", unsigned long, "r", )
+build_mmio_read(readq, "q", unsigned long, "=r", :"memory")
+build_mmio_read(__readq, "q", unsigned long, "=r", )
 build_mmio_write(writeq, "q", unsigned long, "r", :"memory")
 build_mmio_write(__writeq, "q", unsigned long, "r", )
 
diff --git a/include/asm-x86/mmzone_32.h b/include/asm-x86/mmzone_32.h
index b2298a227567..5862e6460658 100644
--- a/include/asm-x86/mmzone_32.h
+++ b/include/asm-x86/mmzone_32.h
@@ -97,10 +97,16 @@ static inline int pfn_valid(int pfn)
         reserve_bootmem_node(NODE_DATA(0), (addr), (size), (flags))
 #define alloc_bootmem(x) \
         __alloc_bootmem_node(NODE_DATA(0), (x), SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS))
+#define alloc_bootmem_nopanic(x) \
+        __alloc_bootmem_node_nopanic(NODE_DATA(0), (x), SMP_CACHE_BYTES, \
+                                __pa(MAX_DMA_ADDRESS))
 #define alloc_bootmem_low(x) \
         __alloc_bootmem_node(NODE_DATA(0), (x), SMP_CACHE_BYTES, 0)
 #define alloc_bootmem_pages(x) \
         __alloc_bootmem_node(NODE_DATA(0), (x), PAGE_SIZE, __pa(MAX_DMA_ADDRESS))
+#define alloc_bootmem_pages_nopanic(x) \
+        __alloc_bootmem_node_nopanic(NODE_DATA(0), (x), PAGE_SIZE, \
+                                __pa(MAX_DMA_ADDRESS))
 #define alloc_bootmem_low_pages(x) \
         __alloc_bootmem_node(NODE_DATA(0), (x), PAGE_SIZE, 0)
 #define alloc_bootmem_node(pgdat, x)                                    \
diff --git a/include/asm-x86/pgtable_64.h b/include/asm-x86/pgtable_64.h
index ac5fff4cc58a..549144d03d99 100644
--- a/include/asm-x86/pgtable_64.h
+++ b/include/asm-x86/pgtable_64.h
@@ -151,7 +151,7 @@ static inline void native_pgd_clear(pgd_t *pgd)
 #define VMALLOC_END      _AC(0xffffe1ffffffffff, UL)
 #define VMEMMAP_START    _AC(0xffffe20000000000, UL)
 #define MODULES_VADDR    _AC(0xffffffffa0000000, UL)
-#define MODULES_END      _AC(0xfffffffffff00000, UL)
+#define MODULES_END      _AC(0xffffffffff000000, UL)
 #define MODULES_LEN   (MODULES_END - MODULES_VADDR)
 
 #ifndef __ASSEMBLY__
diff --git a/include/asm-x86/processor.h b/include/asm-x86/processor.h
index 5f58da401b43..4df3e2f6fb56 100644
--- a/include/asm-x86/processor.h
+++ b/include/asm-x86/processor.h
@@ -728,6 +728,29 @@ extern unsigned long		boot_option_idle_override;
 extern unsigned long            idle_halt;
 extern unsigned long            idle_nomwait;
 
+/*
+ * on systems with caches, caches must be flashed as the absolute
+ * last instruction before going into a suspended halt.  Otherwise,
+ * dirty data can linger in the cache and become stale on resume,
+ * leading to strange errors.
+ *
+ * perform a variety of operations to guarantee that the compiler
+ * will not reorder instructions.  wbinvd itself is serializing
+ * so the processor will not reorder.
+ *
+ * Systems without cache can just go into halt.
+ */
+static inline void wbinvd_halt(void)
+{
+        mb();
+        /* check for clflush to determine if wbinvd is legal */
+        if (cpu_has_clflush)
+                asm volatile("cli; wbinvd; 1: hlt; jmp 1b" : : : "memory");
+        else
+                while (1)
+                        halt();
+}
+
 extern void enable_sep_cpu(void);
 extern int sysenter_setup(void);
 
diff --git a/include/asm-x86/spinlock.h b/include/asm-x86/spinlock.h
index 4f9a9861799a..e39c790dbfd2 100644
--- a/include/asm-x86/spinlock.h
+++ b/include/asm-x86/spinlock.h
@@ -65,7 +65,7 @@ static inline int __ticket_spin_is_contended(raw_spinlock_t *lock)
 {
         int tmp = ACCESS_ONCE(lock->slock);
 
-        return (((tmp >> 8) & 0xff) - (tmp & 0xff)) > 1;
+        return (((tmp >> 8) - tmp) & 0xff) > 1;
 }
 
 static __always_inline void __ticket_spin_lock(raw_spinlock_t *lock)
@@ -127,7 +127,7 @@ static inline int __ticket_spin_is_contended(raw_spinlock_t *lock)
 {
         int tmp = ACCESS_ONCE(lock->slock);
 
-        return (((tmp >> 16) & 0xffff) - (tmp & 0xffff)) > 1;
+        return (((tmp >> 16) - tmp) & 0xffff) > 1;
 }
 
 static __always_inline void __ticket_spin_lock(raw_spinlock_t *lock)