13 files changed, 58 insertions, 24 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index df9e885eee14..a6efe0a2e9ae 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -498,6 +498,19 @@ config PARAVIRT
           over full virtualization.  However, when run without a hypervisor
           the kernel is theoretically slower and slightly larger.
 
+config PARAVIRT_SPINLOCKS
+        bool "Paravirtualization layer for spinlocks"
+        depends on PARAVIRT && SMP && EXPERIMENTAL
+        ---help---
+          Paravirtualized spinlocks allow a pvops backend to replace the
+          spinlock implementation with something virtualization-friendly
+          (for example, block the virtual CPU rather than spinning).
+
+          Unfortunately the downside is an up to 5% performance hit on
+          native kernels, with various workloads.
+
+          If you are unsure how to answer this question, answer N.
+
 config PARAVIRT_CLOCK
         bool
         default n
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 378e3691c08c..a53da004e08e 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -1443,7 +1443,7 @@ u64 _paravirt_ident_64(u64);
 
 #define paravirt_nop    ((void *)_paravirt_nop)
 
-#ifdef CONFIG_SMP
+#if defined(CONFIG_SMP) && defined(CONFIG_PARAVIRT_SPINLOCKS)
 
 static inline int __raw_spin_is_locked(struct raw_spinlock *lock)
 {
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index aee103b26d01..02ecb30982a3 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -82,22 +82,22 @@ do {							\
         case 1:                                         \
                 asm(op "b %1,"__percpu_arg(0)           \
                     : "+m" (var)                        \
-                    : "ri" ((T__)val));                 \
+                    : "qi" ((T__)(val)));               \
                 break;                                  \
         case 2:                                         \
                 asm(op "w %1,"__percpu_arg(0)           \
                     : "+m" (var)                        \
-                    : "ri" ((T__)val));                 \
+                    : "ri" ((T__)(val)));               \
                 break;                                  \
         case 4:                                         \
                 asm(op "l %1,"__percpu_arg(0)           \
                     : "+m" (var)                        \
-                    : "ri" ((T__)val));                 \
+                    : "ri" ((T__)(val)));               \
                 break;                                  \
         case 8:                                         \
                 asm(op "q %1,"__percpu_arg(0)           \
                     : "+m" (var)                        \
-                    : "re" ((T__)val));                 \
+                    : "re" ((T__)(val)));               \
                 break;                                  \
         default: __bad_percpu_size();                   \
         }                                               \
@@ -109,7 +109,7 @@ do {							\
         switch (sizeof(var)) {                          \
         case 1:                                         \
                 asm(op "b "__percpu_arg(1)",%0"         \
-                    : "=r" (ret__)                      \
+                    : "=q" (ret__)                      \
                     : "m" (var));                       \
                 break;                                  \
         case 2:                                         \
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index e304b66abeea..624f133943ed 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -187,14 +187,15 @@ static inline int v8086_mode(struct pt_regs *regs)
 
 /*
  * X86_32 CPUs don't save ss and esp if the CPU is already in kernel mode
- * when it traps.  So regs will be the current sp.
+ * when it traps.  The previous stack will be directly underneath the saved
+ * registers, and 'sp/ss' won't even have been saved. Thus the '&regs->sp'.
  *
  * This is valid only for kernel mode traps.
  */
-static inline unsigned long kernel_trap_sp(struct pt_regs *regs)
+static inline unsigned long kernel_stack_pointer(struct pt_regs *regs)
 {
 #ifdef CONFIG_X86_32
-        return (unsigned long)regs;
+        return (unsigned long)(&regs->sp);
 #else
         return regs->sp;
 #endif
diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
index e5e6caffec87..b7e5db876399 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -172,7 +172,7 @@ static inline int __ticket_spin_is_contended(raw_spinlock_t *lock)
         return (((tmp >> TICKET_SHIFT) - tmp) & ((1 << TICKET_SHIFT) - 1)) > 1;
 }
 
-#ifndef CONFIG_PARAVIRT
+#ifndef CONFIG_PARAVIRT_SPINLOCKS
 
 static inline int __raw_spin_is_locked(raw_spinlock_t *lock)
 {
@@ -206,7 +206,7 @@ static __always_inline void __raw_spin_lock_flags(raw_spinlock_t *lock,
         __raw_spin_lock(lock);
 }
 
-#endif
+#endif  /* CONFIG_PARAVIRT_SPINLOCKS */
 
 static inline void __raw_spin_unlock_wait(raw_spinlock_t *lock)
 {
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 145cce75cda7..88d1bfc847d3 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -89,7 +89,8 @@ obj-$(CONFIG_DEBUG_NX_TEST)	+= test_nx.o
 obj-$(CONFIG_VMI)               += vmi_32.o vmiclock_32.o
 obj-$(CONFIG_KVM_GUEST)         += kvm.o
 obj-$(CONFIG_KVM_CLOCK)         += kvmclock.o
-obj-$(CONFIG_PARAVIRT)          += paravirt.o paravirt_patch_$(BITS).o paravirt-spinlocks.o
+obj-$(CONFIG_PARAVIRT)          += paravirt.o paravirt_patch_$(BITS).o
+obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= paravirt-spinlocks.o
 obj-$(CONFIG_PARAVIRT_CLOCK)    += pvclock.o
 
 obj-$(CONFIG_PCSPKR_PLATFORM)   += pcspeaker.o
diff --git a/arch/x86/kernel/apic/es7000_32.c b/arch/x86/kernel/apic/es7000_32.c
index 1c11b819f245..302947775575 100644
--- a/arch/x86/kernel/apic/es7000_32.c
+++ b/arch/x86/kernel/apic/es7000_32.c
@@ -254,7 +254,7 @@ static int parse_unisys_oem(char *oemptr)
 }
 
 #ifdef CONFIG_ACPI
-static int find_unisys_acpi_oem_table(unsigned long *oem_addr)
+static int __init find_unisys_acpi_oem_table(unsigned long *oem_addr)
 {
         struct acpi_table_header *header = NULL;
         struct es7000_oem_table *table;
@@ -285,7 +285,7 @@ static int find_unisys_acpi_oem_table(unsigned long *oem_addr)
         return 0;
 }
 
-static void unmap_unisys_acpi_oem_table(unsigned long oem_addr)
+static void __init unmap_unisys_acpi_oem_table(unsigned long oem_addr)
 {
         if (!oem_addr)
                 return;
@@ -306,7 +306,7 @@ static int es7000_check_dsdt(void)
 static int es7000_acpi_ret;
 
 /* Hook from generic ACPI tables.c */
-static int es7000_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
+static int __init es7000_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 {
         unsigned long oem_addr = 0;
         int check_dsdt;
@@ -717,7 +717,7 @@ struct apic apic_es7000_cluster = {
         .safe_wait_icr_idle             = native_safe_apic_wait_icr_idle,
 };
 
-struct apic apic_es7000 = {
+struct apic __refdata apic_es7000 = {
 
         .name                           = "es7000",
         .probe                          = probe_es7000,
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 0b776c09aff3..d21d4fb161f7 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -275,7 +275,11 @@ static void __init print_mtrr_state(void)
         }
         printk(KERN_DEBUG "MTRR variable ranges %sabled:\n",
                mtrr_state.enabled & 2 ? "en" : "dis");
-        high_width = ((size_or_mask ? ffs(size_or_mask) - 1 : 32) - (32 - PAGE_SHIFT) + 3) / 4;
+        if (size_or_mask & 0xffffffffUL)
+                high_width = ffs(size_or_mask & 0xffffffffUL) - 1;
+        else
+                high_width = ffs(size_or_mask>>32) + 32 - 1;
+        high_width = (high_width - (32 - PAGE_SHIFT) + 3) / 4;
         for (i = 0; i < num_var_ranges; ++i) {
                 if (mtrr_state.var_ranges[i].mask_lo & (1 << 11))
                         printk(KERN_DEBUG "  %u base %0*X%05X000 mask %0*X%05X000 %s\n",
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 8e45f4464880..9faf43bea336 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -134,7 +134,9 @@ static void *get_call_destination(u8 type)
                 .pv_irq_ops = pv_irq_ops,
                 .pv_apic_ops = pv_apic_ops,
                 .pv_mmu_ops = pv_mmu_ops,
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
                 .pv_lock_ops = pv_lock_ops,
+#endif
         };
         return *((void **)&tmpl + type);
 }
diff --git a/arch/x86/oprofile/backtrace.c b/arch/x86/oprofile/backtrace.c
index 04df67f8a7ba..044897be021f 100644
--- a/arch/x86/oprofile/backtrace.c
+++ b/arch/x86/oprofile/backtrace.c
@@ -76,9 +76,9 @@ void
 x86_backtrace(struct pt_regs * const regs, unsigned int depth)
 {
         struct frame_head *head = (struct frame_head *)frame_pointer(regs);
-        unsigned long stack = kernel_trap_sp(regs);
 
         if (!user_mode_vm(regs)) {
+                unsigned long stack = kernel_stack_pointer(regs);
                 if (depth)
                         dump_trace(NULL, regs, (unsigned long *)stack, 0,
                                    &backtrace_ops, &depth);
diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile
index 3b767d03fd6a..172438f86a02 100644
--- a/arch/x86/xen/Makefile
+++ b/arch/x86/xen/Makefile
@@ -9,5 +9,6 @@ obj-y		:= enlighten.o setup.o multicalls.o mmu.o irq.o \
                         time.o xen-asm.o xen-asm_$(BITS).o \
                         grant-table.o suspend.o
 
-obj-$(CONFIG_SMP)               += smp.o spinlock.o
-obj-$(CONFIG_XEN_DEBUG_FS)      += debugfs.o
\ No newline at end of file
+obj-$(CONFIG_SMP)               += smp.o
+obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= spinlock.o
+obj-$(CONFIG_XEN_DEBUG_FS)      += debugfs.o
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index e25a78e1113a..fba55b1a4021 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -42,6 +42,7 @@
 #include <linux/highmem.h>
 #include <linux/debugfs.h>
 #include <linux/bug.h>
+#include <linux/module.h>
 
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 20139464943c..ca6596b05d53 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -62,15 +62,26 @@ void xen_setup_vcpu_info_placement(void);
 #ifdef CONFIG_SMP
 void xen_smp_init(void);
 
-void __init xen_init_spinlocks(void);
-__cpuinit void xen_init_lock_cpu(int cpu);
-void xen_uninit_lock_cpu(int cpu);
-
 extern cpumask_var_t xen_cpu_initialized_map;
 #else
 static inline void xen_smp_init(void) {}
 #endif
 
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+void __init xen_init_spinlocks(void);
+__cpuinit void xen_init_lock_cpu(int cpu);
+void xen_uninit_lock_cpu(int cpu);
+#else
+static inline void xen_init_spinlocks(void)
+{
+}
+static inline void xen_init_lock_cpu(int cpu)
+{
+}
+static inline void xen_uninit_lock_cpu(int cpu)
+{
+}
+#endif
 
 /* Declare an asm function, along with symbols needed to make it
    inlineable */