Merge branch 'x86/trampoline' into x86/urgent

x86/trampoline contains an urgent commit which is necessarily on a
newer baseline.

Signed-off-by: H. Peter Anvin <hpa@zytor.com>

18 files changed, 214 insertions, 83 deletions

diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 610001d385dd..0c44630d1789 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -29,7 +29,7 @@
 #include <asm/processor.h>
 #include <asm/mmu.h>
 #include <asm/mpspec.h>
-#include <asm/trampoline.h>
+#include <asm/realmode.h>
 
 #define COMPILER_DEPENDENT_INT64   long long
 #define COMPILER_DEPENDENT_UINT64  unsigned long long
@@ -117,11 +117,8 @@ static inline void acpi_disable_pci(void)
 /* Low-level suspend routine. */
 extern int acpi_suspend_lowlevel(void);
 
-extern const unsigned char acpi_wakeup_code[];
-#define acpi_wakeup_address (__pa(TRAMPOLINE_SYM(acpi_wakeup_code)))
-
-/* early initialization routine */
-extern void acpi_reserve_wakeup_memory(void);
+/* Physical address to resume after wakeup */
+#define acpi_wakeup_address ((unsigned long)(real_mode_header->wakeup_start))
 
 /*
  * Check if the CPU can handle C2 and deeper
diff --git a/arch/x86/include/asm/dma-contiguous.h b/arch/x86/include/asm/dma-contiguous.h
new file mode 100644
index 000000000000..c09241659971
--- /dev/null
+++ b/arch/x86/include/asm/dma-contiguous.h
@@ -0,0 +1,13 @@
+#ifndef ASMX86_DMA_CONTIGUOUS_H
+#define ASMX86_DMA_CONTIGUOUS_H
+
+#ifdef __KERNEL__
+
+#include <linux/types.h>
+#include <asm-generic/dma-contiguous.h>
+
+static inline void
+dma_contiguous_early_fixup(phys_addr_t base, unsigned long size) { }
+
+#endif
+#endif
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index 61c0bd25845a..f7b4c7903e7e 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -13,6 +13,7 @@
 #include <asm/io.h>
 #include <asm/swiotlb.h>
 #include <asm-generic/dma-coherent.h>
+#include <linux/dma-contiguous.h>
 
 #ifdef CONFIG_ISA
 # define ISA_DMA_BIT_MASK DMA_BIT_MASK(24)
@@ -62,6 +63,10 @@ extern void *dma_generic_alloc_coherent(struct device *dev, size_t size,
 					dma_addr_t *dma_addr, gfp_t flag,
 					struct dma_attrs *attrs);
 
+extern void dma_generic_free_coherent(struct device *dev, size_t size,
+				      void *vaddr, dma_addr_t dma_addr,
+				      struct dma_attrs *attrs);
+
 #ifdef CONFIG_X86_DMA_REMAP /* Platform code defines bridge-specific code */
 extern bool dma_capable(struct device *dev, dma_addr_t addr, size_t size);
 extern dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr);
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index c222e1a1b12a..1ac46c22dd50 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -200,7 +200,7 @@ typedef u32 __attribute__((vector_size(16))) sse128_t;
 
 /* Type, address-of, and value of an instruction's operand. */
 struct operand {
-	enum { OP_REG, OP_MEM, OP_IMM, OP_XMM, OP_NONE } type;
+	enum { OP_REG, OP_MEM, OP_IMM, OP_XMM, OP_MM, OP_NONE } type;
 	unsigned int bytes;
 	union {
 		unsigned long orig_val;
@@ -213,12 +213,14 @@ struct operand {
 			unsigned seg;
 		} mem;
 		unsigned xmm;
+		unsigned mm;
 	} addr;
 	union {
 		unsigned long val;
 		u64 val64;
 		char valptr[sizeof(unsigned long) + 2];
 		sse128_t vec_val;
+		u64 mm_val;
 	};
 };
 
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index e5b97be12d2a..db7c1f2709a2 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -173,6 +173,9 @@ enum {
 #define DR7_FIXED_1	0x00000400
 #define DR7_VOLATILE	0xffff23ff
 
+/* apic attention bits */
+#define KVM_APIC_CHECK_VAPIC	0
+
 /*
  * We don't want allocation failures within the mmu code, so we preallocate
  * enough memory for a single page fault in a cache.
@@ -238,8 +241,6 @@ struct kvm_mmu_page {
 #endif
 
 	int write_flooding_count;
-
-	struct rcu_head rcu;
 };
 
 struct kvm_pio_request {
@@ -338,6 +339,7 @@ struct kvm_vcpu_arch {
 	u64 efer;
 	u64 apic_base;
 	struct kvm_lapic *apic;    /* kernel irqchip context */
+	unsigned long apic_attention;
 	int32_t apic_arb_prio;
 	int mp_state;
 	int sipi_vector;
@@ -537,8 +539,6 @@ struct kvm_arch {
 	u64 hv_guest_os_id;
 	u64 hv_hypercall;
 
-	atomic_t reader_counter;
-
 	#ifdef CONFIG_KVM_MMU_AUDIT
 	int audit_point;
 	#endif
@@ -713,8 +713,9 @@ void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
 
 int kvm_mmu_reset_context(struct kvm_vcpu *vcpu);
 void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot);
-int kvm_mmu_rmap_write_protect(struct kvm *kvm, u64 gfn,
-			       struct kvm_memory_slot *slot);
+void kvm_mmu_write_protect_pt_masked(struct kvm *kvm,
+				     struct kvm_memory_slot *slot,
+				     gfn_t gfn_offset, unsigned long mask);
 void kvm_mmu_zap_all(struct kvm *kvm);
 unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm);
 void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages);
diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index 183922e13de1..63ab1661d00e 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -95,6 +95,14 @@ struct kvm_vcpu_pv_apf_data {
 extern void kvmclock_init(void);
 extern int kvm_register_clock(char *txt);
 
+#ifdef CONFIG_KVM_CLOCK
+bool kvm_check_and_clear_guest_paused(void);
+#else
+static inline bool kvm_check_and_clear_guest_paused(void)
+{
+	return false;
+}
+#endif /* CONFIG_KVMCLOCK */
 
 /* This instruction is vmcall.  On non-VT architectures, it will generate a
  * trap that we will then rewrite to the appropriate instruction.
@@ -173,14 +181,16 @@ static inline int kvm_para_available(void)
 	if (boot_cpu_data.cpuid_level < 0)
 		return 0;	/* So we don't blow up on old processors */
 
-	cpuid(KVM_CPUID_SIGNATURE, &eax, &ebx, &ecx, &edx);
-	memcpy(signature + 0, &ebx, 4);
-	memcpy(signature + 4, &ecx, 4);
-	memcpy(signature + 8, &edx, 4);
-	signature[12] = 0;
+	if (cpu_has_hypervisor) {
+		cpuid(KVM_CPUID_SIGNATURE, &eax, &ebx, &ecx, &edx);
+		memcpy(signature + 0, &ebx, 4);
+		memcpy(signature + 4, &ecx, 4);
+		memcpy(signature + 8, &edx, 4);
+		signature[12] = 0;
 
-	if (strcmp(signature, "KVMKVMKVM") == 0)
-		return 1;
+		if (strcmp(signature, "KVMKVMKVM") == 0)
+			return 1;
+	}
 
 	return 0;
 }
diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h
index effff47a3c82..43876f16caf1 100644
--- a/arch/x86/include/asm/pgtable-3level.h
+++ b/arch/x86/include/asm/pgtable-3level.h
@@ -31,6 +31,56 @@ static inline void native_set_pte(pte_t *ptep, pte_t pte)
 	ptep->pte_low = pte.pte_low;
 }
 
+#define pmd_read_atomic pmd_read_atomic
+/*
+ * pte_offset_map_lock on 32bit PAE kernels was reading the pmd_t with
+ * a "*pmdp" dereference done by gcc. Problem is, in certain places
+ * where pte_offset_map_lock is called, concurrent page faults are
+ * allowed, if the mmap_sem is hold for reading. An example is mincore
+ * vs page faults vs MADV_DONTNEED. On the page fault side
+ * pmd_populate rightfully does a set_64bit, but if we're reading the
+ * pmd_t with a "*pmdp" on the mincore side, a SMP race can happen
+ * because gcc will not read the 64bit of the pmd atomically. To fix
+ * this all places running pmd_offset_map_lock() while holding the
+ * mmap_sem in read mode, shall read the pmdp pointer using this
+ * function to know if the pmd is null nor not, and in turn to know if
+ * they can run pmd_offset_map_lock or pmd_trans_huge or other pmd
+ * operations.
+ *
+ * Without THP if the mmap_sem is hold for reading, the
+ * pmd can only transition from null to not null while pmd_read_atomic runs.
+ * So there's no need of literally reading it atomically.
+ *
+ * With THP if the mmap_sem is hold for reading, the pmd can become
+ * THP or null or point to a pte (and in turn become "stable") at any
+ * time under pmd_read_atomic, so it's mandatory to read it atomically
+ * with cmpxchg8b.
+ */
+#ifndef CONFIG_TRANSPARENT_HUGEPAGE
+static inline pmd_t pmd_read_atomic(pmd_t *pmdp)
+{
+	pmdval_t ret;
+	u32 *tmp = (u32 *)pmdp;
+
+	ret = (pmdval_t) (*tmp);
+	if (ret) {
+		/*
+		 * If the low part is null, we must not read the high part
+		 * or we can end up with a partial pmd.
+		 */
+		smp_rmb();
+		ret |= ((pmdval_t)*(tmp + 1)) << 32;
+	}
+
+	return (pmd_t) { ret };
+}
+#else /* CONFIG_TRANSPARENT_HUGEPAGE */
+static inline pmd_t pmd_read_atomic(pmd_t *pmdp)
+{
+	return (pmd_t) { atomic64_read((atomic64_t *)pmdp) };
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
 static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte)
 {
 	set_64bit((unsigned long long *)(ptep), native_pte_val(pte));
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 7745b257f035..39bc5777211a 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -544,13 +544,16 @@ static inline void load_sp0(struct tss_struct *tss,
  * enable), so that any CPU's that boot up
  * after us can get the correct flags.
  */
-extern unsigned long		mmu_cr4_features;
+extern unsigned long mmu_cr4_features;
+extern u32 *trampoline_cr4_features;
 
 static inline void set_in_cr4(unsigned long mask)
 {
 	unsigned long cr4;
 
 	mmu_cr4_features |= mask;
+	if (trampoline_cr4_features)
+		*trampoline_cr4_features = mmu_cr4_features;
 	cr4 = read_cr4();
 	cr4 |= mask;
 	write_cr4(cr4);
@@ -561,6 +564,8 @@ static inline void clear_in_cr4(unsigned long mask)
 	unsigned long cr4;
 
 	mmu_cr4_features &= ~mask;
+	if (trampoline_cr4_features)
+		*trampoline_cr4_features = mmu_cr4_features;
 	cr4 = read_cr4();
 	cr4 &= ~mask;
 	write_cr4(cr4);
diff --git a/arch/x86/include/asm/pvclock-abi.h b/arch/x86/include/asm/pvclock-abi.h
index 35f2d1948ada..6167fd798188 100644
--- a/arch/x86/include/asm/pvclock-abi.h
+++ b/arch/x86/include/asm/pvclock-abi.h
@@ -40,5 +40,6 @@ struct pvclock_wall_clock {
 } __attribute__((__packed__));
 
 #define PVCLOCK_TSC_STABLE_BIT	(1 << 0)
+#define PVCLOCK_GUEST_STOPPED	(1 << 1)
 #endif /* __ASSEMBLY__ */
 #endif /* _ASM_X86_PVCLOCK_ABI_H */
diff --git a/arch/x86/include/asm/realmode.h b/arch/x86/include/asm/realmode.h
new file mode 100644
index 000000000000..fce3f4ae5bd6
--- /dev/null
+++ b/arch/x86/include/asm/realmode.h
@@ -0,0 +1,62 @@
+#ifndef _ARCH_X86_REALMODE_H
+#define _ARCH_X86_REALMODE_H
+
+#include <linux/types.h>
+#include <asm/io.h>
+
+/* This must match data at realmode.S */
+struct real_mode_header {
+	u32	text_start;
+	u32	ro_end;
+	/* SMP trampoline */
+	u32	trampoline_start;
+	u32	trampoline_status;
+	u32	trampoline_header;
+#ifdef CONFIG_X86_64
+	u32	trampoline_pgd;
+#endif
+	/* ACPI S3 wakeup */
+#ifdef CONFIG_ACPI_SLEEP
+	u32	wakeup_start;
+	u32	wakeup_header;
+#endif
+	/* APM/BIOS reboot */
+#ifdef CONFIG_X86_32
+	u32	machine_real_restart_asm;
+#endif
+};
+
+/* This must match data at trampoline_32/64.S */
+struct trampoline_header {
+#ifdef CONFIG_X86_32
+	u32 start;
+	u16 gdt_pad;
+	u16 gdt_limit;
+	u32 gdt_base;
+#else
+	u64 start;
+	u64 efer;
+	u32 cr4;
+#endif
+};
+
+extern struct real_mode_header *real_mode_header;
+extern unsigned char real_mode_blob_end[];
+
+extern unsigned long init_rsp;
+extern unsigned long initial_code;
+extern unsigned long initial_gs;
+
+extern unsigned char real_mode_blob[];
+extern unsigned char real_mode_relocs[];
+
+#ifdef CONFIG_X86_32
+extern unsigned char startup_32_smp[];
+extern unsigned char boot_gdt[];
+#else
+extern unsigned char secondary_startup_64[];
+#endif
+
+extern void __init setup_real_mode(void);
+
+#endif /* _ARCH_X86_REALMODE_H */
diff --git a/arch/x86/include/asm/sta2x11.h b/arch/x86/include/asm/sta2x11.h
new file mode 100644
index 000000000000..e9d32df89ccc
--- /dev/null
+++ b/arch/x86/include/asm/sta2x11.h
@@ -0,0 +1,12 @@
+/*
+ * Header file for STMicroelectronics ConneXt (STA2X11) IOHub
+ */
+#ifndef __ASM_STA2X11_H
+#define __ASM_STA2X11_H
+
+#include <linux/pci.h>
+
+/* This needs to be called from the MFD to configure its sub-devices */
+struct sta2x11_instance *sta2x11_get_instance(struct pci_dev *pdev);
+
+#endif /* __ASM_STA2X11_H */
diff --git a/arch/x86/include/asm/trampoline.h b/arch/x86/include/asm/trampoline.h
deleted file mode 100644
index feca3118a73b..000000000000
--- a/arch/x86/include/asm/trampoline.h
+++ /dev/null
@@ -1,39 +0,0 @@
-#ifndef _ASM_X86_TRAMPOLINE_H
-#define _ASM_X86_TRAMPOLINE_H
-
-#ifndef __ASSEMBLY__
-
-#include <linux/types.h>
-#include <asm/io.h>
-
-/*
- * Trampoline 80x86 program as an array.  These are in the init rodata
- * segment, but that's okay, because we only care about the relative
- * addresses of the symbols.
- */
-extern const unsigned char x86_trampoline_start [];
-extern const unsigned char x86_trampoline_end   [];
-extern unsigned char *x86_trampoline_base;
-
-extern unsigned long init_rsp;
-extern unsigned long initial_code;
-extern unsigned long initial_gs;
-
-extern void __init setup_trampolines(void);
-
-extern const unsigned char trampoline_data[];
-extern const unsigned char trampoline_status[];
-
-#define TRAMPOLINE_SYM(x)						\
-	((void *)(x86_trampoline_base +					\
-		  ((const unsigned char *)(x) - x86_trampoline_start)))
-
-/* Address of the SMP trampoline */
-static inline unsigned long trampoline_address(void)
-{
-	return virt_to_phys(TRAMPOLINE_SYM(trampoline_data));
-}
-
-#endif /* __ASSEMBLY__ */
-
-#endif /* _ASM_X86_TRAMPOLINE_H */
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 851fe0dc13bc..04cd6882308e 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -32,6 +32,7 @@
 
 #define segment_eq(a, b)	((a).seg == (b).seg)
 
+#define user_addr_max() (current_thread_info()->addr_limit.seg)
 #define __addr_ok(addr)					\
 	((unsigned long __force)(addr) <		\
 	 (current_thread_info()->addr_limit.seg))
@@ -565,6 +566,9 @@ copy_from_user_nmi(void *to, const void __user *from, unsigned long n);
 extern __must_check long
 strncpy_from_user(char *dst, const char __user *src, long count);
 
+extern __must_check long strlen_user(const char __user *str);
+extern __must_check long strnlen_user(const char __user *str, long n);
+
 /*
  * movsl can be slow when source and dest are not both 8-byte aligned
  */
diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h
index 8084bc73b18c..576e39bca6ad 100644
--- a/arch/x86/include/asm/uaccess_32.h
+++ b/arch/x86/include/asm/uaccess_32.h
@@ -213,23 +213,6 @@ static inline unsigned long __must_check copy_from_user(void *to,
 	return n;
 }
 
-/**
- * strlen_user: - Get the size of a string in user space.
- * @str: The string to measure.
- *
- * Context: User context only.  This function may sleep.
- *
- * Get the size of a NUL-terminated string in user space.
- *
- * Returns the size of the string INCLUDING the terminating NUL.
- * On exception, returns 0.
- *
- * If there is a limit on the length of a valid string, you may wish to
- * consider using strnlen_user() instead.
- */
-#define strlen_user(str) strnlen_user(str, LONG_MAX)
-
-long strnlen_user(const char __user *str, long n);
 unsigned long __must_check clear_user(void __user *mem, unsigned long len);
 unsigned long __must_check __clear_user(void __user *mem, unsigned long len);
 
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index fcd4b6f3ef02..8e796fbbf9c6 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -208,9 +208,6 @@ int __copy_in_user(void __user *dst, const void __user *src, unsigned size)
 	}
 }
 
-__must_check long strnlen_user(const char __user *str, long n);
-__must_check long __strnlen_user(const char __user *str, long n);
-__must_check long strlen_user(const char __user *str);
 __must_check unsigned long clear_user(void __user *mem, unsigned long len);
 __must_check unsigned long __clear_user(void __user *mem, unsigned long len);
 
diff --git a/arch/x86/include/asm/word-at-a-time.h b/arch/x86/include/asm/word-at-a-time.h
index ae03facfadd6..5b238981542a 100644
--- a/arch/x86/include/asm/word-at-a-time.h
+++ b/arch/x86/include/asm/word-at-a-time.h
@@ -10,6 +10,11 @@
  * bit count instruction, that might be better than the multiply
  * and shift, for example.
  */
+struct word_at_a_time {
+	const unsigned long one_bits, high_bits;
+};
+
+#define WORD_AT_A_TIME_CONSTANTS { REPEAT_BYTE(0x01), REPEAT_BYTE(0x80) }
 
 #ifdef CONFIG_64BIT
 
@@ -37,10 +42,31 @@ static inline long count_masked_bytes(long mask)
 
 #endif
 
-/* Return the high bit set in the first byte that is a zero */
-static inline unsigned long has_zero(unsigned long a)
+/* Return nonzero if it has a zero */
+static inline unsigned long has_zero(unsigned long a, unsigned long *bits, const struct word_at_a_time *c)
+{
+	unsigned long mask = ((a - c->one_bits) & ~a) & c->high_bits;
+	*bits = mask;
+	return mask;
+}
+
+static inline unsigned long prep_zero_mask(unsigned long a, unsigned long bits, const struct word_at_a_time *c)
+{
+	return bits;
+}
+
+static inline unsigned long create_zero_mask(unsigned long bits)
+{
+	bits = (bits - 1) & ~bits;
+	return bits >> 7;
+}
+
+/* The mask we created is directly usable as a bytemask */
+#define zero_bytemask(mask) (mask)
+
+static inline unsigned long find_zero(unsigned long mask)
 {
-	return ((a - REPEAT_BYTE(0x01)) & ~a) & REPEAT_BYTE(0x80);
+	return count_masked_bytes(mask);
 }
 
 /*
diff --git a/arch/x86/include/asm/xen/events.h b/arch/x86/include/asm/xen/events.h
index 1df35417c412..cc146d51449e 100644
--- a/arch/x86/include/asm/xen/events.h
+++ b/arch/x86/include/asm/xen/events.h
@@ -6,6 +6,7 @@ enum ipi_vector {
 	XEN_CALL_FUNCTION_VECTOR,
 	XEN_CALL_FUNCTION_SINGLE_VECTOR,
 	XEN_SPIN_UNLOCK_VECTOR,
+	XEN_IRQ_WORK_VECTOR,
 
 	XEN_NR_IPIS,
 };
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index c34f96c2f7a0..93971e841dd5 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -44,6 +44,7 @@ extern unsigned long  machine_to_phys_nr;
 
 extern unsigned long get_phys_to_machine(unsigned long pfn);
 extern bool set_phys_to_machine(unsigned long pfn, unsigned long mfn);
+extern bool __init early_set_phys_to_machine(unsigned long pfn, unsigned long mfn);
 extern bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn);
 extern unsigned long set_phys_range_identity(unsigned long pfn_s,
 					     unsigned long pfn_e);