add idl4k kernel firmware version 1.13.0.105

kernel/arch/x86/vdso/.gitignore

@@ -0,0 +1,6 @@
+vdso.lds
+vdso-syms.lds
+vdso32-syms.lds
+vdso32-syscall-syms.lds
+vdso32-sysenter-syms.lds
+vdso32-int80-syms.lds

kernel/arch/x86/vdso/Makefile

@@ -0,0 +1,140 @@
+#
+# Building vDSO images for x86.
+#
+
+VDSO64-$(CONFIG_X86_64)		:= y
+VDSO32-$(CONFIG_X86_32)		:= y
+VDSO32-$(CONFIG_COMPAT)		:= y
+
+vdso-install-$(VDSO64-y)	+= vdso.so
+vdso-install-$(VDSO32-y)	+= $(vdso32-images)
+
+
+# files to link into the vdso
+vobjs-y := vdso-note.o vclock_gettime.o vgetcpu.o vvar.o
+
+# files to link into kernel
+obj-$(VDSO64-y)			+= vma.o vdso.o
+obj-$(VDSO32-y)			+= vdso32.o vdso32-setup.o
+
+vobjs := $(foreach F,$(vobjs-y),$(obj)/$F)
+
+$(obj)/vdso.o: $(obj)/vdso.so
+
+targets += vdso.so vdso.so.dbg vdso.lds $(vobjs-y)
+
+export CPPFLAGS_vdso.lds += -P -C
+
+VDSO_LDFLAGS_vdso.lds = -m64 -Wl,-soname=linux-vdso.so.1 \
+		      	-Wl,-z,max-page-size=4096 -Wl,-z,common-page-size=4096
+
+$(obj)/vdso.o: $(src)/vdso.S $(obj)/vdso.so
+
+$(obj)/vdso.so.dbg: $(src)/vdso.lds $(vobjs) FORCE
+	$(call if_changed,vdso)
+
+$(obj)/%.so: OBJCOPYFLAGS := -S
+$(obj)/%.so: $(obj)/%.so.dbg FORCE
+	$(call if_changed,objcopy)
+
+CFL := $(PROFILING) -mcmodel=small -fPIC -O2 -fasynchronous-unwind-tables -m64 \
+       $(filter -g%,$(KBUILD_CFLAGS)) $(call cc-option, -fno-stack-protector)
+
+$(vobjs): KBUILD_CFLAGS += $(CFL)
+
+targets += vdso-syms.lds
+obj-$(VDSO64-y)			+= vdso-syms.lds
+
+#
+# Match symbols in the DSO that look like VDSO*; produce a file of constants.
+#
+sed-vdsosym := -e 's/^00*/0/' \
+	-e 's/^\([0-9a-fA-F]*\) . \(VDSO[a-zA-Z0-9_]*\)$$/\2 = 0x\1;/p'
+quiet_cmd_vdsosym = VDSOSYM $@
+define cmd_vdsosym
+	$(NM) $< | LC_ALL=C sed -n $(sed-vdsosym) | LC_ALL=C sort > $@
+endef
+
+$(obj)/%-syms.lds: $(obj)/%.so.dbg FORCE
+	$(call if_changed,vdsosym)
+
+#
+# Build multiple 32-bit vDSO images to choose from at boot time.
+#
+obj-$(VDSO32-y)			+= vdso32-syms.lds
+vdso32.so-$(VDSO32-y)		+= int80
+vdso32.so-$(CONFIG_COMPAT)	+= syscall
+vdso32.so-$(VDSO32-y)		+= sysenter
+
+vdso32-images			= $(vdso32.so-y:%=vdso32-%.so)
+
+CPPFLAGS_vdso32.lds = $(CPPFLAGS_vdso.lds)
+VDSO_LDFLAGS_vdso32.lds = -m32 -Wl,-soname=linux-gate.so.1
+
+# This makes sure the $(obj) subdirectory exists even though vdso32/
+# is not a kbuild sub-make subdirectory.
+override obj-dirs = $(dir $(obj)) $(obj)/vdso32/
+
+targets += vdso32/vdso32.lds
+targets += $(vdso32-images) $(vdso32-images:=.dbg)
+targets += vdso32/note.o $(vdso32.so-y:%=vdso32/%.o)
+
+extra-y	+= $(vdso32-images)
+
+$(obj)/vdso32.o: $(vdso32-images:%=$(obj)/%)
+
+KBUILD_AFLAGS_32 := $(filter-out -m64,$(KBUILD_AFLAGS))
+$(vdso32-images:%=$(obj)/%.dbg): KBUILD_AFLAGS = $(KBUILD_AFLAGS_32)
+$(vdso32-images:%=$(obj)/%.dbg): asflags-$(CONFIG_X86_64) += -m32
+
+$(vdso32-images:%=$(obj)/%.dbg): $(obj)/vdso32-%.so.dbg: FORCE \
+				 $(obj)/vdso32/vdso32.lds \
+				 $(obj)/vdso32/note.o \
+				 $(obj)/vdso32/%.o
+	$(call if_changed,vdso)
+
+# Make vdso32-*-syms.lds from each image, and then make sure they match.
+# The only difference should be that some do not define VDSO32_SYSENTER_RETURN.
+
+targets += vdso32-syms.lds $(vdso32.so-y:%=vdso32-%-syms.lds)
+
+quiet_cmd_vdso32sym = VDSOSYM $@
+define cmd_vdso32sym
+	if LC_ALL=C sort -u $(filter-out FORCE,$^) > $(@D)/.tmp_$(@F) && \
+	   $(foreach H,$(filter-out FORCE,$^),\
+		     if grep -q VDSO32_SYSENTER_RETURN $H; \
+		     then diff -u $(@D)/.tmp_$(@F) $H; \
+		     else sed /VDSO32_SYSENTER_RETURN/d $(@D)/.tmp_$(@F) | \
+			  diff -u - $H; fi &&) : ;\
+	then mv -f $(@D)/.tmp_$(@F) $@; \
+	else rm -f $(@D)/.tmp_$(@F); exit 1; \
+	fi
+endef
+
+$(obj)/vdso32-syms.lds: $(vdso32.so-y:%=$(obj)/vdso32-%-syms.lds) FORCE
+	$(call if_changed,vdso32sym)
+
+#
+# The DSO images are built using a special linker script.
+#
+quiet_cmd_vdso = VDSO    $@
+      cmd_vdso = $(CC) -nostdlib -o $@ \
+		       $(VDSO_LDFLAGS) $(VDSO_LDFLAGS_$(filter %.lds,$(^F))) \
+		       -Wl,-T,$(filter %.lds,$^) $(filter %.o,$^)
+
+VDSO_LDFLAGS = -fPIC -shared $(call cc-ldoption, -Wl$(comma)--hash-style=sysv)
+GCOV_PROFILE := n
+
+#
+# Install the unstripped copy of vdso*.so listed in $(vdso-install-y).
+#
+quiet_cmd_vdso_install = INSTALL $@
+      cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/$@
+$(vdso-install-y): %.so: $(obj)/%.so.dbg FORCE
+	@mkdir -p $(MODLIB)/vdso
+	$(call cmd,vdso_install)
+
+PHONY += vdso_install $(vdso-install-y)
+vdso_install: $(vdso-install-y)
+
+clean-files := vdso32-syscall* vdso32-sysenter* vdso32-int80*

kernel/arch/x86/vdso/vclock_gettime.c

@@ -0,0 +1,159 @@
+/*
+ * Copyright 2006 Andi Kleen, SUSE Labs.
+ * Subject to the GNU Public License, v.2
+ *
+ * Fast user context implementation of clock_gettime and gettimeofday.
+ *
+ * The code should have no internal unresolved relocations.
+ * Check with readelf after changing.
+ * Also alternative() doesn't work.
+ */
+
+/* Disable profiling for userspace code: */
+#define DISABLE_BRANCH_PROFILING
+
+#include <linux/kernel.h>
+#include <linux/posix-timers.h>
+#include <linux/time.h>
+#include <linux/string.h>
+#include <asm/vsyscall.h>
+#include <asm/vgtod.h>
+#include <asm/timex.h>
+#include <asm/hpet.h>
+#include <asm/unistd.h>
+#include <asm/io.h>
+#include "vextern.h"
+
+#define gtod vdso_vsyscall_gtod_data
+
+notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
+{
+	long ret;
+	asm("syscall" : "=a" (ret) :
+	    "0" (__NR_clock_gettime),"D" (clock), "S" (ts) : "memory");
+	return ret;
+}
+
+notrace static inline long vgetns(void)
+{
+	long v;
+	cycles_t (*vread)(void);
+	vread = gtod->clock.vread;
+	v = (vread() - gtod->clock.cycle_last) & gtod->clock.mask;
+	return (v * gtod->clock.mult) >> gtod->clock.shift;
+}
+
+notrace static noinline int do_realtime(struct timespec *ts)
+{
+	unsigned long seq, ns;
+	do {
+		seq = read_seqbegin(&gtod->lock);
+		ts->tv_sec = gtod->wall_time_sec;
+		ts->tv_nsec = gtod->wall_time_nsec;
+		ns = vgetns();
+	} while (unlikely(read_seqretry(&gtod->lock, seq)));
+	timespec_add_ns(ts, ns);
+	return 0;
+}
+
+/* Copy of the version in kernel/time.c which we cannot directly access */
+notrace static void
+vset_normalized_timespec(struct timespec *ts, long sec, long nsec)
+{
+	while (nsec >= NSEC_PER_SEC) {
+		nsec -= NSEC_PER_SEC;
+		++sec;
+	}
+	while (nsec < 0) {
+		nsec += NSEC_PER_SEC;
+		--sec;
+	}
+	ts->tv_sec = sec;
+	ts->tv_nsec = nsec;
+}
+
+notrace static noinline int do_monotonic(struct timespec *ts)
+{
+	unsigned long seq, ns, secs;
+	do {
+		seq = read_seqbegin(&gtod->lock);
+		secs = gtod->wall_time_sec;
+		ns = gtod->wall_time_nsec + vgetns();
+		secs += gtod->wall_to_monotonic.tv_sec;
+		ns += gtod->wall_to_monotonic.tv_nsec;
+	} while (unlikely(read_seqretry(&gtod->lock, seq)));
+	vset_normalized_timespec(ts, secs, ns);
+	return 0;
+}
+
+notrace static noinline int do_realtime_coarse(struct timespec *ts)
+{
+	unsigned long seq;
+	do {
+		seq = read_seqbegin(&gtod->lock);
+		ts->tv_sec = gtod->wall_time_coarse.tv_sec;
+		ts->tv_nsec = gtod->wall_time_coarse.tv_nsec;
+	} while (unlikely(read_seqretry(&gtod->lock, seq)));
+	return 0;
+}
+
+notrace static noinline int do_monotonic_coarse(struct timespec *ts)
+{
+	unsigned long seq, ns, secs;
+	do {
+		seq = read_seqbegin(&gtod->lock);
+		secs = gtod->wall_time_coarse.tv_sec;
+		ns = gtod->wall_time_coarse.tv_nsec;
+		secs += gtod->wall_to_monotonic.tv_sec;
+		ns += gtod->wall_to_monotonic.tv_nsec;
+	} while (unlikely(read_seqretry(&gtod->lock, seq)));
+	vset_normalized_timespec(ts, secs, ns);
+	return 0;
+}
+
+notrace int __vdso_clock_gettime(clockid_t clock, struct timespec *ts)
+{
+	if (likely(gtod->sysctl_enabled))
+		switch (clock) {
+		case CLOCK_REALTIME:
+			if (likely(gtod->clock.vread))
+				return do_realtime(ts);
+			break;
+		case CLOCK_MONOTONIC:
+			if (likely(gtod->clock.vread))
+				return do_monotonic(ts);
+			break;
+		case CLOCK_REALTIME_COARSE:
+			return do_realtime_coarse(ts);
+		case CLOCK_MONOTONIC_COARSE:
+			return do_monotonic_coarse(ts);
+		}
+	return vdso_fallback_gettime(clock, ts);
+}
+int clock_gettime(clockid_t, struct timespec *)
+	__attribute__((weak, alias("__vdso_clock_gettime")));
+
+notrace int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz)
+{
+	long ret;
+	if (likely(gtod->sysctl_enabled && gtod->clock.vread)) {
+		if (likely(tv != NULL)) {
+			BUILD_BUG_ON(offsetof(struct timeval, tv_usec) !=
+				     offsetof(struct timespec, tv_nsec) ||
+				     sizeof(*tv) != sizeof(struct timespec));
+			do_realtime((struct timespec *)tv);
+			tv->tv_usec /= 1000;
+		}
+		if (unlikely(tz != NULL)) {
+			/* Avoid memcpy. Some old compilers fail to inline it */
+			tz->tz_minuteswest = gtod->sys_tz.tz_minuteswest;
+			tz->tz_dsttime = gtod->sys_tz.tz_dsttime;
+		}
+		return 0;
+	}
+	asm("syscall" : "=a" (ret) :
+	    "0" (__NR_gettimeofday), "D" (tv), "S" (tz) : "memory");
+	return ret;
+}
+int gettimeofday(struct timeval *, struct timezone *)
+	__attribute__((weak, alias("__vdso_gettimeofday")));

kernel/arch/x86/vdso/vdso-layout.lds.S

@@ -0,0 +1,64 @@
+/*
+ * Linker script for vDSO.  This is an ELF shared object prelinked to
+ * its virtual address, and with only one read-only segment.
+ * This script controls its layout.
+ */
+
+SECTIONS
+{
+	. = VDSO_PRELINK + SIZEOF_HEADERS;
+
+	.hash		: { *(.hash) }			:text
+	.gnu.hash	: { *(.gnu.hash) }
+	.dynsym		: { *(.dynsym) }
+	.dynstr		: { *(.dynstr) }
+	.gnu.version	: { *(.gnu.version) }
+	.gnu.version_d	: { *(.gnu.version_d) }
+	.gnu.version_r	: { *(.gnu.version_r) }
+
+	.note		: { *(.note.*) }		:text	:note
+
+	.eh_frame_hdr	: { *(.eh_frame_hdr) }		:text	:eh_frame_hdr
+	.eh_frame	: { KEEP (*(.eh_frame)) }	:text
+
+	.dynamic	: { *(.dynamic) }		:text	:dynamic
+
+	.rodata		: { *(.rodata*) }		:text
+	.data		: {
+	      *(.data*)
+	      *(.sdata*)
+	      *(.got.plt) *(.got)
+	      *(.gnu.linkonce.d.*)
+	      *(.bss*)
+	      *(.dynbss*)
+	      *(.gnu.linkonce.b.*)
+	}
+
+	.altinstructions	: { *(.altinstructions) }
+	.altinstr_replacement	: { *(.altinstr_replacement) }
+
+	/*
+	 * Align the actual code well away from the non-instruction data.
+	 * This is the best thing for the I-cache.
+	 */
+	. = ALIGN(0x100);
+
+	.text		: { *(.text*) }			:text	=0x90909090
+}
+
+/*
+ * Very old versions of ld do not recognize this name token; use the constant.
+ */
+#define PT_GNU_EH_FRAME	0x6474e550
+
+/*
+ * We must supply the ELF program headers explicitly to get just one
+ * PT_LOAD segment, and set the flags explicitly to make segments read-only.
+ */
+PHDRS
+{
+	text		PT_LOAD		FLAGS(5) FILEHDR PHDRS; /* PF_R|PF_X */
+	dynamic		PT_DYNAMIC	FLAGS(4);		/* PF_R */
+	note		PT_NOTE		FLAGS(4);		/* PF_R */
+	eh_frame_hdr	PT_GNU_EH_FRAME;
+}

kernel/arch/x86/vdso/vdso-note.S

@@ -0,0 +1,12 @@
+/*
+ * This supplies .note.* sections to go into the PT_NOTE inside the vDSO text.
+ * Here we can supply some information useful to userland.
+ */
+
+#include <linux/uts.h>
+#include <linux/version.h>
+#include <linux/elfnote.h>
+
+ELFNOTE_START(Linux, 0, "a")
+	.long LINUX_VERSION_CODE
+ELFNOTE_END

kernel/arch/x86/vdso/vdso.S

@@ -0,0 +1,10 @@
+#include <linux/init.h>
+
+__INITDATA
+
+	.globl vdso_start, vdso_end
+vdso_start:
+	.incbin "arch/x86/vdso/vdso.so"
+vdso_end:
+
+__FINIT

kernel/arch/x86/vdso/vdso.lds.S

@@ -0,0 +1,37 @@
+/*
+ * Linker script for 64-bit vDSO.
+ * We #include the file to define the layout details.
+ * Here we only choose the prelinked virtual address.
+ *
+ * This file defines the version script giving the user-exported symbols in
+ * the DSO.  We can define local symbols here called VDSO* to make their
+ * values visible using the asm-x86/vdso.h macros from the kernel proper.
+ */
+
+#define VDSO_PRELINK 0xffffffffff700000
+#include "vdso-layout.lds.S"
+
+/*
+ * This controls what userland symbols we export from the vDSO.
+ */
+VERSION {
+	LINUX_2.6 {
+	global:
+		clock_gettime;
+		__vdso_clock_gettime;
+		gettimeofday;
+		__vdso_gettimeofday;
+		getcpu;
+		__vdso_getcpu;
+	local: *;
+	};
+}
+
+VDSO64_PRELINK = VDSO_PRELINK;
+
+/*
+ * Define VDSO64_x for each VEXTERN(x), for use via VDSO64_SYMBOL.
+ */
+#define VEXTERN(x)	VDSO64_ ## x = vdso_ ## x;
+#include "vextern.h"
+#undef	VEXTERN

kernel/arch/x86/vdso/vdso32-setup.c

@@ -0,0 +1,443 @@
+/*
+ * (C) Copyright 2002 Linus Torvalds
+ * Portions based on the vdso-randomization code from exec-shield:
+ * Copyright(C) 2005-2006, Red Hat, Inc., Ingo Molnar
+ *
+ * This file contains the needed initializations to support sysenter.
+ */
+
+#include <linux/init.h>
+#include <linux/smp.h>
+#include <linux/thread_info.h>
+#include <linux/sched.h>
+#include <linux/gfp.h>
+#include <linux/string.h>
+#include <linux/elf.h>
+#include <linux/mm.h>
+#include <linux/err.h>
+#include <linux/module.h>
+
+#include <asm/cpufeature.h>
+#include <asm/msr.h>
+#include <asm/pgtable.h>
+#include <asm/unistd.h>
+#include <asm/elf.h>
+#include <asm/tlbflush.h>
+#include <asm/vdso.h>
+#include <asm/proto.h>
+
+enum {
+	VDSO_DISABLED = 0,
+	VDSO_ENABLED = 1,
+	VDSO_COMPAT = 2,
+};
+
+#ifdef CONFIG_COMPAT_VDSO
+#define VDSO_DEFAULT	VDSO_COMPAT
+#else
+#define VDSO_DEFAULT	VDSO_ENABLED
+#endif
+
+#ifdef CONFIG_X86_64
+#define vdso_enabled			sysctl_vsyscall32
+#define arch_setup_additional_pages	syscall32_setup_pages
+#endif
+
+/*
+ * This is the difference between the prelinked addresses in the vDSO images
+ * and the VDSO_HIGH_BASE address where CONFIG_COMPAT_VDSO places the vDSO
+ * in the user address space.
+ */
+#define VDSO_ADDR_ADJUST	(VDSO_HIGH_BASE - (unsigned long)VDSO32_PRELINK)
+
+/*
+ * Should the kernel map a VDSO page into processes and pass its
+ * address down to glibc upon exec()?
+ */
+unsigned int __read_mostly vdso_enabled = VDSO_DEFAULT;
+
+static int __init vdso_setup(char *s)
+{
+	vdso_enabled = simple_strtoul(s, NULL, 0);
+
+	return 1;
+}
+
+/*
+ * For consistency, the argument vdso32=[012] affects the 32-bit vDSO
+ * behavior on both 64-bit and 32-bit kernels.
+ * On 32-bit kernels, vdso=[012] means the same thing.
+ */
+__setup("vdso32=", vdso_setup);
+
+#ifdef CONFIG_X86_32
+__setup_param("vdso=", vdso32_setup, vdso_setup, 0);
+
+EXPORT_SYMBOL_GPL(vdso_enabled);
+#endif
+
+static __init void reloc_symtab(Elf32_Ehdr *ehdr,
+				unsigned offset, unsigned size)
+{
+	Elf32_Sym *sym = (void *)ehdr + offset;
+	unsigned nsym = size / sizeof(*sym);
+	unsigned i;
+
+	for(i = 0; i < nsym; i++, sym++) {
+		if (sym->st_shndx == SHN_UNDEF ||
+		    sym->st_shndx == SHN_ABS)
+			continue;  /* skip */
+
+		if (sym->st_shndx > SHN_LORESERVE) {
+			printk(KERN_INFO "VDSO: unexpected st_shndx %x\n",
+			       sym->st_shndx);
+			continue;
+		}
+
+		switch(ELF_ST_TYPE(sym->st_info)) {
+		case STT_OBJECT:
+		case STT_FUNC:
+		case STT_SECTION:
+		case STT_FILE:
+			sym->st_value += VDSO_ADDR_ADJUST;
+		}
+	}
+}
+
+static __init void reloc_dyn(Elf32_Ehdr *ehdr, unsigned offset)
+{
+	Elf32_Dyn *dyn = (void *)ehdr + offset;
+
+	for(; dyn->d_tag != DT_NULL; dyn++)
+		switch(dyn->d_tag) {
+		case DT_PLTGOT:
+		case DT_HASH:
+		case DT_STRTAB:
+		case DT_SYMTAB:
+		case DT_RELA:
+		case DT_INIT:
+		case DT_FINI:
+		case DT_REL:
+		case DT_DEBUG:
+		case DT_JMPREL:
+		case DT_VERSYM:
+		case DT_VERDEF:
+		case DT_VERNEED:
+		case DT_ADDRRNGLO ... DT_ADDRRNGHI:
+			/* definitely pointers needing relocation */
+			dyn->d_un.d_ptr += VDSO_ADDR_ADJUST;
+			break;
+
+		case DT_ENCODING ... OLD_DT_LOOS-1:
+		case DT_LOOS ... DT_HIOS-1:
+			/* Tags above DT_ENCODING are pointers if
+			   they're even */
+			if (dyn->d_tag >= DT_ENCODING &&
+			    (dyn->d_tag & 1) == 0)
+				dyn->d_un.d_ptr += VDSO_ADDR_ADJUST;
+			break;
+
+		case DT_VERDEFNUM:
+		case DT_VERNEEDNUM:
+		case DT_FLAGS_1:
+		case DT_RELACOUNT:
+		case DT_RELCOUNT:
+		case DT_VALRNGLO ... DT_VALRNGHI:
+			/* definitely not pointers */
+			break;
+
+		case OLD_DT_LOOS ... DT_LOOS-1:
+		case DT_HIOS ... DT_VALRNGLO-1:
+		default:
+			if (dyn->d_tag > DT_ENCODING)
+				printk(KERN_INFO "VDSO: unexpected DT_tag %x\n",
+				       dyn->d_tag);
+			break;
+		}
+}
+
+static __init void relocate_vdso(Elf32_Ehdr *ehdr)
+{
+	Elf32_Phdr *phdr;
+	Elf32_Shdr *shdr;
+	int i;
+
+	BUG_ON(memcmp(ehdr->e_ident, ELFMAG, SELFMAG) != 0 ||
+	       !elf_check_arch_ia32(ehdr) ||
+	       ehdr->e_type != ET_DYN);
+
+	ehdr->e_entry += VDSO_ADDR_ADJUST;
+
+	/* rebase phdrs */
+	phdr = (void *)ehdr + ehdr->e_phoff;
+	for (i = 0; i < ehdr->e_phnum; i++) {
+		phdr[i].p_vaddr += VDSO_ADDR_ADJUST;
+
+		/* relocate dynamic stuff */
+		if (phdr[i].p_type == PT_DYNAMIC)
+			reloc_dyn(ehdr, phdr[i].p_offset);
+	}
+
+	/* rebase sections */
+	shdr = (void *)ehdr + ehdr->e_shoff;
+	for(i = 0; i < ehdr->e_shnum; i++) {
+		if (!(shdr[i].sh_flags & SHF_ALLOC))
+			continue;
+
+		shdr[i].sh_addr += VDSO_ADDR_ADJUST;
+
+		if (shdr[i].sh_type == SHT_SYMTAB ||
+		    shdr[i].sh_type == SHT_DYNSYM)
+			reloc_symtab(ehdr, shdr[i].sh_offset,
+				     shdr[i].sh_size);
+	}
+}
+
+static struct page *vdso32_pages[1];
+
+#ifdef CONFIG_X86_64
+
+#define	vdso32_sysenter()	(boot_cpu_has(X86_FEATURE_SYSENTER32))
+#define	vdso32_syscall()	(boot_cpu_has(X86_FEATURE_SYSCALL32))
+
+/* May not be __init: called during resume */
+void syscall32_cpu_init(void)
+{
+	/* Load these always in case some future AMD CPU supports
+	   SYSENTER from compat mode too. */
+	checking_wrmsrl(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS);
+	checking_wrmsrl(MSR_IA32_SYSENTER_ESP, 0ULL);
+	checking_wrmsrl(MSR_IA32_SYSENTER_EIP, (u64)ia32_sysenter_target);
+
+	wrmsrl(MSR_CSTAR, ia32_cstar_target);
+}
+
+#define compat_uses_vma		1
+
+static inline void map_compat_vdso(int map)
+{
+}
+
+#else  /* CONFIG_X86_32 */
+
+#define vdso32_sysenter()	(boot_cpu_has(X86_FEATURE_SEP))
+#define vdso32_syscall()	(0)
+
+void enable_sep_cpu(void)
+{
+	int cpu = get_cpu();
+	struct tss_struct *tss = &per_cpu(init_tss, cpu);
+
+	if (!boot_cpu_has(X86_FEATURE_SEP)) {
+		put_cpu();
+		return;
+	}
+
+	tss->x86_tss.ss1 = __KERNEL_CS;
+	tss->x86_tss.sp1 = sizeof(struct tss_struct) + (unsigned long) tss;
+	wrmsr(MSR_IA32_SYSENTER_CS, __KERNEL_CS, 0);
+	wrmsr(MSR_IA32_SYSENTER_ESP, tss->x86_tss.sp1, 0);
+	wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long) ia32_sysenter_target, 0);
+	put_cpu();	
+}
+
+static struct vm_area_struct gate_vma;
+
+static int __init gate_vma_init(void)
+{
+	gate_vma.vm_mm = NULL;
+	gate_vma.vm_start = FIXADDR_USER_START;
+	gate_vma.vm_end = FIXADDR_USER_END;
+	gate_vma.vm_flags = VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC;
+	gate_vma.vm_page_prot = __P101;
+	/*
+	 * Make sure the vDSO gets into every core dump.
+	 * Dumping its contents makes post-mortem fully interpretable later
+	 * without matching up the same kernel and hardware config to see
+	 * what PC values meant.
+	 */
+	gate_vma.vm_flags |= VM_ALWAYSDUMP;
+	return 0;
+}
+
+#define compat_uses_vma		0
+
+static void map_compat_vdso(int map)
+{
+	static int vdso_mapped;
+
+	if (map == vdso_mapped)
+		return;
+
+	vdso_mapped = map;
+
+	__set_fixmap(FIX_VDSO, page_to_pfn(vdso32_pages[0]) << PAGE_SHIFT,
+		     map ? PAGE_READONLY_EXEC : PAGE_NONE);
+
+	/* flush stray tlbs */
+	flush_tlb_all();
+}
+
+#endif	/* CONFIG_X86_64 */
+
+int __init sysenter_setup(void)
+{
+	void *syscall_page = (void *)get_zeroed_page(GFP_ATOMIC);
+	const void *vsyscall;
+	size_t vsyscall_len;
+
+	vdso32_pages[0] = virt_to_page(syscall_page);
+
+#ifdef CONFIG_X86_32
+	gate_vma_init();
+#endif
+
+	if (vdso32_syscall()) {
+		vsyscall = &vdso32_syscall_start;
+		vsyscall_len = &vdso32_syscall_end - &vdso32_syscall_start;
+	} else if (vdso32_sysenter()){
+		vsyscall = &vdso32_sysenter_start;
+		vsyscall_len = &vdso32_sysenter_end - &vdso32_sysenter_start;
+	} else {
+		vsyscall = &vdso32_int80_start;
+		vsyscall_len = &vdso32_int80_end - &vdso32_int80_start;
+	}
+
+	memcpy(syscall_page, vsyscall, vsyscall_len);
+	relocate_vdso(syscall_page);
+
+	return 0;
+}
+
+/* Setup a VMA at program startup for the vsyscall page */
+int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
+{
+	struct mm_struct *mm = current->mm;
+	unsigned long addr;
+	int ret = 0;
+	bool compat;
+
+	if (vdso_enabled == VDSO_DISABLED)
+		return 0;
+
+	down_write(&mm->mmap_sem);
+
+	/* Test compat mode once here, in case someone
+	   changes it via sysctl */
+	compat = (vdso_enabled == VDSO_COMPAT);
+
+	map_compat_vdso(compat);
+
+	if (compat)
+		addr = VDSO_HIGH_BASE;
+	else {
+		addr = get_unmapped_area(NULL, 0, PAGE_SIZE, 0, 0);
+		if (IS_ERR_VALUE(addr)) {
+			ret = addr;
+			goto up_fail;
+		}
+	}
+
+	current->mm->context.vdso = (void *)addr;
+
+	if (compat_uses_vma || !compat) {
+		/*
+		 * MAYWRITE to allow gdb to COW and set breakpoints
+		 *
+		 * Make sure the vDSO gets into every core dump.
+		 * Dumping its contents makes post-mortem fully
+		 * interpretable later without matching up the same
+		 * kernel and hardware config to see what PC values
+		 * meant.
+		 */
+		ret = install_special_mapping(mm, addr, PAGE_SIZE,
+					      VM_READ|VM_EXEC|
+					      VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC|
+					      VM_ALWAYSDUMP,
+					      vdso32_pages);
+
+		if (ret)
+			goto up_fail;
+	}
+
+	current_thread_info()->sysenter_return =
+		VDSO32_SYMBOL(addr, SYSENTER_RETURN);
+
+  up_fail:
+	if (ret)
+		current->mm->context.vdso = NULL;
+
+	up_write(&mm->mmap_sem);
+
+	return ret;
+}
+
+#ifdef CONFIG_X86_64
+
+__initcall(sysenter_setup);
+
+#ifdef CONFIG_SYSCTL
+/* Register vsyscall32 into the ABI table */
+#include <linux/sysctl.h>
+
+static ctl_table abi_table2[] = {
+	{
+		.procname	= "vsyscall32",
+		.data		= &sysctl_vsyscall32,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{}
+};
+
+static ctl_table abi_root_table2[] = {
+	{
+		.ctl_name = CTL_ABI,
+		.procname = "abi",
+		.mode = 0555,
+		.child = abi_table2
+	},
+	{}
+};
+
+static __init int ia32_binfmt_init(void)
+{
+	register_sysctl_table(abi_root_table2);
+	return 0;
+}
+__initcall(ia32_binfmt_init);
+#endif
+
+#else  /* CONFIG_X86_32 */
+
+const char *arch_vma_name(struct vm_area_struct *vma)
+{
+	if (vma->vm_mm && vma->vm_start == (long)vma->vm_mm->context.vdso)
+		return "[vdso]";
+	return NULL;
+}
+
+struct vm_area_struct *get_gate_vma(struct task_struct *tsk)
+{
+	struct mm_struct *mm = tsk->mm;
+
+	/* Check to see if this task was created in compat vdso mode */
+	if (mm && mm->context.vdso == (void *)VDSO_HIGH_BASE)
+		return &gate_vma;
+	return NULL;
+}
+
+int in_gate_area(struct task_struct *task, unsigned long addr)
+{
+	const struct vm_area_struct *vma = get_gate_vma(task);
+
+	return vma && addr >= vma->vm_start && addr < vma->vm_end;
+}
+
+int in_gate_area_no_task(unsigned long addr)
+{
+	return 0;
+}
+
+#endif	/* CONFIG_X86_64 */

kernel/arch/x86/vdso/vdso32.S

@@ -0,0 +1,22 @@
+#include <linux/init.h>
+
+__INITDATA
+
+	.globl vdso32_int80_start, vdso32_int80_end
+vdso32_int80_start:
+	.incbin "arch/x86/vdso/vdso32-int80.so"
+vdso32_int80_end:
+
+	.globl vdso32_syscall_start, vdso32_syscall_end
+vdso32_syscall_start:
+#ifdef CONFIG_COMPAT
+	.incbin "arch/x86/vdso/vdso32-syscall.so"
+#endif
+vdso32_syscall_end:
+
+	.globl vdso32_sysenter_start, vdso32_sysenter_end
+vdso32_sysenter_start:
+	.incbin "arch/x86/vdso/vdso32-sysenter.so"
+vdso32_sysenter_end:
+
+__FINIT

kernel/arch/x86/vdso/vdso32/.gitignore

@@ -0,0 +1 @@
+vdso32.lds

kernel/arch/x86/vdso/vdso32/int80.S

@@ -0,0 +1,56 @@
+/*
+ * Code for the vDSO.  This version uses the old int $0x80 method.
+ *
+ * First get the common code for the sigreturn entry points.
+ * This must come first.
+ */
+#include "sigreturn.S"
+
+	.text
+	.globl __kernel_vsyscall
+	.type __kernel_vsyscall,@function
+	ALIGN
+__kernel_vsyscall:
+.LSTART_vsyscall:
+	int $0x80
+	ret
+.LEND_vsyscall:
+	.size __kernel_vsyscall,.-.LSTART_vsyscall
+	.previous
+
+	.section .eh_frame,"a",@progbits
+.LSTARTFRAMEDLSI:
+	.long .LENDCIEDLSI-.LSTARTCIEDLSI
+.LSTARTCIEDLSI:
+	.long 0			/* CIE ID */
+	.byte 1			/* Version number */
+	.string "zR"		/* NUL-terminated augmentation string */
+	.uleb128 1		/* Code alignment factor */
+	.sleb128 -4		/* Data alignment factor */
+	.byte 8			/* Return address register column */
+	.uleb128 1		/* Augmentation value length */
+	.byte 0x1b		/* DW_EH_PE_pcrel|DW_EH_PE_sdata4. */
+	.byte 0x0c		/* DW_CFA_def_cfa */
+	.uleb128 4
+	.uleb128 4
+	.byte 0x88		/* DW_CFA_offset, column 0x8 */
+	.uleb128 1
+	.align 4
+.LENDCIEDLSI:
+	.long .LENDFDEDLSI-.LSTARTFDEDLSI /* Length FDE */
+.LSTARTFDEDLSI:
+	.long .LSTARTFDEDLSI-.LSTARTFRAMEDLSI /* CIE pointer */
+	.long .LSTART_vsyscall-.	/* PC-relative start address */
+	.long .LEND_vsyscall-.LSTART_vsyscall
+	.uleb128 0
+	.align 4
+.LENDFDEDLSI:
+	.previous
+
+	/*
+	 * Pad out the segment to match the size of the sysenter.S version.
+	 */
+VDSO32_vsyscall_eh_frame_size = 0x40
+	.section .data,"aw",@progbits
+	.space VDSO32_vsyscall_eh_frame_size-(.LENDFDEDLSI-.LSTARTFRAMEDLSI), 0
+	.previous

kernel/arch/x86/vdso/vdso32/note.S

@@ -0,0 +1,44 @@
+/*
+ * This supplies .note.* sections to go into the PT_NOTE inside the vDSO text.
+ * Here we can supply some information useful to userland.
+ */
+
+#include <linux/version.h>
+#include <linux/elfnote.h>
+
+/* Ideally this would use UTS_NAME, but using a quoted string here
+   doesn't work. Remember to change this when changing the
+   kernel's name. */
+ELFNOTE_START(Linux, 0, "a")
+	.long LINUX_VERSION_CODE
+ELFNOTE_END
+
+#ifdef CONFIG_XEN
+/*
+ * Add a special note telling glibc's dynamic linker a fake hardware
+ * flavor that it will use to choose the search path for libraries in the
+ * same way it uses real hardware capabilities like "mmx".
+ * We supply "nosegneg" as the fake capability, to indicate that we
+ * do not like negative offsets in instructions using segment overrides,
+ * since we implement those inefficiently.  This makes it possible to
+ * install libraries optimized to avoid those access patterns in someplace
+ * like /lib/i686/tls/nosegneg.  Note that an /etc/ld.so.conf.d/file
+ * corresponding to the bits here is needed to make ldconfig work right.
+ * It should contain:
+ *	hwcap 1 nosegneg
+ * to match the mapping of bit to name that we give here.
+ *
+ * At runtime, the fake hardware feature will be considered to be present
+ * if its bit is set in the mask word.  So, we start with the mask 0, and
+ * at boot time we set VDSO_NOTE_NONEGSEG_BIT if running under Xen.
+ */
+
+#include "../../xen/vdso.h"	/* Defines VDSO_NOTE_NONEGSEG_BIT.  */
+
+ELFNOTE_START(GNU, 2, "a")
+	.long 1			/* ncaps */
+VDSO32_NOTE_MASK:		/* Symbol used by arch/x86/xen/setup.c */
+	.long 0			/* mask */
+	.byte VDSO_NOTE_NONEGSEG_BIT; .asciz "nosegneg"	/* bit, name */
+ELFNOTE_END
+#endif

kernel/arch/x86/vdso/vdso32/sigreturn.S

@@ -0,0 +1,144 @@
+/*
+ * Common code for the sigreturn entry points in vDSO images.
+ * So far this code is the same for both int80 and sysenter versions.
+ * This file is #include'd by int80.S et al to define them first thing.
+ * The kernel assumes that the addresses of these routines are constant
+ * for all vDSO implementations.
+ */
+
+#include <linux/linkage.h>
+#include <asm/unistd_32.h>
+#include <asm/asm-offsets.h>
+
+#ifndef SYSCALL_ENTER_KERNEL
+#define	SYSCALL_ENTER_KERNEL	int $0x80
+#endif
+
+	.text
+	.globl __kernel_sigreturn
+	.type __kernel_sigreturn,@function
+	ALIGN
+__kernel_sigreturn:
+.LSTART_sigreturn:
+	popl %eax		/* XXX does this mean it needs unwind info? */
+	movl $__NR_sigreturn, %eax
+	SYSCALL_ENTER_KERNEL
+.LEND_sigreturn:
+	nop
+	.size __kernel_sigreturn,.-.LSTART_sigreturn
+
+	.globl __kernel_rt_sigreturn
+	.type __kernel_rt_sigreturn,@function
+	ALIGN
+__kernel_rt_sigreturn:
+.LSTART_rt_sigreturn:
+	movl $__NR_rt_sigreturn, %eax
+	SYSCALL_ENTER_KERNEL
+.LEND_rt_sigreturn:
+	nop
+	.size __kernel_rt_sigreturn,.-.LSTART_rt_sigreturn
+	.previous
+
+	.section .eh_frame,"a",@progbits
+.LSTARTFRAMEDLSI1:
+	.long .LENDCIEDLSI1-.LSTARTCIEDLSI1
+.LSTARTCIEDLSI1:
+	.long 0			/* CIE ID */
+	.byte 1			/* Version number */
+	.string "zRS"		/* NUL-terminated augmentation string */
+	.uleb128 1		/* Code alignment factor */
+	.sleb128 -4		/* Data alignment factor */
+	.byte 8			/* Return address register column */
+	.uleb128 1		/* Augmentation value length */
+	.byte 0x1b		/* DW_EH_PE_pcrel|DW_EH_PE_sdata4. */
+	.byte 0			/* DW_CFA_nop */
+	.align 4
+.LENDCIEDLSI1:
+	.long .LENDFDEDLSI1-.LSTARTFDEDLSI1 /* Length FDE */
+.LSTARTFDEDLSI1:
+	.long .LSTARTFDEDLSI1-.LSTARTFRAMEDLSI1 /* CIE pointer */
+	/* HACK: The dwarf2 unwind routines will subtract 1 from the
+	   return address to get an address in the middle of the
+	   presumed call instruction.  Since we didn't get here via
+	   a call, we need to include the nop before the real start
+	   to make up for it.  */
+	.long .LSTART_sigreturn-1-.	/* PC-relative start address */
+	.long .LEND_sigreturn-.LSTART_sigreturn+1
+	.uleb128 0			/* Augmentation */
+	/* What follows are the instructions for the table generation.
+	   We record the locations of each register saved.  This is
+	   complicated by the fact that the "CFA" is always assumed to
+	   be the value of the stack pointer in the caller.  This means
+	   that we must define the CFA of this body of code to be the
+	   saved value of the stack pointer in the sigcontext.  Which
+	   also means that there is no fixed relation to the other
+	   saved registers, which means that we must use DW_CFA_expression
+	   to compute their addresses.  It also means that when we
+	   adjust the stack with the popl, we have to do it all over again.  */
+
+#define do_cfa_expr(offset)						\
+	.byte 0x0f;			/* DW_CFA_def_cfa_expression */	\
+	.uleb128 1f-0f;			/*   length */			\
+0:	.byte 0x74;			/*     DW_OP_breg4 */		\
+	.sleb128 offset;		/*      offset */		\
+	.byte 0x06;			/*     DW_OP_deref */		\
+1:
+
+#define do_expr(regno, offset)						\
+	.byte 0x10;			/* DW_CFA_expression */		\
+	.uleb128 regno;			/*   regno */			\
+	.uleb128 1f-0f;			/*   length */			\
+0:	.byte 0x74;			/*     DW_OP_breg4 */		\
+	.sleb128 offset;		/*       offset */		\
+1:
+
+	do_cfa_expr(IA32_SIGCONTEXT_sp+4)
+	do_expr(0, IA32_SIGCONTEXT_ax+4)
+	do_expr(1, IA32_SIGCONTEXT_cx+4)
+	do_expr(2, IA32_SIGCONTEXT_dx+4)
+	do_expr(3, IA32_SIGCONTEXT_bx+4)
+	do_expr(5, IA32_SIGCONTEXT_bp+4)
+	do_expr(6, IA32_SIGCONTEXT_si+4)
+	do_expr(7, IA32_SIGCONTEXT_di+4)
+	do_expr(8, IA32_SIGCONTEXT_ip+4)
+
+	.byte 0x42	/* DW_CFA_advance_loc 2 -- nop; popl eax. */
+
+	do_cfa_expr(IA32_SIGCONTEXT_sp)
+	do_expr(0, IA32_SIGCONTEXT_ax)
+	do_expr(1, IA32_SIGCONTEXT_cx)
+	do_expr(2, IA32_SIGCONTEXT_dx)
+	do_expr(3, IA32_SIGCONTEXT_bx)
+	do_expr(5, IA32_SIGCONTEXT_bp)
+	do_expr(6, IA32_SIGCONTEXT_si)
+	do_expr(7, IA32_SIGCONTEXT_di)
+	do_expr(8, IA32_SIGCONTEXT_ip)
+
+	.align 4
+.LENDFDEDLSI1:
+
+	.long .LENDFDEDLSI2-.LSTARTFDEDLSI2 /* Length FDE */
+.LSTARTFDEDLSI2:
+	.long .LSTARTFDEDLSI2-.LSTARTFRAMEDLSI1 /* CIE pointer */
+	/* HACK: See above wrt unwind library assumptions.  */
+	.long .LSTART_rt_sigreturn-1-.	/* PC-relative start address */
+	.long .LEND_rt_sigreturn-.LSTART_rt_sigreturn+1
+	.uleb128 0			/* Augmentation */
+	/* What follows are the instructions for the table generation.
+	   We record the locations of each register saved.  This is
+	   slightly less complicated than the above, since we don't
+	   modify the stack pointer in the process.  */
+
+	do_cfa_expr(IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_sp)
+	do_expr(0, IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_ax)
+	do_expr(1, IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_cx)
+	do_expr(2, IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_dx)
+	do_expr(3, IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_bx)
+	do_expr(5, IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_bp)
+	do_expr(6, IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_si)
+	do_expr(7, IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_di)
+	do_expr(8, IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_ip)
+
+	.align 4
+.LENDFDEDLSI2:
+	.previous

kernel/arch/x86/vdso/vdso32/syscall.S

@@ -0,0 +1,77 @@
+/*
+ * Code for the vDSO.  This version uses the syscall instruction.
+ *
+ * First get the common code for the sigreturn entry points.
+ * This must come first.
+ */
+#define SYSCALL_ENTER_KERNEL	syscall
+#include "sigreturn.S"
+
+#include <asm/segment.h>
+
+	.text
+	.globl __kernel_vsyscall
+	.type __kernel_vsyscall,@function
+	ALIGN
+__kernel_vsyscall:
+.LSTART_vsyscall:
+	push	%ebp
+.Lpush_ebp:
+	movl	%ecx, %ebp
+	syscall
+	movl	$__USER32_DS, %ecx
+	movl	%ecx, %ss
+	movl	%ebp, %ecx
+	popl	%ebp
+.Lpop_ebp:
+	ret
+.LEND_vsyscall:
+	.size __kernel_vsyscall,.-.LSTART_vsyscall
+
+	.section .eh_frame,"a",@progbits
+.LSTARTFRAME:
+	.long .LENDCIE-.LSTARTCIE
+.LSTARTCIE:
+	.long 0			/* CIE ID */
+	.byte 1			/* Version number */
+	.string "zR"		/* NUL-terminated augmentation string */
+	.uleb128 1		/* Code alignment factor */
+	.sleb128 -4		/* Data alignment factor */
+	.byte 8			/* Return address register column */
+	.uleb128 1		/* Augmentation value length */
+	.byte 0x1b		/* DW_EH_PE_pcrel|DW_EH_PE_sdata4. */
+	.byte 0x0c		/* DW_CFA_def_cfa */
+	.uleb128 4
+	.uleb128 4
+	.byte 0x88		/* DW_CFA_offset, column 0x8 */
+	.uleb128 1
+	.align 4
+.LENDCIE:
+
+	.long .LENDFDE1-.LSTARTFDE1	/* Length FDE */
+.LSTARTFDE1:
+	.long .LSTARTFDE1-.LSTARTFRAME	/* CIE pointer */
+	.long .LSTART_vsyscall-.	/* PC-relative start address */
+	.long .LEND_vsyscall-.LSTART_vsyscall
+	.uleb128 0			/* Augmentation length */
+	/* What follows are the instructions for the table generation.
+	   We have to record all changes of the stack pointer.  */
+	.byte 0x40 + .Lpush_ebp-.LSTART_vsyscall /* DW_CFA_advance_loc */
+	.byte 0x0e		/* DW_CFA_def_cfa_offset */
+	.uleb128 8
+	.byte 0x85, 0x02	/* DW_CFA_offset %ebp -8 */
+	.byte 0x40 + .Lpop_ebp-.Lpush_ebp /* DW_CFA_advance_loc */
+	.byte 0xc5		/* DW_CFA_restore %ebp */
+	.byte 0x0e		/* DW_CFA_def_cfa_offset */
+	.uleb128 4
+	.align 4
+.LENDFDE1:
+	.previous
+
+	/*
+	 * Pad out the segment to match the size of the sysenter.S version.
+	 */
+VDSO32_vsyscall_eh_frame_size = 0x40
+	.section .data,"aw",@progbits
+	.space VDSO32_vsyscall_eh_frame_size-(.LENDFDE1-.LSTARTFRAME), 0
+	.previous

kernel/arch/x86/vdso/vdso32/sysenter.S

@@ -0,0 +1,116 @@
+/*
+ * Code for the vDSO.  This version uses the sysenter instruction.
+ *
+ * First get the common code for the sigreturn entry points.
+ * This must come first.
+ */
+#include "sigreturn.S"
+
+/*
+ * The caller puts arg2 in %ecx, which gets pushed. The kernel will use
+ * %ecx itself for arg2. The pushing is because the sysexit instruction
+ * (found in entry.S) requires that we clobber %ecx with the desired %esp.
+ * User code might expect that %ecx is unclobbered though, as it would be
+ * for returning via the iret instruction, so we must push and pop.
+ *
+ * The caller puts arg3 in %edx, which the sysexit instruction requires
+ * for %eip. Thus, exactly as for arg2, we must push and pop.
+ *
+ * Arg6 is different. The caller puts arg6 in %ebp. Since the sysenter
+ * instruction clobbers %esp, the user's %esp won't even survive entry
+ * into the kernel. We store %esp in %ebp. Code in entry.S must fetch
+ * arg6 from the stack.
+ *
+ * You can not use this vsyscall for the clone() syscall because the
+ * three words on the parent stack do not get copied to the child.
+ */
+	.text
+	.globl __kernel_vsyscall
+	.type __kernel_vsyscall,@function
+	ALIGN
+__kernel_vsyscall:
+.LSTART_vsyscall:
+	push %ecx
+.Lpush_ecx:
+	push %edx
+.Lpush_edx:
+	push %ebp
+.Lenter_kernel:
+	movl %esp,%ebp
+	sysenter
+
+	/* 7: align return point with nop's to make disassembly easier */
+	.space 7,0x90
+
+	/* 14: System call restart point is here! (SYSENTER_RETURN-2) */
+	jmp .Lenter_kernel
+	/* 16: System call normal return point is here! */
+VDSO32_SYSENTER_RETURN:	/* Symbol used by sysenter.c via vdso32-syms.h */
+	pop %ebp
+.Lpop_ebp:
+	pop %edx
+.Lpop_edx:
+	pop %ecx
+.Lpop_ecx:
+	ret
+.LEND_vsyscall:
+	.size __kernel_vsyscall,.-.LSTART_vsyscall
+	.previous
+
+	.section .eh_frame,"a",@progbits
+.LSTARTFRAMEDLSI:
+	.long .LENDCIEDLSI-.LSTARTCIEDLSI
+.LSTARTCIEDLSI:
+	.long 0			/* CIE ID */
+	.byte 1			/* Version number */
+	.string "zR"		/* NUL-terminated augmentation string */
+	.uleb128 1		/* Code alignment factor */
+	.sleb128 -4		/* Data alignment factor */
+	.byte 8			/* Return address register column */
+	.uleb128 1		/* Augmentation value length */
+	.byte 0x1b		/* DW_EH_PE_pcrel|DW_EH_PE_sdata4. */
+	.byte 0x0c		/* DW_CFA_def_cfa */
+	.uleb128 4
+	.uleb128 4
+	.byte 0x88		/* DW_CFA_offset, column 0x8 */
+	.uleb128 1
+	.align 4
+.LENDCIEDLSI:
+	.long .LENDFDEDLSI-.LSTARTFDEDLSI /* Length FDE */
+.LSTARTFDEDLSI:
+	.long .LSTARTFDEDLSI-.LSTARTFRAMEDLSI /* CIE pointer */
+	.long .LSTART_vsyscall-.	/* PC-relative start address */
+	.long .LEND_vsyscall-.LSTART_vsyscall
+	.uleb128 0
+	/* What follows are the instructions for the table generation.
+	   We have to record all changes of the stack pointer.  */
+	.byte 0x40 + (.Lpush_ecx-.LSTART_vsyscall) /* DW_CFA_advance_loc */
+	.byte 0x0e		/* DW_CFA_def_cfa_offset */
+	.byte 0x08		/* RA at offset 8 now */
+	.byte 0x40 + (.Lpush_edx-.Lpush_ecx) /* DW_CFA_advance_loc */
+	.byte 0x0e		/* DW_CFA_def_cfa_offset */
+	.byte 0x0c		/* RA at offset 12 now */
+	.byte 0x40 + (.Lenter_kernel-.Lpush_edx) /* DW_CFA_advance_loc */
+	.byte 0x0e		/* DW_CFA_def_cfa_offset */
+	.byte 0x10		/* RA at offset 16 now */
+	.byte 0x85, 0x04	/* DW_CFA_offset %ebp -16 */
+	/* Finally the epilogue.  */
+	.byte 0x40 + (.Lpop_ebp-.Lenter_kernel)	/* DW_CFA_advance_loc */
+	.byte 0x0e		/* DW_CFA_def_cfa_offset */
+	.byte 0x0c		/* RA at offset 12 now */
+	.byte 0xc5		/* DW_CFA_restore %ebp */
+	.byte 0x40 + (.Lpop_edx-.Lpop_ebp) /* DW_CFA_advance_loc */
+	.byte 0x0e		/* DW_CFA_def_cfa_offset */
+	.byte 0x08		/* RA at offset 8 now */
+	.byte 0x40 + (.Lpop_ecx-.Lpop_edx) /* DW_CFA_advance_loc */
+	.byte 0x0e		/* DW_CFA_def_cfa_offset */
+	.byte 0x04		/* RA at offset 4 now */
+	.align 4
+.LENDFDEDLSI:
+	.previous
+
+	/*
+	 * Emit a symbol with the size of this .eh_frame data,
+	 * to verify it matches the other versions.
+	 */
+VDSO32_vsyscall_eh_frame_size = (.LENDFDEDLSI-.LSTARTFRAMEDLSI)

kernel/arch/x86/vdso/vdso32/vdso32.lds.S

@@ -0,0 +1,37 @@
+/*
+ * Linker script for 32-bit vDSO.
+ * We #include the file to define the layout details.
+ * Here we only choose the prelinked virtual address.
+ *
+ * This file defines the version script giving the user-exported symbols in
+ * the DSO.  We can define local symbols here called VDSO* to make their
+ * values visible using the asm-x86/vdso.h macros from the kernel proper.
+ */
+
+#define VDSO_PRELINK 0
+#include "../vdso-layout.lds.S"
+
+/* The ELF entry point can be used to set the AT_SYSINFO value.  */
+ENTRY(__kernel_vsyscall);
+
+/*
+ * This controls what userland symbols we export from the vDSO.
+ */
+VERSION
+{
+	LINUX_2.5 {
+	global:
+		__kernel_vsyscall;
+		__kernel_sigreturn;
+		__kernel_rt_sigreturn;
+	local: *;
+	};
+}
+
+/*
+ * Symbols we define here called VDSO* get their values into vdso32-syms.h.
+ */
+VDSO32_PRELINK		= VDSO_PRELINK;
+VDSO32_vsyscall		= __kernel_vsyscall;
+VDSO32_sigreturn	= __kernel_sigreturn;
+VDSO32_rt_sigreturn	= __kernel_rt_sigreturn;

kernel/arch/x86/vdso/vextern.h

@@ -0,0 +1,16 @@
+#ifndef VEXTERN
+#include <asm/vsyscall.h>
+#define VEXTERN(x) \
+	extern typeof(x) *vdso_ ## x __attribute__((visibility("hidden")));
+#endif
+
+#define VMAGIC 0xfeedbabeabcdefabUL
+
+/* Any kernel variables used in the vDSO must be exported in the main
+   kernel's vmlinux.lds.S/vsyscall.h/proper __section and
+   put into vextern.h and be referenced as a pointer with vdso prefix.
+   The main kernel later fills in the values.   */
+
+VEXTERN(jiffies)
+VEXTERN(vgetcpu_mode)
+VEXTERN(vsyscall_gtod_data)

kernel/arch/x86/vdso/vgetcpu.c

@@ -0,0 +1,36 @@
+/*
+ * Copyright 2006 Andi Kleen, SUSE Labs.
+ * Subject to the GNU Public License, v.2
+ *
+ * Fast user context implementation of getcpu()
+ */
+
+#include <linux/kernel.h>
+#include <linux/getcpu.h>
+#include <linux/jiffies.h>
+#include <linux/time.h>
+#include <asm/vsyscall.h>
+#include <asm/vgtod.h>
+#include "vextern.h"
+
+notrace long
+__vdso_getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *unused)
+{
+	unsigned int p;
+
+	if (*vdso_vgetcpu_mode == VGETCPU_RDTSCP) {
+		/* Load per CPU data from RDTSCP */
+		native_read_tscp(&p);
+	} else {
+		/* Load per CPU data from GDT */
+		asm("lsl %1,%0" : "=r" (p) : "r" (__PER_CPU_SEG));
+	}
+	if (cpu)
+		*cpu = p & 0xfff;
+	if (node)
+		*node = p >> 12;
+	return 0;
+}
+
+long getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *tcache)
+	__attribute__((weak, alias("__vdso_getcpu")));

kernel/arch/x86/vdso/vma.c

@@ -0,0 +1,141 @@
+/*
+ * Set up the VMAs to tell the VM about the vDSO.
+ * Copyright 2007 Andi Kleen, SUSE Labs.
+ * Subject to the GPL, v.2
+ */
+#include <linux/mm.h>
+#include <linux/err.h>
+#include <linux/sched.h>
+#include <linux/init.h>
+#include <linux/random.h>
+#include <linux/elf.h>
+#include <asm/vsyscall.h>
+#include <asm/vgtod.h>
+#include <asm/proto.h>
+#include <asm/vdso.h>
+
+#include "vextern.h"		/* Just for VMAGIC.  */
+#undef VEXTERN
+
+unsigned int __read_mostly vdso_enabled = 1;
+
+extern char vdso_start[], vdso_end[];
+extern unsigned short vdso_sync_cpuid;
+
+static struct page **vdso_pages;
+static unsigned vdso_size;
+
+static inline void *var_ref(void *p, char *name)
+{
+	if (*(void **)p != (void *)VMAGIC) {
+		printk("VDSO: variable %s broken\n", name);
+		vdso_enabled = 0;
+	}
+	return p;
+}
+
+static int __init init_vdso_vars(void)
+{
+	int npages = (vdso_end - vdso_start + PAGE_SIZE - 1) / PAGE_SIZE;
+	int i;
+	char *vbase;
+
+	vdso_size = npages << PAGE_SHIFT;
+	vdso_pages = kmalloc(sizeof(struct page *) * npages, GFP_KERNEL);
+	if (!vdso_pages)
+		goto oom;
+	for (i = 0; i < npages; i++) {
+		struct page *p;
+		p = alloc_page(GFP_KERNEL);
+		if (!p)
+			goto oom;
+		vdso_pages[i] = p;
+		copy_page(page_address(p), vdso_start + i*PAGE_SIZE);
+	}
+
+	vbase = vmap(vdso_pages, npages, 0, PAGE_KERNEL);
+	if (!vbase)
+		goto oom;
+
+	if (memcmp(vbase, "\177ELF", 4)) {
+		printk("VDSO: I'm broken; not ELF\n");
+		vdso_enabled = 0;
+	}
+
+#define VEXTERN(x) \
+	*(typeof(__ ## x) **) var_ref(VDSO64_SYMBOL(vbase, x), #x) = &__ ## x;
+#include "vextern.h"
+#undef VEXTERN
+	return 0;
+
+ oom:
+	printk("Cannot allocate vdso\n");
+	vdso_enabled = 0;
+	return -ENOMEM;
+}
+__initcall(init_vdso_vars);
+
+struct linux_binprm;
+
+/* Put the vdso above the (randomized) stack with another randomized offset.
+   This way there is no hole in the middle of address space.
+   To save memory make sure it is still in the same PTE as the stack top.
+   This doesn't give that many random bits */
+static unsigned long vdso_addr(unsigned long start, unsigned len)
+{
+	unsigned long addr, end;
+	unsigned offset;
+	end = (start + PMD_SIZE - 1) & PMD_MASK;
+	if (end >= TASK_SIZE_MAX)
+		end = TASK_SIZE_MAX;
+	end -= len;
+	/* This loses some more bits than a modulo, but is cheaper */
+	offset = get_random_int() & (PTRS_PER_PTE - 1);
+	addr = start + (offset << PAGE_SHIFT);
+	if (addr >= end)
+		addr = end;
+	return addr;
+}
+
+/* Setup a VMA at program startup for the vsyscall page.
+   Not called for compat tasks */
+int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
+{
+	struct mm_struct *mm = current->mm;
+	unsigned long addr;
+	int ret;
+
+	if (!vdso_enabled)
+		return 0;
+
+	down_write(&mm->mmap_sem);
+	addr = vdso_addr(mm->start_stack, vdso_size);
+	addr = get_unmapped_area(NULL, addr, vdso_size, 0, 0);
+	if (IS_ERR_VALUE(addr)) {
+		ret = addr;
+		goto up_fail;
+	}
+
+	current->mm->context.vdso = (void *)addr;
+
+	ret = install_special_mapping(mm, addr, vdso_size,
+				      VM_READ|VM_EXEC|
+				      VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC|
+				      VM_ALWAYSDUMP,
+				      vdso_pages);
+	if (ret) {
+		current->mm->context.vdso = NULL;
+		goto up_fail;
+	}
+
+up_fail:
+	up_write(&mm->mmap_sem);
+	return ret;
+}
+
+static __init int vdso_setup(char *s)
+{
+	vdso_enabled = simple_strtoul(s, NULL, 0);
+	return 0;
+}
+__setup("vdso=", vdso_setup);

kernel/arch/x86/vdso/vvar.c

@@ -0,0 +1,12 @@
+/* Define pointer to external vDSO variables.
+   These are part of the vDSO. The kernel fills in the real addresses
+   at boot time. This is done because when the vdso is linked the
+   kernel isn't yet and we don't know the final addresses. */
+#include <linux/kernel.h>
+#include <linux/time.h>
+#include <asm/vsyscall.h>
+#include <asm/timex.h>
+#include <asm/vgtod.h>
+
+#define VEXTERN(x) typeof (__ ## x) *const vdso_ ## x = (void *)VMAGIC;
+#include "vextern.h"