Merge commit 'v2.6.26' into bkl-removal

17 files changed, 114 insertions, 53 deletions

diff --git a/include/asm-x86/desc.h b/include/asm-x86/desc.h
index 268a012bcd79..28bddbcb38be 100644
--- a/include/asm-x86/desc.h
+++ b/include/asm-x86/desc.h
@@ -192,8 +192,8 @@ static inline void native_set_ldt(const void *addr, unsigned int entries)
 		unsigned cpu = smp_processor_id();
 		ldt_desc ldt;
 
-		set_tssldt_descriptor(&ldt, (unsigned long)addr,
-				      DESC_LDT, entries * sizeof(ldt) - 1);
+		set_tssldt_descriptor(&ldt, (unsigned long)addr, DESC_LDT,
+				      entries * LDT_ENTRY_SIZE - 1);
 		write_gdt_entry(get_cpu_gdt_table(cpu), GDT_ENTRY_LDT,
 				&ldt, DESC_LDT);
 		asm volatile("lldt %w0"::"q" (GDT_ENTRY_LDT*8));
diff --git a/include/asm-x86/geode.h b/include/asm-x86/geode.h
index 6e6458853a36..bb06027fc83e 100644
--- a/include/asm-x86/geode.h
+++ b/include/asm-x86/geode.h
@@ -112,8 +112,8 @@ extern int geode_get_dev_base(unsigned int dev);
 #define VSA_VR_UNLOCK		0xFC53	/* unlock virtual register */
 #define VSA_VR_SIGNATURE	0x0003
 #define VSA_VR_MEM_SIZE		0x0200
-#define VSA_SIG			0x4132	/* signature is ascii 'VSA2' */
-
+#define AMD_VSA_SIG		0x4132	/* signature is ascii 'VSA2' */
+#define GSW_VSA_SIG		0x534d  /* General Software signature */
 /* GPIO */
 
 #define GPIO_OUTPUT_VAL		0x00
diff --git a/include/asm-x86/i387.h b/include/asm-x86/i387.h
index 6b722d315936..37672f79dcc8 100644
--- a/include/asm-x86/i387.h
+++ b/include/asm-x86/i387.h
@@ -193,6 +193,8 @@ static inline int restore_i387(struct _fpstate __user *buf)
 
 #else  /* CONFIG_X86_32 */
 
+extern void finit(void);
+
 static inline void tolerant_fwait(void)
 {
 	asm volatile("fnclex ; fwait");
diff --git a/include/asm-x86/kvm_host.h b/include/asm-x86/kvm_host.h
index 1d8cd01fa514..844f2a89afbc 100644
--- a/include/asm-x86/kvm_host.h
+++ b/include/asm-x86/kvm_host.h
@@ -18,6 +18,7 @@
 #include <linux/kvm_para.h>
 #include <linux/kvm_types.h>
 
+#include <asm/pvclock-abi.h>
 #include <asm/desc.h>
 
 #define KVM_MAX_VCPUS 16
@@ -282,7 +283,8 @@ struct kvm_vcpu_arch {
 	struct x86_emulate_ctxt emulate_ctxt;
 
 	gpa_t time;
-	struct kvm_vcpu_time_info hv_clock;
+	struct pvclock_vcpu_time_info hv_clock;
+	unsigned int hv_clock_tsc_khz;
 	unsigned int time_offset;
 	struct page *time_page;
 };
diff --git a/include/asm-x86/kvm_para.h b/include/asm-x86/kvm_para.h
index 509845942070..76f392146daa 100644
--- a/include/asm-x86/kvm_para.h
+++ b/include/asm-x86/kvm_para.h
@@ -48,24 +48,6 @@ struct kvm_mmu_op_release_pt {
 #ifdef __KERNEL__
 #include <asm/processor.h>
 
-/* xen binary-compatible interface. See xen headers for details */
-struct kvm_vcpu_time_info {
-	uint32_t version;
-	uint32_t pad0;
-	uint64_t tsc_timestamp;
-	uint64_t system_time;
-	uint32_t tsc_to_system_mul;
-	int8_t   tsc_shift;
-	int8_t	 pad[3];
-} __attribute__((__packed__)); /* 32 bytes */
-
-struct kvm_wall_clock {
-	uint32_t wc_version;
-	uint32_t wc_sec;
-	uint32_t wc_nsec;
-} __attribute__((__packed__));
-
-
 extern void kvmclock_init(void);
 
 
@@ -89,7 +71,8 @@ static inline long kvm_hypercall0(unsigned int nr)
 	long ret;
 	asm volatile(KVM_HYPERCALL
 		     : "=a"(ret)
-		     : "a"(nr));
+		     : "a"(nr)
+		     : "memory");
 	return ret;
 }
 
@@ -98,7 +81,8 @@ static inline long kvm_hypercall1(unsigned int nr, unsigned long p1)
 	long ret;
 	asm volatile(KVM_HYPERCALL
 		     : "=a"(ret)
-		     : "a"(nr), "b"(p1));
+		     : "a"(nr), "b"(p1)
+		     : "memory");
 	return ret;
 }
 
@@ -108,7 +92,8 @@ static inline long kvm_hypercall2(unsigned int nr, unsigned long p1,
 	long ret;
 	asm volatile(KVM_HYPERCALL
 		     : "=a"(ret)
-		     : "a"(nr), "b"(p1), "c"(p2));
+		     : "a"(nr), "b"(p1), "c"(p2)
+		     : "memory");
 	return ret;
 }
 
@@ -118,7 +103,8 @@ static inline long kvm_hypercall3(unsigned int nr, unsigned long p1,
 	long ret;
 	asm volatile(KVM_HYPERCALL
 		     : "=a"(ret)
-		     : "a"(nr), "b"(p1), "c"(p2), "d"(p3));
+		     : "a"(nr), "b"(p1), "c"(p2), "d"(p3)
+		     : "memory");
 	return ret;
 }
 
@@ -129,7 +115,8 @@ static inline long kvm_hypercall4(unsigned int nr, unsigned long p1,
 	long ret;
 	asm volatile(KVM_HYPERCALL
 		     : "=a"(ret)
-		     : "a"(nr), "b"(p1), "c"(p2), "d"(p3), "S"(p4));
+		     : "a"(nr), "b"(p1), "c"(p2), "d"(p3), "S"(p4)
+		     : "memory");
 	return ret;
 }
 
diff --git a/include/asm-x86/kvm_x86_emulate.h b/include/asm-x86/kvm_x86_emulate.h
index d6337f941c98..b877bbd2d3a7 100644
--- a/include/asm-x86/kvm_x86_emulate.h
+++ b/include/asm-x86/kvm_x86_emulate.h
@@ -135,6 +135,7 @@ struct decode_cache {
 	u8 modrm_rm;
 	u8 use_modrm_ea;
 	unsigned long modrm_ea;
+	void *modrm_ptr;
 	unsigned long modrm_val;
 	struct fetch_cache fetch;
 };
diff --git a/include/asm-x86/msr.h b/include/asm-x86/msr.h
index 3707650a169b..2b5f2c91db25 100644
--- a/include/asm-x86/msr.h
+++ b/include/asm-x86/msr.h
@@ -18,7 +18,7 @@ static inline unsigned long long native_read_tscp(unsigned int *aux)
 	unsigned long low, high;
 	asm volatile(".byte 0x0f,0x01,0xf9"
 		     : "=a" (low), "=d" (high), "=c" (*aux));
-	return low | ((u64)high >> 32);
+	return low | ((u64)high << 32);
 }
 
 /*
diff --git a/include/asm-x86/page.h b/include/asm-x86/page.h
index b381f4a5a0bd..dc936dddf161 100644
--- a/include/asm-x86/page.h
+++ b/include/asm-x86/page.h
@@ -10,8 +10,16 @@
 
 #ifdef __KERNEL__
 
-#define PHYSICAL_PAGE_MASK	(PAGE_MASK & __PHYSICAL_MASK)
-#define PTE_MASK		(_AT(long, PHYSICAL_PAGE_MASK))
+#define __PHYSICAL_MASK		((phys_addr_t)(1ULL << __PHYSICAL_MASK_SHIFT) - 1)
+#define __VIRTUAL_MASK		((1UL << __VIRTUAL_MASK_SHIFT) - 1)
+
+/* Cast PAGE_MASK to a signed type so that it is sign-extended if
+   virtual addresses are 32-bits but physical addresses are larger
+   (ie, 32-bit PAE). */
+#define PHYSICAL_PAGE_MASK	(((signed long)PAGE_MASK) & __PHYSICAL_MASK)
+
+/* PTE_MASK extracts the PFN from a (pte|pmd|pud|pgd)val_t */
+#define PTE_MASK		((pteval_t)PHYSICAL_PAGE_MASK)
 
 #define PMD_PAGE_SIZE		(_AC(1, UL) << PMD_SHIFT)
 #define PMD_PAGE_MASK		(~(PMD_PAGE_SIZE-1))
@@ -24,9 +32,6 @@
 /* to align the pointer to the (next) page boundary */
 #define PAGE_ALIGN(addr)	(((addr)+PAGE_SIZE-1)&PAGE_MASK)
 
-#define __PHYSICAL_MASK		_AT(phys_addr_t, (_AC(1,ULL) << __PHYSICAL_MASK_SHIFT) - 1)
-#define __VIRTUAL_MASK		((_AC(1,UL) << __VIRTUAL_MASK_SHIFT) - 1)
-
 #ifndef __ASSEMBLY__
 #include <linux/types.h>
 #endif
diff --git a/include/asm-x86/page_32.h b/include/asm-x86/page_32.h
index 424e82f8ae27..ccf0ba3c3aba 100644
--- a/include/asm-x86/page_32.h
+++ b/include/asm-x86/page_32.h
@@ -14,7 +14,8 @@
 #define __PAGE_OFFSET		_AC(CONFIG_PAGE_OFFSET, UL)
 
 #ifdef CONFIG_X86_PAE
-#define __PHYSICAL_MASK_SHIFT	36
+/* 44=32+12, the limit we can fit into an unsigned long pfn */
+#define __PHYSICAL_MASK_SHIFT	44
 #define __VIRTUAL_MASK_SHIFT	32
 #define PAGETABLE_LEVELS	3
 
diff --git a/include/asm-x86/pgtable-3level.h b/include/asm-x86/pgtable-3level.h
index 8b4a9d44b7f4..c93dbb6c2624 100644
--- a/include/asm-x86/pgtable-3level.h
+++ b/include/asm-x86/pgtable-3level.h
@@ -120,9 +120,9 @@ static inline void pud_clear(pud_t *pudp)
 		write_cr3(pgd);
 }
 
-#define pud_page(pud) ((struct page *) __va(pud_val(pud) & PAGE_MASK))
+#define pud_page(pud) ((struct page *) __va(pud_val(pud) & PTE_MASK))
 
-#define pud_page_vaddr(pud) ((unsigned long) __va(pud_val(pud) & PAGE_MASK))
+#define pud_page_vaddr(pud) ((unsigned long) __va(pud_val(pud) & PTE_MASK))
 
 
 /* Find an entry in the second-level page table.. */
@@ -160,7 +160,7 @@ static inline int pte_none(pte_t pte)
 
 static inline unsigned long pte_pfn(pte_t pte)
 {
-	return (pte_val(pte) & ~_PAGE_NX) >> PAGE_SHIFT;
+	return (pte_val(pte) & PTE_MASK) >> PAGE_SHIFT;
 }
 
 /*
diff --git a/include/asm-x86/pgtable.h b/include/asm-x86/pgtable.h
index 55c3a0e3a8ce..97c271b2910b 100644
--- a/include/asm-x86/pgtable.h
+++ b/include/asm-x86/pgtable.h
@@ -57,6 +57,7 @@
 #define _KERNPG_TABLE	(_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED |	\
 			 _PAGE_DIRTY)
 
+/* Set of bits not changed in pte_modify */
 #define _PAGE_CHG_MASK	(PTE_MASK | _PAGE_PCD | _PAGE_PWT |		\
 			 _PAGE_ACCESSED | _PAGE_DIRTY)
 
@@ -304,7 +305,7 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
 	return __pgprot(preservebits | addbits);
 }
 
-#define pte_pgprot(x) __pgprot(pte_val(x) & (0xfff | _PAGE_NX))
+#define pte_pgprot(x) __pgprot(pte_val(x) & ~PTE_MASK)
 
 #define canon_pgprot(p) __pgprot(pgprot_val(p) & __supported_pte_mask)
 
diff --git a/include/asm-x86/pgtable_32.h b/include/asm-x86/pgtable_32.h
index d7f0403bbecb..32ca03109a4c 100644
--- a/include/asm-x86/pgtable_32.h
+++ b/include/asm-x86/pgtable_32.h
@@ -88,7 +88,7 @@ extern unsigned long pg0[];
 /* To avoid harmful races, pmd_none(x) should check only the lower when PAE */
 #define pmd_none(x)	(!(unsigned long)pmd_val((x)))
 #define pmd_present(x)	(pmd_val((x)) & _PAGE_PRESENT)
-#define pmd_bad(x) ((pmd_val(x) & (~PAGE_MASK & ~_PAGE_USER)) != _KERNPG_TABLE)
+#define pmd_bad(x) ((pmd_val(x) & (~PTE_MASK & ~_PAGE_USER)) != _KERNPG_TABLE)
 
 #define pages_to_mb(x) ((x) >> (20-PAGE_SHIFT))
 
@@ -159,7 +159,7 @@ static inline int pud_large(pud_t pud) { return 0; }
 #define pmd_page(pmd) (pfn_to_page(pmd_val((pmd)) >> PAGE_SHIFT))
 
 #define pmd_page_vaddr(pmd)					\
-	((unsigned long)__va(pmd_val((pmd)) & PAGE_MASK))
+	((unsigned long)__va(pmd_val((pmd)) & PTE_MASK))
 
 #if defined(CONFIG_HIGHPTE)
 #define pte_offset_map(dir, address)					\
diff --git a/include/asm-x86/pgtable_64.h b/include/asm-x86/pgtable_64.h
index efe83dcbd412..1cc50d22d735 100644
--- a/include/asm-x86/pgtable_64.h
+++ b/include/asm-x86/pgtable_64.h
@@ -151,19 +151,19 @@ static inline void native_pgd_clear(pgd_t *pgd)
 
 #ifndef __ASSEMBLY__
 
-static inline unsigned long pgd_bad(pgd_t pgd)
+static inline int pgd_bad(pgd_t pgd)
 {
-	return pgd_val(pgd) & ~(PTE_MASK | _KERNPG_TABLE | _PAGE_USER);
+	return (pgd_val(pgd) & ~(PTE_MASK | _PAGE_USER)) != _KERNPG_TABLE;
 }
 
-static inline unsigned long pud_bad(pud_t pud)
+static inline int pud_bad(pud_t pud)
 {
-	return pud_val(pud) & ~(PTE_MASK | _KERNPG_TABLE | _PAGE_USER);
+	return (pud_val(pud) & ~(PTE_MASK | _PAGE_USER)) != _KERNPG_TABLE;
 }
 
-static inline unsigned long pmd_bad(pmd_t pmd)
+static inline int pmd_bad(pmd_t pmd)
 {
-	return pmd_val(pmd) & ~(PTE_MASK | _KERNPG_TABLE | _PAGE_USER);
+	return (pmd_val(pmd) & ~(PTE_MASK | _PAGE_USER)) != _KERNPG_TABLE;
 }
 
 #define pte_none(x)	(!pte_val((x)))
diff --git a/include/asm-x86/pvclock-abi.h b/include/asm-x86/pvclock-abi.h
new file mode 100644
index 000000000000..6857f840b243
--- /dev/null
+++ b/include/asm-x86/pvclock-abi.h
@@ -0,0 +1,42 @@
+#ifndef _ASM_X86_PVCLOCK_ABI_H_
+#define _ASM_X86_PVCLOCK_ABI_H_
+#ifndef __ASSEMBLY__
+
+/*
+ * These structs MUST NOT be changed.
+ * They are the ABI between hypervisor and guest OS.
+ * Both Xen and KVM are using this.
+ *
+ * pvclock_vcpu_time_info holds the system time and the tsc timestamp
+ * of the last update. So the guest can use the tsc delta to get a
+ * more precise system time.  There is one per virtual cpu.
+ *
+ * pvclock_wall_clock references the point in time when the system
+ * time was zero (usually boot time), thus the guest calculates the
+ * current wall clock by adding the system time.
+ *
+ * Protocol for the "version" fields is: hypervisor raises it (making
+ * it uneven) before it starts updating the fields and raises it again
+ * (making it even) when it is done.  Thus the guest can make sure the
+ * time values it got are consistent by checking the version before
+ * and after reading them.
+ */
+
+struct pvclock_vcpu_time_info {
+	u32   version;
+	u32   pad0;
+	u64   tsc_timestamp;
+	u64   system_time;
+	u32   tsc_to_system_mul;
+	s8    tsc_shift;
+	u8    pad[3];
+} __attribute__((__packed__)); /* 32 bytes */
+
+struct pvclock_wall_clock {
+	u32   version;
+	u32   sec;
+	u32   nsec;
+} __attribute__((__packed__));
+
+#endif /* __ASSEMBLY__ */
+#endif /* _ASM_X86_PVCLOCK_ABI_H_ */
diff --git a/include/asm-x86/pvclock.h b/include/asm-x86/pvclock.h
new file mode 100644
index 000000000000..85b1bba8e0a3
--- /dev/null
+++ b/include/asm-x86/pvclock.h
@@ -0,0 +1,13 @@
+#ifndef _ASM_X86_PVCLOCK_H_
+#define _ASM_X86_PVCLOCK_H_
+
+#include <linux/clocksource.h>
+#include <asm/pvclock-abi.h>
+
+/* some helper functions for xen and kvm pv clock sources */
+cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src);
+void pvclock_read_wallclock(struct pvclock_wall_clock *wall,
+			    struct pvclock_vcpu_time_info *vcpu,
+			    struct timespec *ts);
+
+#endif /* _ASM_X86_PVCLOCK_H_ */
diff --git a/include/asm-x86/tlbflush.h b/include/asm-x86/tlbflush.h
index 0c0674d94255..35c76ceb9f40 100644
--- a/include/asm-x86/tlbflush.h
+++ b/include/asm-x86/tlbflush.h
@@ -22,12 +22,23 @@ static inline void __native_flush_tlb(void)
 
 static inline void __native_flush_tlb_global(void)
 {
-	unsigned long cr4 = read_cr4();
+	unsigned long flags;
+	unsigned long cr4;
 
+	/*
+	 * Read-modify-write to CR4 - protect it from preemption and
+	 * from interrupts. (Use the raw variant because this code can
+	 * be called from deep inside debugging code.)
+	 */
+	raw_local_irq_save(flags);
+
+	cr4 = read_cr4();
 	/* clear PGE */
 	write_cr4(cr4 & ~X86_CR4_PGE);
 	/* write old PGE again and flush TLBs */
 	write_cr4(cr4);
+
+	raw_local_irq_restore(flags);
 }
 
 static inline void __native_flush_tlb_single(unsigned long addr)
diff --git a/include/asm-x86/xen/page.h b/include/asm-x86/xen/page.h
index 01799305f02a..e11f24038b1d 100644
--- a/include/asm-x86/xen/page.h
+++ b/include/asm-x86/xen/page.h
@@ -127,7 +127,7 @@ static inline void set_phys_to_machine(unsigned long pfn, unsigned long mfn)
 
 static inline unsigned long pte_mfn(pte_t pte)
 {
-	return (pte.pte & ~_PAGE_NX) >> PAGE_SHIFT;
+	return (pte.pte & PTE_MASK) >> PAGE_SHIFT;
 }
 
 static inline pte_t mfn_pte(unsigned long page_nr, pgprot_t pgprot)
@@ -150,13 +150,9 @@ static inline pte_t __pte_ma(pteval_t x)
 	return (pte_t) { .pte = x };
 }
 
-#ifdef CONFIG_X86_PAE
 #define pmd_val_ma(v) ((v).pmd)
 #define pud_val_ma(v) ((v).pgd.pgd)
 #define __pmd_ma(x)	((pmd_t) { (x) } )
-#else  /* !X86_PAE */
-#define pmd_val_ma(v)	((v).pud.pgd.pgd)
-#endif	/* CONFIG_X86_PAE */
 
 #define pgd_val_ma(x)	((x).pgd)