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

* 'x86-vdso-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  x86-64, vdso: Do not allocate memory for the vDSO
  clocksource: Change __ARCH_HAS_CLOCKSOURCE_DATA to a CONFIG option
  x86, vdso: Drop now wrong comment
  Document the vDSO and add a reference parser
  ia64: Replace clocksource.fsys_mmio with generic arch data
  x86-64: Move vread_tsc and vread_hpet into the vDSO
  clocksource: Replace vread with generic arch data
  x86-64: Add --no-undefined to vDSO build
  x86-64: Allow alternative patching in the vDSO
  x86: Make alternative instruction pointers relative
  x86-64: Improve vsyscall emulation CS and RIP handling
  x86-64: Emulate legacy vsyscalls
  x86-64: Fill unused parts of the vsyscall page with 0xcc
  x86-64: Remove vsyscall number 3 (venosys)
  x86-64: Map the HPET NX
  x86-64: Remove kernel.vsyscall64 sysctl
  x86-64: Give vvars their own page
  x86-64: Document some of entry_64.S
  x86-64: Fix alignment of jiffies variable

12 files changed, 54 insertions, 36 deletions

diff --git a/arch/x86/include/asm/alternative-asm.h b/arch/x86/include/asm/alternative-asm.h
index 94d420b360d1..4554cc6fb96a 100644
--- a/arch/x86/include/asm/alternative-asm.h
+++ b/arch/x86/include/asm/alternative-asm.h
@@ -17,8 +17,8 @@
 
 .macro altinstruction_entry orig alt feature orig_len alt_len
 	.align 8
-	.quad \orig
-	.quad \alt
+	.long \orig - .
+	.long \alt - .
 	.word \feature
 	.byte \orig_len
 	.byte \alt_len
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index bf535f947e8c..23fb6d79f209 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -43,8 +43,8 @@
 #endif
 
 struct alt_instr {
-	u8 *instr;		/* original instruction */
-	u8 *replacement;
+	s32 instr_offset;	/* original instruction */
+	s32 repl_offset;	/* offset to replacement instruction */
 	u16 cpuid;		/* cpuid bit set for replacement */
 	u8  instrlen;		/* length of original instruction */
 	u8  replacementlen;	/* length of new instruction, <= instrlen */
@@ -84,8 +84,8 @@ static inline int alternatives_text_reserved(void *start, void *end)
       "661:\n\t" oldinstr "\n662:\n"					\
       ".section .altinstructions,\"a\"\n"				\
       _ASM_ALIGN "\n"							\
-      _ASM_PTR "661b\n"				/* label           */	\
-      _ASM_PTR "663f\n"				/* new instruction */	\
+      "	 .long 661b - .\n"			/* label           */	\
+      "	 .long 663f - .\n"			/* new instruction */	\
       "	 .word " __stringify(feature) "\n"	/* feature bit     */	\
       "	 .byte 662b-661b\n"			/* sourcelen       */	\
       "	 .byte 664f-663f\n"			/* replacementlen  */	\
diff --git a/arch/x86/include/asm/clocksource.h b/arch/x86/include/asm/clocksource.h
new file mode 100644
index 000000000000..0bdbbb3b9ce7
--- /dev/null
+++ b/arch/x86/include/asm/clocksource.h
@@ -0,0 +1,18 @@
+/* x86-specific clocksource additions */
+
+#ifndef _ASM_X86_CLOCKSOURCE_H
+#define _ASM_X86_CLOCKSOURCE_H
+
+#ifdef CONFIG_X86_64
+
+#define VCLOCK_NONE 0  /* No vDSO clock available.	*/
+#define VCLOCK_TSC  1  /* vDSO should use vread_tsc.	*/
+#define VCLOCK_HPET 2  /* vDSO should use vread_hpet.	*/
+
+struct arch_clocksource_data {
+	int vclock_mode;
+};
+
+#endif /* CONFIG_X86_64 */
+
+#endif /* _ASM_X86_CLOCKSOURCE_H */
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 71cc3800712c..9929b35929ff 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -331,8 +331,8 @@ static __always_inline __pure bool __static_cpu_has(u16 bit)
 			 "2:\n"
 			 ".section .altinstructions,\"a\"\n"
 			 _ASM_ALIGN "\n"
-			 _ASM_PTR "1b\n"
-			 _ASM_PTR "0\n" 	/* no replacement */
+			 " .long 1b - .\n"
+			 " .long 0\n"		/* no replacement */
 			 " .word %P0\n"		/* feature bit */
 			 " .byte 2b - 1b\n"	/* source len */
 			 " .byte 0\n"		/* replacement len */
@@ -349,8 +349,8 @@ static __always_inline __pure bool __static_cpu_has(u16 bit)
 			     "2:\n"
 			     ".section .altinstructions,\"a\"\n"
 			     _ASM_ALIGN "\n"
-			     _ASM_PTR "1b\n"
-			     _ASM_PTR "3f\n"
+			     " .long 1b - .\n"
+			     " .long 3f - .\n"
 			     " .word %P1\n"		/* feature bit */
 			     " .byte 2b - 1b\n"		/* source len */
 			     " .byte 4f - 3f\n"		/* replacement len */
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index 4729b2b63117..460c74e4852c 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -78,6 +78,7 @@ enum fixed_addresses {
 	VSYSCALL_LAST_PAGE,
 	VSYSCALL_FIRST_PAGE = VSYSCALL_LAST_PAGE
 			    + ((VSYSCALL_END-VSYSCALL_START) >> PAGE_SHIFT) - 1,
+	VVAR_PAGE,
 	VSYSCALL_HPET,
 #endif
 	FIX_DBGP_BASE,
diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index 6665026ea3ea..f9a320984a10 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -17,7 +17,8 @@
  *  Vectors   0 ...  31 : system traps and exceptions - hardcoded events
  *  Vectors  32 ... 127 : device interrupts
  *  Vector  128         : legacy int80 syscall interface
- *  Vectors 129 ... INVALIDATE_TLB_VECTOR_START-1 : device interrupts
+ *  Vector  204         : legacy x86_64 vsyscall emulation
+ *  Vectors 129 ... INVALIDATE_TLB_VECTOR_START-1 except 204 : device interrupts
  *  Vectors INVALIDATE_TLB_VECTOR_START ... 255 : special interrupts
  *
  * 64-bit x86 has per CPU IDT tables, 32-bit has one shared IDT table.
@@ -50,6 +51,9 @@
 #ifdef CONFIG_X86_32
 # define SYSCALL_VECTOR			0x80
 #endif
+#ifdef CONFIG_X86_64
+# define VSYSCALL_EMU_VECTOR		0xcc
+#endif
 
 /*
  * Vectors 0x30-0x3f are used for ISA interrupts.
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index d56187c6b838..013286a10c2c 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -107,7 +107,8 @@
 #define __PAGE_KERNEL_NOCACHE		(__PAGE_KERNEL | _PAGE_PCD | _PAGE_PWT)
 #define __PAGE_KERNEL_UC_MINUS		(__PAGE_KERNEL | _PAGE_PCD)
 #define __PAGE_KERNEL_VSYSCALL		(__PAGE_KERNEL_RX | _PAGE_USER)
-#define __PAGE_KERNEL_VSYSCALL_NOCACHE	(__PAGE_KERNEL_VSYSCALL | _PAGE_PCD | _PAGE_PWT)
+#define __PAGE_KERNEL_VVAR		(__PAGE_KERNEL_RO | _PAGE_USER)
+#define __PAGE_KERNEL_VVAR_NOCACHE	(__PAGE_KERNEL_VVAR | _PAGE_PCD | _PAGE_PWT)
 #define __PAGE_KERNEL_LARGE		(__PAGE_KERNEL | _PAGE_PSE)
 #define __PAGE_KERNEL_LARGE_NOCACHE	(__PAGE_KERNEL | _PAGE_CACHE_UC | _PAGE_PSE)
 #define __PAGE_KERNEL_LARGE_EXEC	(__PAGE_KERNEL_EXEC | _PAGE_PSE)
@@ -129,7 +130,8 @@
 #define PAGE_KERNEL_LARGE_NOCACHE	__pgprot(__PAGE_KERNEL_LARGE_NOCACHE)
 #define PAGE_KERNEL_LARGE_EXEC		__pgprot(__PAGE_KERNEL_LARGE_EXEC)
 #define PAGE_KERNEL_VSYSCALL		__pgprot(__PAGE_KERNEL_VSYSCALL)
-#define PAGE_KERNEL_VSYSCALL_NOCACHE	__pgprot(__PAGE_KERNEL_VSYSCALL_NOCACHE)
+#define PAGE_KERNEL_VVAR		__pgprot(__PAGE_KERNEL_VVAR)
+#define PAGE_KERNEL_VVAR_NOCACHE	__pgprot(__PAGE_KERNEL_VVAR_NOCACHE)
 
 #define PAGE_KERNEL_IO			__pgprot(__PAGE_KERNEL_IO)
 #define PAGE_KERNEL_IO_NOCACHE		__pgprot(__PAGE_KERNEL_IO_NOCACHE)
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index 0310da67307f..2bae0a513b40 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -1,6 +1,8 @@
 #ifndef _ASM_X86_TRAPS_H
 #define _ASM_X86_TRAPS_H
 
+#include <linux/kprobes.h>
+
 #include <asm/debugreg.h>
 #include <asm/siginfo.h>			/* TRAP_TRACE, ... */
 
@@ -38,6 +40,7 @@ asmlinkage void alignment_check(void);
 asmlinkage void machine_check(void);
 #endif /* CONFIG_X86_MCE */
 asmlinkage void simd_coprocessor_error(void);
+asmlinkage void emulate_vsyscall(void);
 
 dotraplinkage void do_divide_error(struct pt_regs *, long);
 dotraplinkage void do_debug(struct pt_regs *, long);
@@ -64,6 +67,7 @@ dotraplinkage void do_alignment_check(struct pt_regs *, long);
 dotraplinkage void do_machine_check(struct pt_regs *, long);
 #endif
 dotraplinkage void do_simd_coprocessor_error(struct pt_regs *, long);
+dotraplinkage void do_emulate_vsyscall(struct pt_regs *, long);
 #ifdef CONFIG_X86_32
 dotraplinkage void do_iret_error(struct pt_regs *, long);
 #endif
diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h
index 9db5583b6d38..83e2efd181e2 100644
--- a/arch/x86/include/asm/tsc.h
+++ b/arch/x86/include/asm/tsc.h
@@ -51,10 +51,6 @@ extern int unsynchronized_tsc(void);
 extern int check_tsc_unstable(void);
 extern unsigned long native_calibrate_tsc(void);
 
-#ifdef CONFIG_X86_64
-extern cycles_t vread_tsc(void);
-#endif
-
 /*
  * Boot-time check whether the TSCs are synchronized across
  * all CPUs/cores:
diff --git a/arch/x86/include/asm/vgtod.h b/arch/x86/include/asm/vgtod.h
index 646b4c1ca695..815285bcaceb 100644
--- a/arch/x86/include/asm/vgtod.h
+++ b/arch/x86/include/asm/vgtod.h
@@ -11,10 +11,9 @@ struct vsyscall_gtod_data {
 	time_t		wall_time_sec;
 	u32		wall_time_nsec;
 
-	int		sysctl_enabled;
 	struct timezone sys_tz;
 	struct { /* extract of a clocksource struct */
-		cycle_t (*vread)(void);
+		int vclock_mode;
 		cycle_t	cycle_last;
 		cycle_t	mask;
 		u32	mult;
diff --git a/arch/x86/include/asm/vsyscall.h b/arch/x86/include/asm/vsyscall.h
index d55597351f6a..60107072c28b 100644
--- a/arch/x86/include/asm/vsyscall.h
+++ b/arch/x86/include/asm/vsyscall.h
@@ -16,10 +16,6 @@ enum vsyscall_num {
 #ifdef __KERNEL__
 #include <linux/seqlock.h>
 
-/* Definitions for CONFIG_GENERIC_TIME definitions */
-#define __vsyscall_fn \
-	__attribute__ ((unused, __section__(".vsyscall_fn"))) notrace
-
 #define VGETCPU_RDTSCP	1
 #define VGETCPU_LSL	2
 
diff --git a/arch/x86/include/asm/vvar.h b/arch/x86/include/asm/vvar.h
index 341b3559452b..de656ac2af41 100644
--- a/arch/x86/include/asm/vvar.h
+++ b/arch/x86/include/asm/vvar.h
@@ -10,15 +10,14 @@
  * In normal kernel code, they are used like any other variable.
  * In user code, they are accessed through the VVAR macro.
  *
- * Each of these variables lives in the vsyscall page, and each
- * one needs a unique offset within the little piece of the page
- * reserved for vvars.  Specify that offset in DECLARE_VVAR.
- * (There are 896 bytes available.  If you mess up, the linker will
- * catch it.)
+ * These variables live in a page of kernel data that has an extra RO
+ * mapping for userspace.  Each variable needs a unique offset within
+ * that page; specify that offset with the DECLARE_VVAR macro.  (If
+ * you mess up, the linker will catch it.)
  */
 
-/* Offset of vars within vsyscall page */
-#define VSYSCALL_VARS_OFFSET (3072 + 128)
+/* Base address of vvars.  This is not ABI. */
+#define VVAR_ADDRESS (-10*1024*1024 - 4096)
 
 #if defined(__VVAR_KERNEL_LDS)
 
@@ -26,17 +25,17 @@
  * right place.
  */
 #define DECLARE_VVAR(offset, type, name) \
-	EMIT_VVAR(name, VSYSCALL_VARS_OFFSET + offset)
+	EMIT_VVAR(name, offset)
 
 #else
 
 #define DECLARE_VVAR(offset, type, name)				\
 	static type const * const vvaraddr_ ## name =			\
-		(void *)(VSYSCALL_START + VSYSCALL_VARS_OFFSET + (offset));
+		(void *)(VVAR_ADDRESS + (offset));
 
 #define DEFINE_VVAR(type, name)						\
-	type __vvar_ ## name						\
-	__attribute__((section(".vsyscall_var_" #name), aligned(16)))
+	type name							\
+	__attribute__((section(".vvar_" #name), aligned(16)))
 
 #define VVAR(name) (*vvaraddr_ ## name)
 
@@ -45,8 +44,7 @@
 /* DECLARE_VVAR(offset, type, name) */
 
 DECLARE_VVAR(0, volatile unsigned long, jiffies)
-DECLARE_VVAR(8, int, vgetcpu_mode)
+DECLARE_VVAR(16, int, vgetcpu_mode)
 DECLARE_VVAR(128, struct vsyscall_gtod_data, vsyscall_gtod_data)
 
 #undef DECLARE_VVAR
-#undef VSYSCALL_VARS_OFFSET