aboutsummaryrefslogtreecommitdiffstats
path: root/arch/x86/vdso
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/vdso')
-rw-r--r--arch/x86/vdso/Makefile26
-rw-r--r--arch/x86/vdso/vclock_gettime.c256
-rw-r--r--arch/x86/vdso/vdso-layout.lds.S29
-rw-r--r--arch/x86/vdso/vdso.S22
-rw-r--r--arch/x86/vdso/vdso32-setup.c301
-rw-r--r--arch/x86/vdso/vdso32.S21
-rw-r--r--arch/x86/vdso/vdso32/vclock_gettime.c30
-rw-r--r--arch/x86/vdso/vdso32/vdso32.lds.S15
-rw-r--r--arch/x86/vdso/vdsox32.S22
-rw-r--r--arch/x86/vdso/vma.c20
10 files changed, 356 insertions, 386 deletions
diff --git a/arch/x86/vdso/Makefile b/arch/x86/vdso/Makefile
index fd14be1d1472..c580d1210ffe 100644
--- a/arch/x86/vdso/Makefile
+++ b/arch/x86/vdso/Makefile
@@ -2,6 +2,8 @@
# Building vDSO images for x86.
#
+KBUILD_CFLAGS += $(DISABLE_LTO)
+
VDSO64-$(CONFIG_X86_64) := y
VDSOX32-$(CONFIG_X86_X32_ABI) := y
VDSO32-$(CONFIG_X86_32) := y
@@ -21,7 +23,8 @@ vobjs-$(VDSOX32-y) += $(vobjx32s-compat)
vobj64s := $(filter-out $(vobjx32s-compat),$(vobjs-y))
# files to link into kernel
-obj-$(VDSO64-y) += vma.o vdso.o
+obj-y += vma.o
+obj-$(VDSO64-y) += vdso.o
obj-$(VDSOX32-y) += vdsox32.o
obj-$(VDSO32-y) += vdso32.o vdso32-setup.o
@@ -35,7 +38,8 @@ export CPPFLAGS_vdso.lds += -P -C
VDSO_LDFLAGS_vdso.lds = -m64 -Wl,-soname=linux-vdso.so.1 \
-Wl,--no-undefined \
- -Wl,-z,max-page-size=4096 -Wl,-z,common-page-size=4096
+ -Wl,-z,max-page-size=4096 -Wl,-z,common-page-size=4096 \
+ $(DISABLE_LTO)
$(obj)/vdso.o: $(src)/vdso.S $(obj)/vdso.so
@@ -127,7 +131,7 @@ vdso32.so-$(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
+VDSO_LDFLAGS_vdso32.lds = -m32 -Wl,-m,elf_i386 -Wl,-soname=linux-gate.so.1
# This makes sure the $(obj) subdirectory exists even though vdso32/
# is not a kbuild sub-make subdirectory.
@@ -135,7 +139,7 @@ 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)
+targets += vdso32/note.o vdso32/vclock_gettime.o $(vdso32.so-y:%=vdso32/%.o)
extra-y += $(vdso32-images)
@@ -145,8 +149,19 @@ 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
+KBUILD_CFLAGS_32 := $(filter-out -m64,$(KBUILD_CFLAGS))
+KBUILD_CFLAGS_32 := $(filter-out -mcmodel=kernel,$(KBUILD_CFLAGS_32))
+KBUILD_CFLAGS_32 := $(filter-out -fno-pic,$(KBUILD_CFLAGS_32))
+KBUILD_CFLAGS_32 := $(filter-out -mfentry,$(KBUILD_CFLAGS_32))
+KBUILD_CFLAGS_32 += -m32 -msoft-float -mregparm=0 -fpic
+KBUILD_CFLAGS_32 += $(call cc-option, -fno-stack-protector)
+KBUILD_CFLAGS_32 += $(call cc-option, -foptimize-sibling-calls)
+KBUILD_CFLAGS_32 += -fno-omit-frame-pointer
+$(vdso32-images:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_32)
+
$(vdso32-images:%=$(obj)/%.dbg): $(obj)/vdso32-%.so.dbg: FORCE \
$(obj)/vdso32/vdso32.lds \
+ $(obj)/vdso32/vclock_gettime.o \
$(obj)/vdso32/note.o \
$(obj)/vdso32/%.o
$(call if_changed,vdso)
@@ -181,7 +196,8 @@ quiet_cmd_vdso = VDSO $@
-Wl,-T,$(filter %.lds,$^) $(filter %.o,$^) && \
sh $(srctree)/$(src)/checkundef.sh '$(NM)' '$@'
-VDSO_LDFLAGS = -fPIC -shared $(call cc-ldoption, -Wl$(comma)--hash-style=sysv)
+VDSO_LDFLAGS = -fPIC -shared $(call cc-ldoption, -Wl$(comma)--hash-style=sysv) \
+ $(LTO_CFLAGS)
GCOV_PROFILE := n
#
diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c
index eb5d7a56f8d4..16d686171e9a 100644
--- a/arch/x86/vdso/vclock_gettime.c
+++ b/arch/x86/vdso/vclock_gettime.c
@@ -4,6 +4,9 @@
*
* Fast user context implementation of clock_gettime, gettimeofday, and time.
*
+ * 32 Bit compat layer by Stefani Seibold <stefani@seibold.net>
+ * sponsored by Rohde & Schwarz GmbH & Co. KG Munich/Germany
+ *
* The code should have no internal unresolved relocations.
* Check with readelf after changing.
*/
@@ -11,56 +14,55 @@
/* 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/fixmap.h>
+#include <uapi/linux/time.h>
#include <asm/vgtod.h>
-#include <asm/timex.h>
#include <asm/hpet.h>
+#include <asm/vvar.h>
#include <asm/unistd.h>
-#include <asm/io.h>
-#include <asm/pvclock.h>
+#include <asm/msr.h>
+#include <linux/math64.h>
+#include <linux/time.h>
#define gtod (&VVAR(vsyscall_gtod_data))
-notrace static cycle_t vread_tsc(void)
+extern int __vdso_clock_gettime(clockid_t clock, struct timespec *ts);
+extern int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz);
+extern time_t __vdso_time(time_t *t);
+
+#ifdef CONFIG_HPET_TIMER
+static inline u32 read_hpet_counter(const volatile void *addr)
{
- cycle_t ret;
- u64 last;
+ return *(const volatile u32 *) (addr + HPET_COUNTER);
+}
+#endif
- /*
- * Empirically, a fence (of type that depends on the CPU)
- * before rdtsc is enough to ensure that rdtsc is ordered
- * with respect to loads. The various CPU manuals are unclear
- * as to whether rdtsc can be reordered with later loads,
- * but no one has ever seen it happen.
- */
- rdtsc_barrier();
- ret = (cycle_t)vget_cycles();
+#ifndef BUILD_VDSO32
- last = VVAR(vsyscall_gtod_data).clock.cycle_last;
+#include <linux/kernel.h>
+#include <asm/vsyscall.h>
+#include <asm/fixmap.h>
+#include <asm/pvclock.h>
- if (likely(ret >= last))
- return ret;
+static notrace cycle_t vread_hpet(void)
+{
+ return read_hpet_counter((const void *)fix_to_virt(VSYSCALL_HPET));
+}
- /*
- * GCC likes to generate cmov here, but this branch is extremely
- * predictable (it's just a funciton of time and the likely is
- * very likely) and there's a data dependence, so force GCC
- * to generate a branch instead. I don't barrier() because
- * we don't actually need a barrier, and if this function
- * ever gets inlined it will generate worse code.
- */
- asm volatile ("");
- return last;
+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;
}
-static notrace cycle_t vread_hpet(void)
+notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz)
{
- return readl((const void __iomem *)fix_to_virt(VSYSCALL_HPET) + HPET_COUNTER);
+ long ret;
+
+ asm("syscall" : "=a" (ret) :
+ "0" (__NR_gettimeofday), "D" (tv), "S" (tz) : "memory");
+ return ret;
}
#ifdef CONFIG_PARAVIRT_CLOCK
@@ -124,7 +126,7 @@ static notrace cycle_t vread_pvclock(int *mode)
*mode = VCLOCK_NONE;
/* refer to tsc.c read_tsc() comment for rationale */
- last = VVAR(vsyscall_gtod_data).clock.cycle_last;
+ last = gtod->cycle_last;
if (likely(ret >= last))
return ret;
@@ -133,11 +135,30 @@ static notrace cycle_t vread_pvclock(int *mode)
}
#endif
+#else
+
+extern u8 hpet_page
+ __attribute__((visibility("hidden")));
+
+#ifdef CONFIG_HPET_TIMER
+static notrace cycle_t vread_hpet(void)
+{
+ return read_hpet_counter((const void *)(&hpet_page));
+}
+#endif
+
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");
+
+ asm(
+ "mov %%ebx, %%edx \n"
+ "mov %2, %%ebx \n"
+ "call VDSO32_vsyscall \n"
+ "mov %%edx, %%ebx \n"
+ : "=a" (ret)
+ : "0" (__NR_clock_gettime), "g" (clock), "c" (ts)
+ : "memory", "edx");
return ret;
}
@@ -145,28 +166,79 @@ notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz)
{
long ret;
- asm("syscall" : "=a" (ret) :
- "0" (__NR_gettimeofday), "D" (tv), "S" (tz) : "memory");
+ asm(
+ "mov %%ebx, %%edx \n"
+ "mov %2, %%ebx \n"
+ "call VDSO32_vsyscall \n"
+ "mov %%edx, %%ebx \n"
+ : "=a" (ret)
+ : "0" (__NR_gettimeofday), "g" (tv), "c" (tz)
+ : "memory", "edx");
return ret;
}
+#ifdef CONFIG_PARAVIRT_CLOCK
+
+static notrace cycle_t vread_pvclock(int *mode)
+{
+ *mode = VCLOCK_NONE;
+ return 0;
+}
+#endif
+
+#endif
+
+notrace static cycle_t vread_tsc(void)
+{
+ cycle_t ret;
+ u64 last;
+
+ /*
+ * Empirically, a fence (of type that depends on the CPU)
+ * before rdtsc is enough to ensure that rdtsc is ordered
+ * with respect to loads. The various CPU manuals are unclear
+ * as to whether rdtsc can be reordered with later loads,
+ * but no one has ever seen it happen.
+ */
+ rdtsc_barrier();
+ ret = (cycle_t)__native_read_tsc();
+
+ last = gtod->cycle_last;
+
+ if (likely(ret >= last))
+ return ret;
+
+ /*
+ * GCC likes to generate cmov here, but this branch is extremely
+ * predictable (it's just a funciton of time and the likely is
+ * very likely) and there's a data dependence, so force GCC
+ * to generate a branch instead. I don't barrier() because
+ * we don't actually need a barrier, and if this function
+ * ever gets inlined it will generate worse code.
+ */
+ asm volatile ("");
+ return last;
+}
notrace static inline u64 vgetsns(int *mode)
{
- long v;
+ u64 v;
cycles_t cycles;
- if (gtod->clock.vclock_mode == VCLOCK_TSC)
+
+ if (gtod->vclock_mode == VCLOCK_TSC)
cycles = vread_tsc();
- else if (gtod->clock.vclock_mode == VCLOCK_HPET)
+#ifdef CONFIG_HPET_TIMER
+ else if (gtod->vclock_mode == VCLOCK_HPET)
cycles = vread_hpet();
+#endif
#ifdef CONFIG_PARAVIRT_CLOCK
- else if (gtod->clock.vclock_mode == VCLOCK_PVCLOCK)
+ else if (gtod->vclock_mode == VCLOCK_PVCLOCK)
cycles = vread_pvclock(mode);
#endif
else
return 0;
- v = (cycles - gtod->clock.cycle_last) & gtod->clock.mask;
- return v * gtod->clock.mult;
+ v = (cycles - gtod->cycle_last) & gtod->mask;
+ return v * gtod->mult;
}
/* Code size doesn't matter (vdso is 4k anyway) and this is faster. */
@@ -176,106 +248,102 @@ notrace static int __always_inline do_realtime(struct timespec *ts)
u64 ns;
int mode;
- ts->tv_nsec = 0;
do {
- seq = raw_read_seqcount_begin(&gtod->seq);
- mode = gtod->clock.vclock_mode;
+ seq = gtod_read_begin(gtod);
+ mode = gtod->vclock_mode;
ts->tv_sec = gtod->wall_time_sec;
ns = gtod->wall_time_snsec;
ns += vgetsns(&mode);
- ns >>= gtod->clock.shift;
- } while (unlikely(read_seqcount_retry(&gtod->seq, seq)));
+ ns >>= gtod->shift;
+ } while (unlikely(gtod_read_retry(gtod, seq)));
+
+ ts->tv_sec += __iter_div_u64_rem(ns, NSEC_PER_SEC, &ns);
+ ts->tv_nsec = ns;
- timespec_add_ns(ts, ns);
return mode;
}
-notrace static int do_monotonic(struct timespec *ts)
+notrace static int __always_inline do_monotonic(struct timespec *ts)
{
unsigned long seq;
u64 ns;
int mode;
- ts->tv_nsec = 0;
do {
- seq = raw_read_seqcount_begin(&gtod->seq);
- mode = gtod->clock.vclock_mode;
+ seq = gtod_read_begin(gtod);
+ mode = gtod->vclock_mode;
ts->tv_sec = gtod->monotonic_time_sec;
ns = gtod->monotonic_time_snsec;
ns += vgetsns(&mode);
- ns >>= gtod->clock.shift;
- } while (unlikely(read_seqcount_retry(&gtod->seq, seq)));
- timespec_add_ns(ts, ns);
+ ns >>= gtod->shift;
+ } while (unlikely(gtod_read_retry(gtod, seq)));
+
+ ts->tv_sec += __iter_div_u64_rem(ns, NSEC_PER_SEC, &ns);
+ ts->tv_nsec = ns;
return mode;
}
-notrace static int do_realtime_coarse(struct timespec *ts)
+notrace static void do_realtime_coarse(struct timespec *ts)
{
unsigned long seq;
do {
- seq = raw_read_seqcount_begin(&gtod->seq);
- ts->tv_sec = gtod->wall_time_coarse.tv_sec;
- ts->tv_nsec = gtod->wall_time_coarse.tv_nsec;
- } while (unlikely(read_seqcount_retry(&gtod->seq, seq)));
- return 0;
+ seq = gtod_read_begin(gtod);
+ ts->tv_sec = gtod->wall_time_coarse_sec;
+ ts->tv_nsec = gtod->wall_time_coarse_nsec;
+ } while (unlikely(gtod_read_retry(gtod, seq)));
}
-notrace static int do_monotonic_coarse(struct timespec *ts)
+notrace static void do_monotonic_coarse(struct timespec *ts)
{
unsigned long seq;
do {
- seq = raw_read_seqcount_begin(&gtod->seq);
- ts->tv_sec = gtod->monotonic_time_coarse.tv_sec;
- ts->tv_nsec = gtod->monotonic_time_coarse.tv_nsec;
- } while (unlikely(read_seqcount_retry(&gtod->seq, seq)));
-
- return 0;
+ seq = gtod_read_begin(gtod);
+ ts->tv_sec = gtod->monotonic_time_coarse_sec;
+ ts->tv_nsec = gtod->monotonic_time_coarse_nsec;
+ } while (unlikely(gtod_read_retry(gtod, seq)));
}
notrace int __vdso_clock_gettime(clockid_t clock, struct timespec *ts)
{
- int ret = VCLOCK_NONE;
-
switch (clock) {
case CLOCK_REALTIME:
- ret = do_realtime(ts);
+ if (do_realtime(ts) == VCLOCK_NONE)
+ goto fallback;
break;
case CLOCK_MONOTONIC:
- ret = do_monotonic(ts);
+ if (do_monotonic(ts) == VCLOCK_NONE)
+ goto fallback;
break;
case CLOCK_REALTIME_COARSE:
- return do_realtime_coarse(ts);
+ do_realtime_coarse(ts);
+ break;
case CLOCK_MONOTONIC_COARSE:
- return do_monotonic_coarse(ts);
+ do_monotonic_coarse(ts);
+ break;
+ default:
+ goto fallback;
}
- if (ret == VCLOCK_NONE)
- return vdso_fallback_gettime(clock, ts);
return 0;
+fallback:
+ 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 = VCLOCK_NONE;
-
if (likely(tv != NULL)) {
- BUILD_BUG_ON(offsetof(struct timeval, tv_usec) !=
- offsetof(struct timespec, tv_nsec) ||
- sizeof(*tv) != sizeof(struct timespec));
- ret = do_realtime((struct timespec *)tv);
+ if (unlikely(do_realtime((struct timespec *)tv) == VCLOCK_NONE))
+ return vdso_fallback_gtod(tv, tz);
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;
+ tz->tz_minuteswest = gtod->tz_minuteswest;
+ tz->tz_dsttime = gtod->tz_dsttime;
}
- if (ret == VCLOCK_NONE)
- return vdso_fallback_gtod(tv, tz);
return 0;
}
int gettimeofday(struct timeval *, struct timezone *)
@@ -287,8 +355,8 @@ int gettimeofday(struct timeval *, struct timezone *)
*/
notrace time_t __vdso_time(time_t *t)
{
- /* This is atomic on x86_64 so we don't need any locks. */
- time_t result = ACCESS_ONCE(VVAR(vsyscall_gtod_data).wall_time_sec);
+ /* This is atomic on x86 so we don't need any locks. */
+ time_t result = ACCESS_ONCE(gtod->wall_time_sec);
if (t)
*t = result;
diff --git a/arch/x86/vdso/vdso-layout.lds.S b/arch/x86/vdso/vdso-layout.lds.S
index 634a2cf62046..2e263f367b13 100644
--- a/arch/x86/vdso/vdso-layout.lds.S
+++ b/arch/x86/vdso/vdso-layout.lds.S
@@ -6,7 +6,25 @@
SECTIONS
{
- . = VDSO_PRELINK + SIZEOF_HEADERS;
+#ifdef BUILD_VDSO32
+#include <asm/vdso32.h>
+
+ .hpet_sect : {
+ hpet_page = . - VDSO_OFFSET(VDSO_HPET_PAGE);
+ } :text :hpet_sect
+
+ .vvar_sect : {
+ vvar = . - VDSO_OFFSET(VDSO_VVAR_PAGE);
+
+ /* Place all vvars at the offsets in asm/vvar.h. */
+#define EMIT_VVAR(name, offset) vvar_ ## name = vvar + offset;
+#define __VVAR_KERNEL_LDS
+#include <asm/vvar.h>
+#undef __VVAR_KERNEL_LDS
+#undef EMIT_VVAR
+ } :text :vvar_sect
+#endif
+ . = SIZEOF_HEADERS;
.hash : { *(.hash) } :text
.gnu.hash : { *(.gnu.hash) }
@@ -44,6 +62,11 @@ SECTIONS
. = ALIGN(0x100);
.text : { *(.text*) } :text =0x90909090
+
+ /DISCARD/ : {
+ *(.discard)
+ *(.discard.*)
+ }
}
/*
@@ -61,4 +84,8 @@ PHDRS
dynamic PT_DYNAMIC FLAGS(4); /* PF_R */
note PT_NOTE FLAGS(4); /* PF_R */
eh_frame_hdr PT_GNU_EH_FRAME;
+#ifdef BUILD_VDSO32
+ vvar_sect PT_NULL FLAGS(4); /* PF_R */
+ hpet_sect PT_NULL FLAGS(4); /* PF_R */
+#endif
}
diff --git a/arch/x86/vdso/vdso.S b/arch/x86/vdso/vdso.S
index 1e13eb8c9656..be3f23b09af5 100644
--- a/arch/x86/vdso/vdso.S
+++ b/arch/x86/vdso/vdso.S
@@ -1,21 +1,3 @@
-#include <asm/page_types.h>
-#include <linux/linkage.h>
+#include <asm/vdso.h>
-__PAGE_ALIGNED_DATA
-
- .globl vdso_start, vdso_end
- .align PAGE_SIZE
-vdso_start:
- .incbin "arch/x86/vdso/vdso.so"
-vdso_end:
- .align PAGE_SIZE /* extra data here leaks to userspace. */
-
-.previous
-
- .globl vdso_pages
- .bss
- .align 8
- .type vdso_pages, @object
-vdso_pages:
- .zero (vdso_end - vdso_start + PAGE_SIZE - 1) / PAGE_SIZE * 8
- .size vdso_pages, .-vdso_pages
+DEFINE_VDSO_IMAGE(vdso, "arch/x86/vdso/vdso.so")
diff --git a/arch/x86/vdso/vdso32-setup.c b/arch/x86/vdso/vdso32-setup.c
index d6bfb876cfb0..00348980a3a6 100644
--- a/arch/x86/vdso/vdso32-setup.c
+++ b/arch/x86/vdso/vdso32-setup.c
@@ -16,6 +16,7 @@
#include <linux/mm.h>
#include <linux/err.h>
#include <linux/module.h>
+#include <linux/slab.h>
#include <asm/cpufeature.h>
#include <asm/msr.h>
@@ -25,17 +26,14 @@
#include <asm/tlbflush.h>
#include <asm/vdso.h>
#include <asm/proto.h>
-
-enum {
- VDSO_DISABLED = 0,
- VDSO_ENABLED = 1,
- VDSO_COMPAT = 2,
-};
+#include <asm/fixmap.h>
+#include <asm/hpet.h>
+#include <asm/vvar.h>
#ifdef CONFIG_COMPAT_VDSO
-#define VDSO_DEFAULT VDSO_COMPAT
+#define VDSO_DEFAULT 0
#else
-#define VDSO_DEFAULT VDSO_ENABLED
+#define VDSO_DEFAULT 1
#endif
#ifdef CONFIG_X86_64
@@ -44,13 +42,6 @@ enum {
#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()?
*/
@@ -60,6 +51,9 @@ static int __init vdso_setup(char *s)
{
vdso_enabled = simple_strtoul(s, NULL, 0);
+ if (vdso_enabled > 1)
+ pr_warn("vdso32 values other than 0 and 1 are no longer allowed; vdso disabled\n");
+
return 1;
}
@@ -76,124 +70,8 @@ __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];
+static struct page **vdso32_pages;
+static unsigned vdso32_size;
#ifdef CONFIG_X86_64
@@ -212,12 +90,6 @@ void syscall32_cpu_init(void)
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))
@@ -241,64 +113,36 @@ void enable_sep_cpu(void)
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;
-
- 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
+ char *vdso32_start, *vdso32_end;
+ int npages, i;
+#ifdef CONFIG_COMPAT
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;
+ vdso32_start = vdso32_syscall_start;
+ vdso32_end = vdso32_syscall_end;
+ vdso32_pages = vdso32_syscall_pages;
+ } else
+#endif
+ if (vdso32_sysenter()) {
+ vdso32_start = vdso32_sysenter_start;
+ vdso32_end = vdso32_sysenter_end;
+ vdso32_pages = vdso32_sysenter_pages;
} else {
- vsyscall = &vdso32_int80_start;
- vsyscall_len = &vdso32_int80_end - &vdso32_int80_start;
+ vdso32_start = vdso32_int80_start;
+ vdso32_end = vdso32_int80_end;
+ vdso32_pages = vdso32_int80_pages;
}
- memcpy(syscall_page, vsyscall, vsyscall_len);
- relocate_vdso(syscall_page);
+ npages = ((vdso32_end - vdso32_start) + PAGE_SIZE - 1) / PAGE_SIZE;
+ vdso32_size = npages << PAGE_SHIFT;
+ for (i = 0; i < npages; i++)
+ vdso32_pages[i] = virt_to_page(vdso32_start + i*PAGE_SIZE);
+
+ patch_vdso32(vdso32_start, vdso32_size);
return 0;
}
@@ -309,48 +153,73 @@ 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;
+ struct vm_area_struct *vma;
#ifdef CONFIG_X86_X32_ABI
if (test_thread_flag(TIF_X32))
return x32_setup_additional_pages(bprm, uses_interp);
#endif
- if (vdso_enabled == VDSO_DISABLED)
+ if (vdso_enabled != 1) /* Other values all mean "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);
+ addr = get_unmapped_area(NULL, 0, vdso32_size + VDSO_OFFSET(VDSO_PREV_PAGES), 0, 0);
+ if (IS_ERR_VALUE(addr)) {
+ ret = addr;
+ goto up_fail;
+ }
+
+ addr += VDSO_OFFSET(VDSO_PREV_PAGES);
- map_compat_vdso(compat);
+ current->mm->context.vdso = (void *)addr;
- 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;
- }
+ /*
+ * MAYWRITE to allow gdb to COW and set breakpoints
+ */
+ ret = install_special_mapping(mm,
+ addr,
+ vdso32_size,
+ VM_READ|VM_EXEC|
+ VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
+ vdso32_pages);
+
+ if (ret)
+ goto up_fail;
+
+ vma = _install_special_mapping(mm,
+ addr - VDSO_OFFSET(VDSO_PREV_PAGES),
+ VDSO_OFFSET(VDSO_PREV_PAGES),
+ VM_READ,
+ NULL);
+
+ if (IS_ERR(vma)) {
+ ret = PTR_ERR(vma);
+ goto up_fail;
}
- current->mm->context.vdso = (void *)addr;
+ ret = remap_pfn_range(vma,
+ addr - VDSO_OFFSET(VDSO_VVAR_PAGE),
+ __pa_symbol(&__vvar_page) >> PAGE_SHIFT,
+ PAGE_SIZE,
+ PAGE_READONLY);
+
+ if (ret)
+ goto up_fail;
- if (compat_uses_vma || !compat) {
- /*
- * MAYWRITE to allow gdb to COW and set breakpoints
- */
- ret = install_special_mapping(mm, addr, PAGE_SIZE,
- VM_READ|VM_EXEC|
- VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
- vdso32_pages);
+#ifdef CONFIG_HPET_TIMER
+ if (hpet_address) {
+ ret = io_remap_pfn_range(vma,
+ addr - VDSO_OFFSET(VDSO_HPET_PAGE),
+ hpet_address >> PAGE_SHIFT,
+ PAGE_SIZE,
+ pgprot_noncached(PAGE_READONLY));
if (ret)
goto up_fail;
}
+#endif
current_thread_info()->sysenter_return =
VDSO32_SYMBOL(addr, SYSENTER_RETURN);
@@ -411,20 +280,12 @@ const char *arch_vma_name(struct vm_area_struct *vma)
struct vm_area_struct *get_gate_vma(struct mm_struct *mm)
{
- /*
- * Check to see if the corresponding 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 mm_struct *mm, unsigned long addr)
{
- const struct vm_area_struct *vma = get_gate_vma(mm);
-
- return vma && addr >= vma->vm_start && addr < vma->vm_end;
+ return 0;
}
int in_gate_area_no_mm(unsigned long addr)
diff --git a/arch/x86/vdso/vdso32.S b/arch/x86/vdso/vdso32.S
index 2ce5f82c333b..018bcd9f97b4 100644
--- a/arch/x86/vdso/vdso32.S
+++ b/arch/x86/vdso/vdso32.S
@@ -1,22 +1,9 @@
-#include <linux/init.h>
+#include <asm/vdso.h>
-__INITDATA
+DEFINE_VDSO_IMAGE(vdso32_int80, "arch/x86/vdso/vdso32-int80.so")
- .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"
+DEFINE_VDSO_IMAGE(vdso32_syscall, "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
+DEFINE_VDSO_IMAGE(vdso32_sysenter, "arch/x86/vdso/vdso32-sysenter.so")
diff --git a/arch/x86/vdso/vdso32/vclock_gettime.c b/arch/x86/vdso/vdso32/vclock_gettime.c
new file mode 100644
index 000000000000..175cc72c0f68
--- /dev/null
+++ b/arch/x86/vdso/vdso32/vclock_gettime.c
@@ -0,0 +1,30 @@
+#define BUILD_VDSO32
+
+#ifndef CONFIG_CC_OPTIMIZE_FOR_SIZE
+#undef CONFIG_OPTIMIZE_INLINING
+#endif
+
+#undef CONFIG_X86_PPRO_FENCE
+
+#ifdef CONFIG_X86_64
+
+/*
+ * in case of a 32 bit VDSO for a 64 bit kernel fake a 32 bit kernel
+ * configuration
+ */
+#undef CONFIG_64BIT
+#undef CONFIG_X86_64
+#undef CONFIG_ILLEGAL_POINTER_VALUE
+#undef CONFIG_SPARSEMEM_VMEMMAP
+#undef CONFIG_NR_CPUS
+
+#define CONFIG_X86_32 1
+#define CONFIG_PAGE_OFFSET 0
+#define CONFIG_ILLEGAL_POINTER_VALUE 0
+#define CONFIG_NR_CPUS 1
+
+#define BUILD_VDSO32_64
+
+#endif
+
+#include "../vclock_gettime.c"
diff --git a/arch/x86/vdso/vdso32/vdso32.lds.S b/arch/x86/vdso/vdso32/vdso32.lds.S
index 976124bb5f92..aadb8b9994cd 100644
--- a/arch/x86/vdso/vdso32/vdso32.lds.S
+++ b/arch/x86/vdso/vdso32/vdso32.lds.S
@@ -8,7 +8,11 @@
* values visible using the asm-x86/vdso.h macros from the kernel proper.
*/
+#include <asm/page.h>
+
+#define BUILD_VDSO32
#define VDSO_PRELINK 0
+
#include "../vdso-layout.lds.S"
/* The ELF entry point can be used to set the AT_SYSINFO value. */
@@ -19,6 +23,13 @@ ENTRY(__kernel_vsyscall);
*/
VERSION
{
+ LINUX_2.6 {
+ global:
+ __vdso_clock_gettime;
+ __vdso_gettimeofday;
+ __vdso_time;
+ };
+
LINUX_2.5 {
global:
__kernel_vsyscall;
@@ -31,7 +42,9 @@ VERSION
/*
* 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;
+VDSO32_clock_gettime = clock_gettime;
+VDSO32_gettimeofday = gettimeofday;
+VDSO32_time = time;
diff --git a/arch/x86/vdso/vdsox32.S b/arch/x86/vdso/vdsox32.S
index 295f1c7543d8..f4aa34e7f370 100644
--- a/arch/x86/vdso/vdsox32.S
+++ b/arch/x86/vdso/vdsox32.S
@@ -1,21 +1,3 @@
-#include <asm/page_types.h>
-#include <linux/linkage.h>
+#include <asm/vdso.h>
-__PAGE_ALIGNED_DATA
-
- .globl vdsox32_start, vdsox32_end
- .align PAGE_SIZE
-vdsox32_start:
- .incbin "arch/x86/vdso/vdsox32.so"
-vdsox32_end:
- .align PAGE_SIZE /* extra data here leaks to userspace. */
-
-.previous
-
- .globl vdsox32_pages
- .bss
- .align 8
- .type vdsox32_pages, @object
-vdsox32_pages:
- .zero (vdsox32_end - vdsox32_start + PAGE_SIZE - 1) / PAGE_SIZE * 8
- .size vdsox32_pages, .-vdsox32_pages
+DEFINE_VDSO_IMAGE(vdsox32, "arch/x86/vdso/vdsox32.so")
diff --git a/arch/x86/vdso/vma.c b/arch/x86/vdso/vma.c
index 431e87544411..1ad102613127 100644
--- a/arch/x86/vdso/vma.c
+++ b/arch/x86/vdso/vma.c
@@ -16,20 +16,22 @@
#include <asm/vdso.h>
#include <asm/page.h>
+#if defined(CONFIG_X86_64)
unsigned int __read_mostly vdso_enabled = 1;
-extern char vdso_start[], vdso_end[];
+DECLARE_VDSO_IMAGE(vdso);
extern unsigned short vdso_sync_cpuid;
-
-extern struct page *vdso_pages[];
static unsigned vdso_size;
#ifdef CONFIG_X86_X32_ABI
-extern char vdsox32_start[], vdsox32_end[];
-extern struct page *vdsox32_pages[];
+DECLARE_VDSO_IMAGE(vdsox32);
static unsigned vdsox32_size;
+#endif
+#endif
-static void __init patch_vdsox32(void *vdso, size_t len)
+#if defined(CONFIG_X86_32) || defined(CONFIG_X86_X32_ABI) || \
+ defined(CONFIG_COMPAT)
+void __init patch_vdso32(void *vdso, size_t len)
{
Elf32_Ehdr *hdr = vdso;
Elf32_Shdr *sechdrs, *alt_sec = 0;
@@ -52,7 +54,7 @@ static void __init patch_vdsox32(void *vdso, size_t len)
}
/* If we get here, it's probably a bug. */
- pr_warning("patch_vdsox32: .altinstructions not found\n");
+ pr_warning("patch_vdso32: .altinstructions not found\n");
return; /* nothing to patch */
found:
@@ -61,6 +63,7 @@ found:
}
#endif
+#if defined(CONFIG_X86_64)
static void __init patch_vdso64(void *vdso, size_t len)
{
Elf64_Ehdr *hdr = vdso;
@@ -104,7 +107,7 @@ static int __init init_vdso(void)
vdso_pages[i] = virt_to_page(vdso_start + i*PAGE_SIZE);
#ifdef CONFIG_X86_X32_ABI
- patch_vdsox32(vdsox32_start, vdsox32_end - vdsox32_start);
+ patch_vdso32(vdsox32_start, vdsox32_end - vdsox32_start);
npages = (vdsox32_end - vdsox32_start + PAGE_SIZE - 1) / PAGE_SIZE;
vdsox32_size = npages << PAGE_SHIFT;
for (i = 0; i < npages; i++)
@@ -204,3 +207,4 @@ static __init int vdso_setup(char *s)
return 0;
}
__setup("vdso=", vdso_setup);
+#endif
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.