Merge branch 'x86-vdso-for-linus' of git://git.kernel.org/pub/scm/lin…

…ux/kernel/git/tip/tip

Pull x86 vdso changes from Peter Anvin:
 "This is the revamp of the 32-bit vdso and the associated cleanups.

  This adds timekeeping support to the 32-bit vdso that we already have
  in the 64-bit vdso.  Although 32-bit x86 is legacy, it is likely to
  remain in the embedded space for a very long time to come.

  This removes the traditional COMPAT_VDSO support; the configuration
  variable is reused for simply removing the 32-bit vdso, which will
  produce correct results but obviously suffer a performance penalty.
  Only one beta version of glibc was affected, but that version was
  unfortunately included in one OpenSUSE release.

  This is not the end of the vdso cleanups.  Stefani and Andy have
  agreed to continue work for the next kernel cycle; in fact Andy has
  already produced another set of cleanups that came too late for this
  cycle.

  An incidental, but arguably important, change is that this ensures
  that unused space in the VVAR page is properly zeroed.  It wasn't
  before, and would contain whatever garbage was left in memory by BIOS
  or the bootloader.  Since the VVAR page is accessible to user space
  this had the potential of information leaks"

* 'x86-vdso-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (23 commits)
  x86, vdso: Fix the symbol versions on the 32-bit vDSO
  x86, vdso, build: Don't rebuild 32-bit vdsos on every make
  x86, vdso: Actually discard the .discard sections
  x86, vdso: Fix size of get_unmapped_area()
  x86, vdso: Finish removing VDSO32_PRELINK
  x86, vdso: Move more vdso definitions into vdso.h
  x86: Load the 32-bit vdso in place, just like the 64-bit vdsos
  x86, vdso32: handle 32 bit vDSO larger one page
  x86, vdso32: Disable stack protector, adjust optimizations
  x86, vdso: Zero-pad the VVAR page
  x86, vdso: Add 32 bit VDSO time support for 64 bit kernel
  x86, vdso: Add 32 bit VDSO time support for 32 bit kernel
  x86, vdso: Patch alternatives in the 32-bit VDSO
  x86, vdso: Introduce VVAR marco for vdso32
  x86, vdso: Cleanup __vdso_gettimeofday()
  x86, vdso: Replace VVAR(vsyscall_gtod_data) by gtod macro
  x86, vdso: __vdso_clock_gettime() cleanup
  x86, vdso: Revamp vclock_gettime.c
  mm: Add new func _install_special_mapping() to mmap.c
  x86, vdso: Make vsyscall_gtod_data handling x86 generic
  ...

Documentation/kernel-parameters.txt

@@ -3424,14 +3424,24 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 					of CONFIG_HIGHPTE.
 
 	vdso=		[X86,SH]
-			vdso=2: enable compat VDSO (default with COMPAT_VDSO)
-			vdso=1: enable VDSO (default)
+			On X86_32, this is an alias for vdso32=.  Otherwise:
+
+			vdso=1: enable VDSO (the default)
 			vdso=0: disable VDSO mapping
 
-	vdso32=		[X86]
-			vdso32=2: enable compat VDSO (default with COMPAT_VDSO)
-			vdso32=1: enable 32-bit VDSO (default)
-			vdso32=0: disable 32-bit VDSO mapping
+	vdso32=		[X86] Control the 32-bit vDSO
+			vdso32=1: enable 32-bit VDSO
+			vdso32=0 or vdso32=2: disable 32-bit VDSO
+
+			See the help text for CONFIG_COMPAT_VDSO for more
+			details.  If CONFIG_COMPAT_VDSO is set, the default is
+			vdso32=0; otherwise, the default is vdso32=1.
+
+			For compatibility with older kernels, vdso32=2 is an
+			alias for vdso32=0.
+
+			Try vdso32=0 if you encounter an error that says:
+			dl_main: Assertion `(void *) ph->p_vaddr == _rtld_local._dl_sysinfo_dso' failed!
 
 	vector=		[IA-64,SMP]
 			vector=percpu: enable percpu vector domain

arch/x86/Kconfig

@@ -107,9 +107,9 @@ config X86
 	select HAVE_ARCH_SOFT_DIRTY
 	select CLOCKSOURCE_WATCHDOG
 	select GENERIC_CLOCKEVENTS
-	select ARCH_CLOCKSOURCE_DATA if X86_64
+	select ARCH_CLOCKSOURCE_DATA
 	select GENERIC_CLOCKEVENTS_BROADCAST if X86_64 || (X86_32 && X86_LOCAL_APIC)
-	select GENERIC_TIME_VSYSCALL if X86_64
+	select GENERIC_TIME_VSYSCALL
 	select KTIME_SCALAR if X86_32
 	select GENERIC_STRNCPY_FROM_USER
 	select GENERIC_STRNLEN_USER
@@ -1848,17 +1848,29 @@ config DEBUG_HOTPLUG_CPU0
 	  If unsure, say N.
 
 config COMPAT_VDSO
-	def_bool y
-	prompt "Compat VDSO support"
+	def_bool n
+	prompt "Disable the 32-bit vDSO (needed for glibc 2.3.3)"
 	depends on X86_32 || IA32_EMULATION
 	---help---
-	  Map the 32-bit VDSO to the predictable old-style address too.
+	  Certain buggy versions of glibc will crash if they are
+	  presented with a 32-bit vDSO that is not mapped at the address
+	  indicated in its segment table.
 
-	  Say N here if you are running a sufficiently recent glibc
-	  version (2.3.3 or later), to remove the high-mapped
-	  VDSO mapping and to exclusively use the randomized VDSO.
+	  The bug was introduced by f866314b89d56845f55e6f365e18b31ec978ec3a
+	  and fixed by 3b3ddb4f7db98ec9e912ccdf54d35df4aa30e04a and
+	  49ad572a70b8aeb91e57483a11dd1b77e31c4468.  Glibc 2.3.3 is
+	  the only released version with the bug, but OpenSUSE 9
+	  contains a buggy "glibc 2.3.2".
 
-	  If unsure, say Y.
+	  The symptom of the bug is that everything crashes on startup, saying:
+	  dl_main: Assertion `(void *) ph->p_vaddr == _rtld_local._dl_sysinfo_dso' failed!
+
+	  Saying Y here changes the default value of the vdso32 boot
+	  option from 1 to 0, which turns off the 32-bit vDSO entirely.
+	  This works around the glibc bug but hurts performance.
+
+	  If unsure, say N: if you are compiling your own kernel, you
+	  are unlikely to be using a buggy version of glibc.
 
 config CMDLINE_BOOL
 	bool "Built-in kernel command line"

arch/x86/include/asm/clocksource.h

@@ -3,8 +3,6 @@
 #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.	*/
@@ -14,6 +12,4 @@ struct arch_clocksource_data {
 	int vclock_mode;
 };
 
-#endif /* CONFIG_X86_64 */
-
 #endif /* _ASM_X86_CLOCKSOURCE_H */

arch/x86/include/asm/elf.h

@@ -281,16 +281,12 @@ do {									\
 
 #define STACK_RND_MASK (0x7ff)
 
-#define VDSO_HIGH_BASE		(__fix_to_virt(FIX_VDSO))
-
 #define ARCH_DLINFO		ARCH_DLINFO_IA32(vdso_enabled)
 
 /* update AT_VECTOR_SIZE_ARCH if the number of NEW_AUX_ENT entries changes */
 
 #else /* CONFIG_X86_32 */
 
-#define VDSO_HIGH_BASE		0xffffe000U /* CONFIG_COMPAT_VDSO address */
-
 /* 1GB for 64bit, 8MB for 32bit */
 #define STACK_RND_MASK (test_thread_flag(TIF_ADDR32) ? 0x7ff : 0x3fffff)
 

arch/x86/include/asm/fixmap.h

@@ -40,15 +40,8 @@
  */
 extern unsigned long __FIXADDR_TOP;
 #define FIXADDR_TOP	((unsigned long)__FIXADDR_TOP)
-
-#define FIXADDR_USER_START     __fix_to_virt(FIX_VDSO)
-#define FIXADDR_USER_END       __fix_to_virt(FIX_VDSO - 1)
 #else
 #define FIXADDR_TOP	(VSYSCALL_END-PAGE_SIZE)
-
-/* Only covers 32bit vsyscalls currently. Need another set for 64bit. */
-#define FIXADDR_USER_START	((unsigned long)VSYSCALL32_VSYSCALL)
-#define FIXADDR_USER_END	(FIXADDR_USER_START + PAGE_SIZE)
 #endif
 
 
@@ -74,7 +67,6 @@ extern unsigned long __FIXADDR_TOP;
 enum fixed_addresses {
 #ifdef CONFIG_X86_32
 	FIX_HOLE,
-	FIX_VDSO,
 #else
 	VSYSCALL_LAST_PAGE,
 	VSYSCALL_FIRST_PAGE = VSYSCALL_LAST_PAGE

arch/x86/include/asm/pgtable_types.h

@@ -214,13 +214,8 @@
 #ifdef CONFIG_X86_64
 #define __PAGE_KERNEL_IDENT_LARGE_EXEC	__PAGE_KERNEL_LARGE_EXEC
 #else
-/*
- * For PDE_IDENT_ATTR include USER bit. As the PDE and PTE protection
- * bits are combined, this will alow user to access the high address mapped
- * VDSO in the presence of CONFIG_COMPAT_VDSO
- */
 #define PTE_IDENT_ATTR	 0x003		/* PRESENT+RW */
-#define PDE_IDENT_ATTR	 0x067		/* PRESENT+RW+USER+DIRTY+ACCESSED */
+#define PDE_IDENT_ATTR	 0x063		/* PRESENT+RW+DIRTY+ACCESSED */
 #define PGD_IDENT_ATTR	 0x001		/* PRESENT (no other attributes) */
 #endif
 

arch/x86/include/asm/vdso.h

@@ -1,8 +1,45 @@
 #ifndef _ASM_X86_VDSO_H
 #define _ASM_X86_VDSO_H
 
+#include <asm/page_types.h>
+#include <linux/linkage.h>
+
+#ifdef __ASSEMBLER__
+
+#define DEFINE_VDSO_IMAGE(symname, filename)				\
+__PAGE_ALIGNED_DATA ;							\
+	.globl symname##_start, symname##_end ;				\
+	.align PAGE_SIZE ;						\
+	symname##_start: ;						\
+	.incbin filename ;						\
+	symname##_end: ;						\
+	.align PAGE_SIZE /* extra data here leaks to userspace. */ ;	\
+									\
+.previous ;								\
+									\
+	.globl symname##_pages ;					\
+	.bss ;								\
+	.align 8 ;							\
+	.type symname##_pages, @object ;				\
+	symname##_pages: ;						\
+	.zero (symname##_end - symname##_start + PAGE_SIZE - 1) / PAGE_SIZE * (BITS_PER_LONG / 8) ; \
+	.size symname##_pages, .-symname##_pages
+
+#else
+
+#define DECLARE_VDSO_IMAGE(symname)				\
+	extern char symname##_start[], symname##_end[];		\
+	extern struct page *symname##_pages[]
+
 #if defined CONFIG_X86_32 || defined CONFIG_COMPAT
-extern const char VDSO32_PRELINK[];
+
+#include <asm/vdso32.h>
+
+DECLARE_VDSO_IMAGE(vdso32_int80);
+#ifdef CONFIG_COMPAT
+DECLARE_VDSO_IMAGE(vdso32_syscall);
+#endif
+DECLARE_VDSO_IMAGE(vdso32_sysenter);
 
 /*
  * Given a pointer to the vDSO image, find the pointer to VDSO32_name
@@ -11,8 +48,7 @@ extern const char VDSO32_PRELINK[];
 #define VDSO32_SYMBOL(base, name)					\
 ({									\
 	extern const char VDSO32_##name[];				\
-	(void __user *)(VDSO32_##name - VDSO32_PRELINK +		\
-			(unsigned long)(base));				\
+	(void __user *)(VDSO32_##name + (unsigned long)(base));		\
 })
 #endif
 
@@ -23,12 +59,8 @@ extern const char VDSO32_PRELINK[];
 extern void __user __kernel_sigreturn;
 extern void __user __kernel_rt_sigreturn;
 
-/*
- * These symbols are defined by vdso32.S to mark the bounds
- * of the ELF DSO images included therein.
- */
-extern const char vdso32_int80_start, vdso32_int80_end;
-extern const char vdso32_syscall_start, vdso32_syscall_end;
-extern const char vdso32_sysenter_start, vdso32_sysenter_end;
+void __init patch_vdso32(void *vdso, size_t len);
+
+#endif /* __ASSEMBLER__ */
 
 #endif /* _ASM_X86_VDSO_H */

arch/x86/include/asm/vdso32.h

@@ -0,0 +1,11 @@
+#ifndef _ASM_X86_VDSO32_H
+#define _ASM_X86_VDSO32_H
+
+#define VDSO_BASE_PAGE	0
+#define VDSO_VVAR_PAGE	1
+#define VDSO_HPET_PAGE	2
+#define VDSO_PAGES	3
+#define VDSO_PREV_PAGES	2
+#define VDSO_OFFSET(x)	((x) * PAGE_SIZE)
+
+#endif

arch/x86/include/asm/vgtod.h

@@ -1,30 +1,73 @@
 #ifndef _ASM_X86_VGTOD_H
 #define _ASM_X86_VGTOD_H
 
-#include <asm/vsyscall.h>
+#include <linux/compiler.h>
 #include <linux/clocksource.h>
 
+#ifdef BUILD_VDSO32_64
+typedef u64 gtod_long_t;
+#else
+typedef unsigned long gtod_long_t;
+#endif
+/*
+ * vsyscall_gtod_data will be accessed by 32 and 64 bit code at the same time
+ * so be carefull by modifying this structure.
+ */
 struct vsyscall_gtod_data {
-	seqcount_t	seq;
+	unsigned seq;
 
-	struct { /* extract of a clocksource struct */
-		int vclock_mode;
-		cycle_t	cycle_last;
-		cycle_t	mask;
-		u32	mult;
-		u32	shift;
-	} clock;
+	int vclock_mode;
+	cycle_t	cycle_last;
+	cycle_t	mask;
+	u32	mult;
+	u32	shift;
 
 	/* open coded 'struct timespec' */
-	time_t		wall_time_sec;
 	u64		wall_time_snsec;
+	gtod_long_t	wall_time_sec;
+	gtod_long_t	monotonic_time_sec;
 	u64		monotonic_time_snsec;
-	time_t		monotonic_time_sec;
+	gtod_long_t	wall_time_coarse_sec;
+	gtod_long_t	wall_time_coarse_nsec;
+	gtod_long_t	monotonic_time_coarse_sec;
+	gtod_long_t	monotonic_time_coarse_nsec;
 
-	struct timezone sys_tz;
-	struct timespec wall_time_coarse;
-	struct timespec monotonic_time_coarse;
+	int		tz_minuteswest;
+	int		tz_dsttime;
 };
 extern struct vsyscall_gtod_data vsyscall_gtod_data;
 
+static inline unsigned gtod_read_begin(const struct vsyscall_gtod_data *s)
+{
+	unsigned ret;
+
+repeat:
+	ret = ACCESS_ONCE(s->seq);
+	if (unlikely(ret & 1)) {
+		cpu_relax();
+		goto repeat;
+	}
+	smp_rmb();
+	return ret;
+}
+
+static inline int gtod_read_retry(const struct vsyscall_gtod_data *s,
+					unsigned start)
+{
+	smp_rmb();
+	return unlikely(s->seq != start);
+}
+
+static inline void gtod_write_begin(struct vsyscall_gtod_data *s)
+{
+	++s->seq;
+	smp_wmb();
+}
+
+static inline void gtod_write_end(struct vsyscall_gtod_data *s)
+{
+	smp_wmb();
+	++s->seq;
+}
+
 #endif /* _ASM_X86_VGTOD_H */

arch/x86/include/asm/vvar.h

@@ -16,8 +16,8 @@
  * you mess up, the linker will catch it.)
  */
 
-/* Base address of vvars.  This is not ABI. */
-#define VVAR_ADDRESS (-10*1024*1024 - 4096)
+#ifndef _ASM_X86_VVAR_H
+#define _ASM_X86_VVAR_H
 
 #if defined(__VVAR_KERNEL_LDS)
 
@@ -29,16 +29,35 @@
 
 #else
 
+#ifdef BUILD_VDSO32
+
+#define DECLARE_VVAR(offset, type, name)				\
+	extern type vvar_ ## name __attribute__((visibility("hidden")));
+
+#define VVAR(name) (vvar_ ## name)
+
+#else
+
+extern char __vvar_page;
+
+/* Base address of vvars.  This is not ABI. */
+#ifdef CONFIG_X86_64
+#define VVAR_ADDRESS (-10*1024*1024 - 4096)
+#else
+#define VVAR_ADDRESS (&__vvar_page)
+#endif
+
 #define DECLARE_VVAR(offset, type, name)				\
 	static type const * const vvaraddr_ ## name =			\
 		(void *)(VVAR_ADDRESS + (offset));
 
+#define VVAR(name) (*vvaraddr_ ## name)
+#endif
+
 #define DEFINE_VVAR(type, name)						\
 	type name							\
 	__attribute__((section(".vvar_" #name), aligned(16))) __visible
 
-#define VVAR(name) (*vvaraddr_ ## name)
-
 #endif
 
 /* DECLARE_VVAR(offset, type, name) */
@@ -48,3 +67,5 @@ DECLARE_VVAR(16, int, vgetcpu_mode)
 DECLARE_VVAR(128, struct vsyscall_gtod_data, vsyscall_gtod_data)
 
 #undef DECLARE_VVAR
+
+#endif

arch/x86/kernel/Makefile

@@ -26,7 +26,7 @@ obj-$(CONFIG_IRQ_WORK)  += irq_work.o
 obj-y			+= probe_roms.o
 obj-$(CONFIG_X86_32)	+= i386_ksyms_32.o
 obj-$(CONFIG_X86_64)	+= sys_x86_64.o x8664_ksyms_64.o
-obj-y			+= syscall_$(BITS).o
+obj-y			+= syscall_$(BITS).o vsyscall_gtod.o
 obj-$(CONFIG_X86_64)	+= vsyscall_64.o
 obj-$(CONFIG_X86_64)	+= vsyscall_emu_64.o
 obj-$(CONFIG_SYSFS)	+= ksysfs.o

arch/x86/kernel/hpet.c

@@ -752,9 +752,7 @@ static struct clocksource clocksource_hpet = {
 	.mask		= HPET_MASK,
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 	.resume		= hpet_resume_counter,
-#ifdef CONFIG_X86_64
 	.archdata	= { .vclock_mode = VCLOCK_HPET },
-#endif
 };
 
 static int hpet_clocksource_register(void)