Merge branch 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  x86: Use .cfi_sections for assembly code
  x86-64: Reduce SMP locks table size
  x86, asm: Introduce and use percpu_inc()

5 files changed, 41 insertions, 5 deletions

diff --git a/arch/x86/include/asm/alternative-asm.h b/arch/x86/include/asm/alternative-asm.h
index b97f786a48d5..a63a68be1cce 100644
--- a/arch/x86/include/asm/alternative-asm.h
+++ b/arch/x86/include/asm/alternative-asm.h
@@ -6,8 +6,8 @@
         .macro LOCK_PREFIX
 1:      lock
         .section .smp_locks,"a"
-        _ASM_ALIGN
-        _ASM_PTR 1b
+        .balign 4
+        .long 1b - .
         .previous
         .endm
 #else
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index b09ec55650b3..714bf2417284 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -30,8 +30,8 @@
 #ifdef CONFIG_SMP
 #define LOCK_PREFIX \
                 ".section .smp_locks,\"a\"\n"   \
-                _ASM_ALIGN "\n"                 \
-                _ASM_PTR "661f\n" /* address */ \
+                ".balign 4\n"                   \
+                ".long 661f - .\n" /* offset */ \
                 ".previous\n"                   \
                 "661:\n\tlock; "
 
diff --git a/arch/x86/include/asm/dwarf2.h b/arch/x86/include/asm/dwarf2.h
index ae6253ab9029..733f7e91e7a9 100644
--- a/arch/x86/include/asm/dwarf2.h
+++ b/arch/x86/include/asm/dwarf2.h
@@ -34,6 +34,18 @@
 #define CFI_SIGNAL_FRAME
 #endif
 
+#if defined(CONFIG_AS_CFI_SECTIONS) && defined(__ASSEMBLY__)
+        /*
+         * Emit CFI data in .debug_frame sections, not .eh_frame sections.
+         * The latter we currently just discard since we don't do DWARF
+         * unwinding at runtime.  So only the offline DWARF information is
+         * useful to anyone.  Note we should not use this directive if this
+         * file is used in the vDSO assembly, or if vmlinux.lds.S gets
+         * changed so it doesn't discard .eh_frame.
+         */
+        .cfi_sections .debug_frame
+#endif
+
 #else
 
 /*
diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index 0f8576427cfe..aeab29aee617 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -35,7 +35,7 @@ DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
 
 #define __ARCH_IRQ_STAT
 
-#define inc_irq_stat(member)    percpu_add(irq_stat.member, 1)
+#define inc_irq_stat(member)    percpu_inc(irq_stat.member)
 
 #define local_softirq_pending() percpu_read(irq_stat.__softirq_pending)
 
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 66a272dfd8b8..0ec6d12d84e6 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -190,6 +190,29 @@ do {									\
         pfo_ret__;                                      \
 })
 
+#define percpu_unary_op(op, var)                        \
+({                                                      \
+        switch (sizeof(var)) {                          \
+        case 1:                                         \
+                asm(op "b "__percpu_arg(0)              \
+                    : "+m" (var));                      \
+                break;                                  \
+        case 2:                                         \
+                asm(op "w "__percpu_arg(0)              \
+                    : "+m" (var));                      \
+                break;                                  \
+        case 4:                                         \
+                asm(op "l "__percpu_arg(0)              \
+                    : "+m" (var));                      \
+                break;                                  \
+        case 8:                                         \
+                asm(op "q "__percpu_arg(0)              \
+                    : "+m" (var));                      \
+                break;                                  \
+        default: __bad_percpu_size();                   \
+        }                                               \
+})
+
 /*
  * percpu_read() makes gcc load the percpu variable every time it is
  * accessed while percpu_read_stable() allows the value to be cached.
@@ -207,6 +230,7 @@ do {									\
 #define percpu_and(var, val)            percpu_to_op("and", var, val)
 #define percpu_or(var, val)             percpu_to_op("or", var, val)
 #define percpu_xor(var, val)            percpu_to_op("xor", var, val)
+#define percpu_inc(var)         percpu_unary_op("inc", var)
 
 #define __this_cpu_read_1(pcp)          percpu_from_op("mov", (pcp), "m"(pcp))
 #define __this_cpu_read_2(pcp)          percpu_from_op("mov", (pcp), "m"(pcp))