Merge branch 'linus' into x86/cleanups

15 files changed, 112 insertions, 29 deletions

diff --git a/include/asm-x86/amd_iommu_types.h b/include/asm-x86/amd_iommu_types.h
index 22aa58ca199..dcc81206739 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/atomic_64.h b/include/asm-x86/atomic_64.h
index a0095191c02..91c7d03e65b 100644
--- a/include/asm-x86/atomic_64.h
+++ b/include/asm-x86/atomic_64.h
@@ -228,7 +228,7 @@ static inline void atomic64_add(long i, atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "addq %1,%0"
 		     : "=m" (v->counter)
-		     : "ir" (i), "m" (v->counter));
+		     : "er" (i), "m" (v->counter));
 }
 
 /**
@@ -242,7 +242,7 @@ static inline void atomic64_sub(long i, atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "subq %1,%0"
 		     : "=m" (v->counter)
-		     : "ir" (i), "m" (v->counter));
+		     : "er" (i), "m" (v->counter));
 }
 
 /**
@@ -260,7 +260,7 @@ static inline int atomic64_sub_and_test(long i, atomic64_t *v)
 
 	asm volatile(LOCK_PREFIX "subq %2,%0; sete %1"
 		     : "=m" (v->counter), "=qm" (c)
-		     : "ir" (i), "m" (v->counter) : "memory");
+		     : "er" (i), "m" (v->counter) : "memory");
 	return c;
 }
 
@@ -341,7 +341,7 @@ static inline int atomic64_add_negative(long i, atomic64_t *v)
 
 	asm volatile(LOCK_PREFIX "addq %2,%0; sets %1"
 		     : "=m" (v->counter), "=qm" (c)
-		     : "ir" (i), "m" (v->counter) : "memory");
+		     : "er" (i), "m" (v->counter) : "memory");
 	return c;
 }
 
diff --git a/include/asm-x86/efi.h b/include/asm-x86/efi.h
index 7ed2bd7a7f5..d4f2b0abe92 100644
--- a/include/asm-x86/efi.h
+++ b/include/asm-x86/efi.h
@@ -86,7 +86,7 @@ extern u64 efi_call6(void *fp, u64 arg1, u64 arg2, u64 arg3,
 	efi_call6((void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \
 		  (u64)(a3), (u64)(a4), (u64)(a5), (u64)(a6))
 
-extern void *efi_ioremap(unsigned long addr, unsigned long size);
+extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size);
 
 #endif /* CONFIG_X86_32 */
 
diff --git a/include/asm-x86/geode.h b/include/asm-x86/geode.h
index bb06027fc83..2c1cda0b8a8 100644
--- a/include/asm-x86/geode.h
+++ b/include/asm-x86/geode.h
@@ -50,6 +50,7 @@ extern int geode_get_dev_base(unsigned int dev);
 #define MSR_PIC_YSEL_HIGH	0x51400021
 #define MSR_PIC_ZSEL_LOW	0x51400022
 #define MSR_PIC_ZSEL_HIGH	0x51400023
+#define MSR_PIC_IRQM_LPC	0x51400025
 
 #define MSR_MFGPT_IRQ		0x51400028
 #define MSR_MFGPT_NR		0x51400029
@@ -237,7 +238,7 @@ static inline u16 geode_mfgpt_read(int timer, u16 reg)
 }
 
 extern int geode_mfgpt_toggle_event(int timer, int cmp, int event, int enable);
-extern int geode_mfgpt_set_irq(int timer, int cmp, int irq, int enable);
+extern int geode_mfgpt_set_irq(int timer, int cmp, int *irq, int enable);
 extern int geode_mfgpt_alloc_timer(int timer, int domain);
 
 #define geode_mfgpt_setup_irq(t, c, i) geode_mfgpt_set_irq((t), (c), (i), 1)
diff --git a/include/asm-x86/hw_irq.h b/include/asm-x86/hw_irq.h
index 77ba51df566..edd0b95f14d 100644
--- a/include/asm-x86/hw_irq.h
+++ b/include/asm-x86/hw_irq.h
@@ -98,9 +98,17 @@ extern void (*const interrupt[NR_IRQS])(void);
 #else
 typedef int vector_irq_t[NR_VECTORS];
 DECLARE_PER_CPU(vector_irq_t, vector_irq);
-extern spinlock_t vector_lock;
 #endif
-extern void setup_vector_irq(int cpu);
+
+#if defined(CONFIG_X86_IO_APIC) && defined(CONFIG_X86_64)
+extern void lock_vector_lock(void);
+extern void unlock_vector_lock(void);
+extern void __setup_vector_irq(int cpu);
+#else
+static inline void lock_vector_lock(void) {}
+static inline void unlock_vector_lock(void) {}
+static inline void __setup_vector_irq(int cpu) {}
+#endif
 
 #endif /* !ASSEMBLY_ */
 
diff --git a/include/asm-x86/i387.h b/include/asm-x86/i387.h
index 96fa8449ff1..56d00e31aec 100644
--- a/include/asm-x86/i387.h
+++ b/include/asm-x86/i387.h
@@ -13,6 +13,7 @@
 #include <linux/sched.h>
 #include <linux/kernel_stat.h>
 #include <linux/regset.h>
+#include <linux/hardirq.h>
 #include <asm/asm.h>
 #include <asm/processor.h>
 #include <asm/sigcontext.h>
@@ -62,8 +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;
 }
 
@@ -236,6 +235,37 @@ static inline void kernel_fpu_end(void)
 	preempt_enable();
 }
 
+/*
+ * Some instructions like VIA's padlock instructions generate a spurious
+ * DNA fault but don't modify SSE registers. And these instructions
+ * get used from interrupt context aswell. To prevent these kernel instructions
+ * in interrupt context interact wrongly with other user/kernel fpu usage, we
+ * should use them only in the context of irq_ts_save/restore()
+ */
+static inline int irq_ts_save(void)
+{
+	/*
+	 * If we are in process context, we are ok to take a spurious DNA fault.
+	 * Otherwise, doing clts() in process context require pre-emption to
+	 * be disabled or some heavy lifting like kernel_fpu_begin()
+	 */
+	if (!in_interrupt())
+		return 0;
+
+	if (read_cr0() & X86_CR0_TS) {
+		clts();
+		return 1;
+	}
+
+	return 0;
+}
+
+static inline void irq_ts_restore(int TS_state)
+{
+	if (TS_state)
+		stts();
+}
+
 #ifdef CONFIG_X86_64
 
 static inline void save_init_fpu(struct task_struct *tsk)
diff --git a/include/asm-x86/io.h b/include/asm-x86/io.h
index bf5d629b3a3..0f954dc89cb 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/irq_vectors.h b/include/asm-x86/irq_vectors.h
index 90b1d1f12f0..b95d167b7fb 100644
--- a/include/asm-x86/irq_vectors.h
+++ b/include/asm-x86/irq_vectors.h
@@ -109,7 +109,15 @@
 #define LAST_VM86_IRQ		15
 #define invalid_vm86_irq(irq)	((irq) < 3 || (irq) > 15)
 
-#if !defined(CONFIG_X86_VOYAGER)
+#ifdef CONFIG_X86_64
+# if NR_CPUS < MAX_IO_APICS
+#  define NR_IRQS (NR_VECTORS + (32 * NR_CPUS))
+# else
+#  define NR_IRQS (NR_VECTORS + (32 * MAX_IO_APICS))
+# endif
+# define NR_IRQ_VECTORS NR_IRQS
+
+#elif !defined(CONFIG_X86_VOYAGER)
 
 # if defined(CONFIG_X86_IO_APIC) || defined(CONFIG_PARAVIRT) || defined(CONFIG_X86_VISWS)
 
diff --git a/include/asm-x86/kexec.h b/include/asm-x86/kexec.h
index c0e52a14fd4..4246ab7dc98 100644
--- a/include/asm-x86/kexec.h
+++ b/include/asm-x86/kexec.h
@@ -41,6 +41,10 @@
 # define PAGES_NR		17
 #endif
 
+#ifdef CONFIG_X86_32
+# define KEXEC_CONTROL_CODE_MAX_SIZE	2048
+#endif
+
 #ifndef __ASSEMBLY__
 
 #include <linux/string.h>
@@ -63,7 +67,7 @@
 /* Maximum address we can use for the control code buffer */
 # define KEXEC_CONTROL_MEMORY_LIMIT TASK_SIZE
 
-# define KEXEC_CONTROL_CODE_SIZE	4096
+# define KEXEC_CONTROL_PAGE_SIZE	4096
 
 /* The native architecture */
 # define KEXEC_ARCH KEXEC_ARCH_386
@@ -79,7 +83,7 @@
 # define KEXEC_CONTROL_MEMORY_LIMIT     (0xFFFFFFFFFFUL)
 
 /* Allocate one page for the pdp and the second for the code */
-# define KEXEC_CONTROL_CODE_SIZE  (4096UL + 4096UL)
+# define KEXEC_CONTROL_PAGE_SIZE  (4096UL + 4096UL)
 
 /* The native architecture */
 # define KEXEC_ARCH KEXEC_ARCH_X86_64
diff --git a/include/asm-x86/mman.h b/include/asm-x86/mman.h
index c1682b542da..90bc4108a4f 100644
--- a/include/asm-x86/mman.h
+++ b/include/asm-x86/mman.h
@@ -12,6 +12,7 @@
 #define MAP_NORESERVE	0x4000		/* don't check for reservations */
 #define MAP_POPULATE	0x8000		/* populate (prefault) pagetables */
 #define MAP_NONBLOCK	0x10000		/* do not block on IO */
+#define MAP_STACK	0x20000		/* give out an address that is best suited for process/thread stacks */
 
 #define MCL_CURRENT	1		/* lock all current mappings */
 #define MCL_FUTURE	2		/* lock all future mappings */
diff --git a/include/asm-x86/mmzone_32.h b/include/asm-x86/mmzone_32.h
index b2298a22756..5862e646065 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/percpu.h b/include/asm-x86/percpu.h
index 4e91ee1e37a..f643a3a92da 100644
--- a/include/asm-x86/percpu.h
+++ b/include/asm-x86/percpu.h
@@ -182,7 +182,7 @@ do {							\
 	DEFINE_PER_CPU(_type, _name) = _initvalue;			\
 	__typeof__(_type) _name##_early_map[NR_CPUS] __initdata =	\
 				{ [0 ... NR_CPUS-1] = _initvalue };	\
-	__typeof__(_type) *_name##_early_ptr = _name##_early_map
+	__typeof__(_type) *_name##_early_ptr __refdata = _name##_early_map
 
 #define EXPORT_EARLY_PER_CPU_SYMBOL(_name)			\
 	EXPORT_PER_CPU_SYMBOL(_name)
diff --git a/include/asm-x86/pgtable_64.h b/include/asm-x86/pgtable_64.h
index ac5fff4cc58..549144d03d9 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 5f58da401b4..4df3e2f6fb5 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 4f9a9861799..e39c790dbfd 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)