9 files changed, 37 insertions, 8 deletions

diff --git a/include/asm-x86_64/cache.h b/include/asm-x86_64/cache.h
index c8043a16152e..f8dff1c67538 100644
--- a/include/asm-x86_64/cache.h
+++ b/include/asm-x86_64/cache.h
@@ -20,8 +20,8 @@
        __attribute__((__section__(".data.page_aligned")))
 #endif
 
-#define __read_mostly __attribute__((__section__(".data.read_mostly")))
-
 #endif
 
+#define __read_mostly __attribute__((__section__(".data.read_mostly")))
+
 #endif
diff --git a/include/asm-x86_64/cpufeature.h b/include/asm-x86_64/cpufeature.h
index 76bb6193ae91..662964b74e34 100644
--- a/include/asm-x86_64/cpufeature.h
+++ b/include/asm-x86_64/cpufeature.h
@@ -64,6 +64,7 @@
 #define X86_FEATURE_REP_GOOD    (3*32+ 4) /* rep microcode works well on this CPU */
 #define X86_FEATURE_CONSTANT_TSC (3*32+5) /* TSC runs at constant rate */
 #define X86_FEATURE_SYNC_RDTSC  (3*32+6)  /* RDTSC syncs CPU core */
+#define X86_FEATURE_FXSAVE_LEAK (3*32+7)  /* FIP/FOP/FDP leaks through FXSAVE */
 
 /* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
 #define X86_FEATURE_XMM3        (4*32+ 0) /* Streaming SIMD Extensions-3 */
diff --git a/include/asm-x86_64/e820.h b/include/asm-x86_64/e820.h
index 93b51df51687..670a3388e70a 100644
--- a/include/asm-x86_64/e820.h
+++ b/include/asm-x86_64/e820.h
@@ -59,6 +59,8 @@ extern void __init parse_memopt(char *p, char **end);
 extern void __init parse_memmapopt(char *p, char **end);
 
 extern struct e820map e820;
+
+extern unsigned ebda_addr, ebda_size;
 #endif/*!__ASSEMBLY__*/
 
 #endif/*__E820_HEADER*/
diff --git a/include/asm-x86_64/elf.h b/include/asm-x86_64/elf.h
index c98633af07d2..b4f8f4a41a6e 100644
--- a/include/asm-x86_64/elf.h
+++ b/include/asm-x86_64/elf.h
@@ -159,7 +159,7 @@ extern int dump_task_fpu (struct task_struct *, elf_fpregset_t *);
 #define ELF_CORE_COPY_FPREGS(tsk, elf_fpregs) dump_task_fpu(tsk, elf_fpregs)
 
 /* 1GB for 64bit, 8MB for 32bit */
-#define STACK_RND_MASK (is_compat_task() ? 0x7ff : 0x3fffff)
+#define STACK_RND_MASK (test_thread_flag(TIF_IA32) ? 0x7ff : 0x3fffff)
 
 #endif
 
diff --git a/include/asm-x86_64/i387.h b/include/asm-x86_64/i387.h
index 876eb9a2fe78..cba8a3b0cded 100644
--- a/include/asm-x86_64/i387.h
+++ b/include/asm-x86_64/i387.h
@@ -72,6 +72,23 @@ extern int set_fpregs(struct task_struct *tsk,
 #define set_fpu_swd(t,val) ((t)->thread.i387.fxsave.swd = (val))
 #define set_fpu_fxsr_twd(t,val) ((t)->thread.i387.fxsave.twd = (val))
 
+#define X87_FSW_ES (1 << 7)     /* Exception Summary */
+
+/* AMD CPUs don't save/restore FDP/FIP/FOP unless an exception
+   is pending. Clear the x87 state here by setting it to fixed
+   values. The kernel data segment can be sometimes 0 and sometimes
+   new user value. Both should be ok.
+   Use the PDA as safe address because it should be already in L1. */
+static inline void clear_fpu_state(struct i387_fxsave_struct *fx)
+{
+        if (unlikely(fx->swd & X87_FSW_ES))
+                 asm volatile("fnclex");
+        alternative_input(ASM_NOP8 ASM_NOP2,
+                     "    emms\n"               /* clear stack tags */
+                     "    fildl %%gs:0",        /* load to clear state */
+                     X86_FEATURE_FXSAVE_LEAK);
+}
+
 static inline int restore_fpu_checking(struct i387_fxsave_struct *fx) 
 { 
         int err;
@@ -119,6 +136,7 @@ static inline int save_i387_checking(struct i387_fxsave_struct __user *fx)
 #endif
         if (unlikely(err))
                 __clear_user(fx, sizeof(struct i387_fxsave_struct));
+        /* No need to clear here because the caller clears USED_MATH */
         return err;
 } 
 
@@ -149,7 +167,7 @@ static inline void __fxsave_clear(struct task_struct *tsk)
                                 "i" (offsetof(__typeof__(*tsk),
                                               thread.i387.fxsave)));
 #endif
-        __asm__ __volatile__("fnclex");
+        clear_fpu_state(&tsk->thread.i387.fxsave);
 }
 
 static inline void kernel_fpu_begin(void)
diff --git a/include/asm-x86_64/io_apic.h b/include/asm-x86_64/io_apic.h
index ee1bc69aec9c..52484e82c641 100644
--- a/include/asm-x86_64/io_apic.h
+++ b/include/asm-x86_64/io_apic.h
@@ -205,6 +205,7 @@ extern int skip_ioapic_setup;
 extern int io_apic_get_version (int ioapic);
 extern int io_apic_get_redir_entries (int ioapic);
 extern int io_apic_set_pci_routing (int ioapic, int pin, int irq, int, int);
+extern int timer_uses_ioapic_pin_0;
 #endif
 
 extern int sis_apic_bug; /* dummy */ 
diff --git a/include/asm-x86_64/mmzone.h b/include/asm-x86_64/mmzone.h
index 6b18cd8f293d..6944e7122df5 100644
--- a/include/asm-x86_64/mmzone.h
+++ b/include/asm-x86_64/mmzone.h
@@ -12,7 +12,8 @@
 
 #include <asm/smp.h>
 
-#define NODEMAPSIZE 0xfff
+/* Should really switch to dynamic allocation at some point */
+#define NODEMAPSIZE 0x4fff
 
 /* Simple perfect hash to map physical addresses to node numbers */
 struct memnode {
diff --git a/include/asm-x86_64/percpu.h b/include/asm-x86_64/percpu.h
index 4405b4adeaba..7f33aaf9f7b1 100644
--- a/include/asm-x86_64/percpu.h
+++ b/include/asm-x86_64/percpu.h
@@ -26,7 +26,7 @@
 #define percpu_modcopy(pcpudst, src, size)                      \
 do {                                                            \
         unsigned int __i;                                       \
-        for_each_cpu(__i)                                       \
+        for_each_possible_cpu(__i)                              \
                 memcpy((pcpudst)+__per_cpu_offset(__i),         \
                        (src), (size));                          \
 } while (0)
diff --git a/include/asm-x86_64/unistd.h b/include/asm-x86_64/unistd.h
index f21ff2c1e960..feb77cb8c044 100644
--- a/include/asm-x86_64/unistd.h
+++ b/include/asm-x86_64/unistd.h
@@ -611,8 +611,14 @@ __SYSCALL(__NR_set_robust_list, sys_set_robust_list)
 __SYSCALL(__NR_get_robust_list, sys_get_robust_list)
 #define __NR_splice             275
 __SYSCALL(__NR_splice, sys_splice)
-
-#define __NR_syscall_max __NR_splice
+#define __NR_tee                276
+__SYSCALL(__NR_tee, sys_tee)
+#define __NR_sync_file_range    277
+__SYSCALL(__NR_sync_file_range, sys_sync_file_range)
+#define __NR_vmsplice           278
+__SYSCALL(__NR_vmsplice, sys_vmsplice)
+
+#define __NR_syscall_max __NR_vmsplice
 
 #ifndef __NO_STUBS