3 files changed, 34 insertions, 7 deletions

diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 0ab4f9fd2687..3a45668f6dc3 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -50,6 +50,7 @@ void acpi_pic_sci_set_trigger(unsigned int, u16);
 
 extern int (*__acpi_register_gsi)(struct device *dev, u32 gsi,
                                   int trigger, int polarity);
+extern void (*__acpi_unregister_gsi)(u32 gsi);
 
 static inline void disable_acpi(void)
 {
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index 50d033a8947d..a94b82e8f156 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -251,7 +251,8 @@ static inline void native_load_tls(struct thread_struct *t, unsigned int cpu)
                 gdt[GDT_ENTRY_TLS_MIN + i] = t->tls_array[i];
 }
 
-#define _LDT_empty(info)                                \
+/* This intentionally ignores lm, since 32-bit apps don't have that field. */
+#define LDT_empty(info)                                 \
         ((info)->base_addr              == 0    &&      \
          (info)->limit                  == 0    &&      \
          (info)->contents               == 0    &&      \
@@ -261,11 +262,18 @@ static inline void native_load_tls(struct thread_struct *t, unsigned int cpu)
          (info)->seg_not_present        == 1    &&      \
          (info)->useable                == 0)
 
-#ifdef CONFIG_X86_64
-#define LDT_empty(info) (_LDT_empty(info) && ((info)->lm == 0))
-#else
-#define LDT_empty(info) (_LDT_empty(info))
-#endif
+/* Lots of programs expect an all-zero user_desc to mean "no segment at all". */
+static inline bool LDT_zero(const struct user_desc *info)
+{
+        return (info->base_addr         == 0 &&
+                info->limit             == 0 &&
+                info->contents          == 0 &&
+                info->read_exec_only    == 0 &&
+                info->seg_32bit         == 0 &&
+                info->limit_in_pages    == 0 &&
+                info->seg_not_present   == 0 &&
+                info->useable           == 0);
+}
 
 static inline void clear_LDT(void)
 {
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 40269a2bf6f9..4b75d591eb5e 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -130,7 +130,25 @@ static inline void arch_bprm_mm_init(struct mm_struct *mm,
 static inline void arch_unmap(struct mm_struct *mm, struct vm_area_struct *vma,
                               unsigned long start, unsigned long end)
 {
-        mpx_notify_unmap(mm, vma, start, end);
+        /*
+         * mpx_notify_unmap() goes and reads a rarely-hot
+         * cacheline in the mm_struct.  That can be expensive
+         * enough to be seen in profiles.
+         *
+         * The mpx_notify_unmap() call and its contents have been
+         * observed to affect munmap() performance on hardware
+         * where MPX is not present.
+         *
+         * The unlikely() optimizes for the fast case: no MPX
+         * in the CPU, or no MPX use in the process.  Even if
+         * we get this wrong (in the unlikely event that MPX
+         * is widely enabled on some system) the overhead of
+         * MPX itself (reading bounds tables) is expected to
+         * overwhelm the overhead of getting this unlikely()
+         * consistently wrong.
+         */
+        if (unlikely(cpu_feature_enabled(X86_FEATURE_MPX)))
+                mpx_notify_unmap(mm, vma, start, end);
 }
 
 #endif /* _ASM_X86_MMU_CONTEXT_H */