x86_64: move vdso
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
diff --git a/arch/x86/vdso/.gitignore b/arch/x86/vdso/.gitignore
new file mode 100644
index 0000000..f8b69d8
--- /dev/null
+++ b/arch/x86/vdso/.gitignore
@@ -0,0 +1 @@
+vdso.lds
diff --git a/arch/x86/vdso/Makefile b/arch/x86/vdso/Makefile
new file mode 100644
index 0000000..8d03de0
--- /dev/null
+++ b/arch/x86/vdso/Makefile
@@ -0,0 +1,49 @@
+#
+# x86-64 vDSO.
+#
+
+# files to link into the vdso
+# vdso-start.o has to be first
+vobjs-y := vdso-start.o vdso-note.o vclock_gettime.o vgetcpu.o vvar.o
+
+# files to link into kernel
+obj-y := vma.o vdso.o vdso-syms.o
+
+vobjs := $(foreach F,$(vobjs-y),$(obj)/$F)
+
+$(obj)/vdso.o: $(obj)/vdso.so
+
+targets += vdso.so vdso.lds $(vobjs-y) vdso-syms.o
+
+# The DSO images are built using a special linker script.
+quiet_cmd_syscall = SYSCALL $@
+ cmd_syscall = $(CC) -m elf_x86_64 -nostdlib $(SYSCFLAGS_$(@F)) \
+ -Wl,-T,$(filter-out FORCE,$^) -o $@
+
+export CPPFLAGS_vdso.lds += -P -C -U$(ARCH)
+
+vdso-flags = -fPIC -shared -Wl,-soname=linux-vdso.so.1 \
+ $(call ld-option, -Wl$(comma)--hash-style=sysv) \
+ -Wl,-z,max-page-size=4096 -Wl,-z,common-page-size=4096
+SYSCFLAGS_vdso.so = $(vdso-flags)
+
+$(obj)/vdso.o: $(src)/vdso.S $(obj)/vdso.so
+
+$(obj)/vdso.so: $(src)/vdso.lds $(vobjs) FORCE
+ $(call if_changed,syscall)
+
+CFL := $(PROFILING) -mcmodel=small -fPIC -g0 -O2 -fasynchronous-unwind-tables -m64
+
+$(obj)/vclock_gettime.o: CFLAGS = $(CFL)
+$(obj)/vgetcpu.o: CFLAGS = $(CFL)
+
+# We also create a special relocatable object that should mirror the symbol
+# table and layout of the linked DSO. With ld -R we can then refer to
+# these symbols in the kernel code rather than hand-coded addresses.
+extra-y += vdso-syms.o
+$(obj)/built-in.o: $(obj)/vdso-syms.o
+$(obj)/built-in.o: ld_flags += -R $(obj)/vdso-syms.o
+
+SYSCFLAGS_vdso-syms.o = -r -d
+$(obj)/vdso-syms.o: $(src)/vdso.lds $(vobjs) FORCE
+ $(call if_changed,syscall)
diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c
new file mode 100644
index 0000000..5b54cdf
--- /dev/null
+++ b/arch/x86/vdso/vclock_gettime.c
@@ -0,0 +1,121 @@
+/*
+ * 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.
+ */
+
+#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 <asm/vgtod.h>
+#include "vextern.h"
+
+#define gtod vdso_vsyscall_gtod_data
+
+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;
+}
+
+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;
+}
+
+static noinline int do_realtime(struct timespec *ts)
+{
+ unsigned long seq, ns;
+ do {
+ seq = read_seqbegin(>od->lock);
+ ts->tv_sec = gtod->wall_time_sec;
+ ts->tv_nsec = gtod->wall_time_nsec;
+ ns = vgetns();
+ } while (unlikely(read_seqretry(>od->lock, seq)));
+ timespec_add_ns(ts, ns);
+ return 0;
+}
+
+/* Copy of the version in kernel/time.c which we cannot directly access */
+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;
+}
+
+static noinline int do_monotonic(struct timespec *ts)
+{
+ unsigned long seq, ns, secs;
+ do {
+ seq = read_seqbegin(>od->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(>od->lock, seq)));
+ vset_normalized_timespec(ts, secs, ns);
+ return 0;
+}
+
+int __vdso_clock_gettime(clockid_t clock, struct timespec *ts)
+{
+ if (likely(gtod->sysctl_enabled && gtod->clock.vread))
+ switch (clock) {
+ case CLOCK_REALTIME:
+ return do_realtime(ts);
+ case CLOCK_MONOTONIC:
+ return do_monotonic(ts);
+ }
+ return vdso_fallback_gettime(clock, ts);
+}
+int clock_gettime(clockid_t, struct timespec *)
+ __attribute__((weak, alias("__vdso_clock_gettime")));
+
+int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz)
+{
+ long ret;
+ if (likely(gtod->sysctl_enabled && gtod->clock.vread)) {
+ 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)) {
+ /* This relies on gcc inlining the memcpy. We'll notice
+ if it ever fails to do so. */
+ memcpy(tz, >od->sys_tz, sizeof(struct timezone));
+ }
+ 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")));
diff --git a/arch/x86/vdso/vdso-note.S b/arch/x86/vdso/vdso-note.S
new file mode 100644
index 0000000..79a071e
--- /dev/null
+++ b/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
diff --git a/arch/x86/vdso/vdso-start.S b/arch/x86/vdso/vdso-start.S
new file mode 100644
index 0000000..2dc2cdb
--- /dev/null
+++ b/arch/x86/vdso/vdso-start.S
@@ -0,0 +1,2 @@
+ .globl vdso_kernel_start
+vdso_kernel_start:
diff --git a/arch/x86/vdso/vdso.S b/arch/x86/vdso/vdso.S
new file mode 100644
index 0000000..4b1620a
--- /dev/null
+++ b/arch/x86/vdso/vdso.S
@@ -0,0 +1,2 @@
+ .section ".vdso","a"
+ .incbin "arch/x86/vdso/vdso.so"
diff --git a/arch/x86/vdso/vdso.lds.S b/arch/x86/vdso/vdso.lds.S
new file mode 100644
index 0000000..b9a60e6
--- /dev/null
+++ b/arch/x86/vdso/vdso.lds.S
@@ -0,0 +1,77 @@
+/*
+ * Linker script for vsyscall DSO. The vsyscall page is an ELF shared
+ * object prelinked to its virtual address, and with only one read-only
+ * segment (that fits in one page). This script controls its layout.
+ */
+#include <asm/asm-offsets.h>
+#include "voffset.h"
+
+#define VDSO_PRELINK 0xffffffffff700000
+
+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) }
+
+ /* This linker script is used both with -r and with -shared.
+ For the layouts to match, we need to skip more than enough
+ space for the dynamic symbol table et al. If this amount
+ is insufficient, ld -shared will barf. Just increase it here. */
+ . = VDSO_PRELINK + VDSO_TEXT_OFFSET;
+
+ .text : { *(.text) } :text
+ .text.ptr : { *(.text.ptr) } :text
+ . = VDSO_PRELINK + 0x900;
+ .data : { *(.data) } :text
+ .bss : { *(.bss) } :text
+
+ .altinstructions : { *(.altinstructions) } :text
+ .altinstr_replacement : { *(.altinstr_replacement) } :text
+
+ .note : { *(.note.*) } :text :note
+ .eh_frame_hdr : { *(.eh_frame_hdr) } :text :eh_frame_hdr
+ .eh_frame : { KEEP (*(.eh_frame)) } :text
+ .dynamic : { *(.dynamic) } :text :dynamic
+ .useless : {
+ *(.got.plt) *(.got)
+ *(.gnu.linkonce.d.*)
+ *(.dynbss)
+ *(.gnu.linkonce.b.*)
+ } :text
+}
+
+/*
+ * 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 FILEHDR PHDRS FLAGS(5); /* PF_R|PF_X */
+ dynamic PT_DYNAMIC FLAGS(4); /* PF_R */
+ note PT_NOTE FLAGS(4); /* PF_R */
+ eh_frame_hdr 0x6474e550; /* PT_GNU_EH_FRAME, but ld doesn't match the name */
+}
+
+/*
+ * This controls what symbols we export from the DSO.
+ */
+VERSION
+{
+ LINUX_2.6 {
+ global:
+ clock_gettime;
+ __vdso_clock_gettime;
+ gettimeofday;
+ __vdso_gettimeofday;
+ getcpu;
+ __vdso_getcpu;
+ local: *;
+ };
+}
diff --git a/arch/x86/vdso/vextern.h b/arch/x86/vdso/vextern.h
new file mode 100644
index 0000000..1683ba2
--- /dev/null
+++ b/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)
diff --git a/arch/x86/vdso/vgetcpu.c b/arch/x86/vdso/vgetcpu.c
new file mode 100644
index 0000000..91f6e85
--- /dev/null
+++ b/arch/x86/vdso/vgetcpu.c
@@ -0,0 +1,50 @@
+/*
+ * 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"
+
+long __vdso_getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *tcache)
+{
+ unsigned int dummy, p;
+ unsigned long j = 0;
+
+ /* Fast cache - only recompute value once per jiffies and avoid
+ relatively costly rdtscp/cpuid otherwise.
+ This works because the scheduler usually keeps the process
+ on the same CPU and this syscall doesn't guarantee its
+ results anyways.
+ We do this here because otherwise user space would do it on
+ its own in a likely inferior way (no access to jiffies).
+ If you don't like it pass NULL. */
+ if (tcache && tcache->blob[0] == (j = *vdso_jiffies)) {
+ p = tcache->blob[1];
+ } else if (*vdso_vgetcpu_mode == VGETCPU_RDTSCP) {
+ /* Load per CPU data from RDTSCP */
+ rdtscp(dummy, dummy, p);
+ } else {
+ /* Load per CPU data from GDT */
+ asm("lsl %1,%0" : "=r" (p) : "r" (__PER_CPU_SEG));
+ }
+ if (tcache) {
+ tcache->blob[0] = j;
+ tcache->blob[1] = p;
+ }
+ 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")));
diff --git a/arch/x86/vdso/vma.c b/arch/x86/vdso/vma.c
new file mode 100644
index 0000000..ff9333e
--- /dev/null
+++ b/arch/x86/vdso/vma.c
@@ -0,0 +1,140 @@
+/*
+ * 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 <asm/vsyscall.h>
+#include <asm/vgtod.h>
+#include <asm/proto.h>
+#include "voffset.h"
+
+int vdso_enabled = 1;
+
+#define VEXTERN(x) extern typeof(__ ## x) *vdso_ ## x;
+#include "vextern.h"
+#undef VEXTERN
+
+extern char vdso_kernel_start[], vdso_start[], vdso_end[];
+extern unsigned short vdso_sync_cpuid;
+
+struct page **vdso_pages;
+
+static inline void *var_ref(void *vbase, char *var, char *name)
+{
+ unsigned offset = var - &vdso_kernel_start[0] + VDSO_TEXT_OFFSET;
+ void *p = vbase + offset;
+ 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_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 V(x) *(typeof(x) *) var_ref(vbase, (char *)RELOC_HIDE(&x, 0), #x)
+#define VEXTERN(x) \
+ V(vdso_ ## 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_SIZE64)
+ end = TASK_SIZE64;
+ 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 exstack)
+{
+ struct mm_struct *mm = current->mm;
+ unsigned long addr;
+ int ret;
+ unsigned len = round_up(vdso_end - vdso_start, PAGE_SIZE);
+
+ if (!vdso_enabled)
+ return 0;
+
+ down_write(&mm->mmap_sem);
+ addr = vdso_addr(mm->start_stack, len);
+ addr = get_unmapped_area(NULL, addr, len, 0, 0);
+ if (IS_ERR_VALUE(addr)) {
+ ret = addr;
+ goto up_fail;
+ }
+
+ ret = install_special_mapping(mm, addr, len,
+ VM_READ|VM_EXEC|
+ VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC|
+ VM_ALWAYSDUMP,
+ vdso_pages);
+ if (ret)
+ goto up_fail;
+
+ current->mm->context.vdso = (void *)addr;
+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);
diff --git a/arch/x86/vdso/voffset.h b/arch/x86/vdso/voffset.h
new file mode 100644
index 0000000..4af67c7
--- /dev/null
+++ b/arch/x86/vdso/voffset.h
@@ -0,0 +1 @@
+#define VDSO_TEXT_OFFSET 0x600
diff --git a/arch/x86/vdso/vvar.c b/arch/x86/vdso/vvar.c
new file mode 100644
index 0000000..6fc2221
--- /dev/null
+++ b/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) *vdso_ ## x = (void *)VMAGIC;
+#include "vextern.h"