diff options
Diffstat (limited to 'kernel/arch/x86/vdso')
22 files changed, 2142 insertions, 0 deletions
diff --git a/kernel/arch/x86/vdso/.gitignore b/kernel/arch/x86/vdso/.gitignore new file mode 100644 index 000000000..aae8ffdd5 --- /dev/null +++ b/kernel/arch/x86/vdso/.gitignore @@ -0,0 +1,7 @@ +vdso.lds +vdsox32.lds +vdso32-syscall-syms.lds +vdso32-sysenter-syms.lds +vdso32-int80-syms.lds +vdso-image-*.c +vdso2c diff --git a/kernel/arch/x86/vdso/Makefile b/kernel/arch/x86/vdso/Makefile new file mode 100644 index 000000000..e97032069 --- /dev/null +++ b/kernel/arch/x86/vdso/Makefile @@ -0,0 +1,209 @@ +# +# Building vDSO images for x86. +# + +KBUILD_CFLAGS += $(DISABLE_LTO) +KASAN_SANITIZE := n + +VDSO64-$(CONFIG_X86_64) := y +VDSOX32-$(CONFIG_X86_X32_ABI) := y +VDSO32-$(CONFIG_X86_32) := y +VDSO32-$(CONFIG_COMPAT) := y + +# files to link into the vdso +vobjs-y := vdso-note.o vclock_gettime.o vgetcpu.o + +# files to link into kernel +obj-y += vma.o + +# vDSO images to build +vdso_img-$(VDSO64-y) += 64 +vdso_img-$(VDSOX32-y) += x32 +vdso_img-$(VDSO32-y) += 32-int80 +vdso_img-$(CONFIG_COMPAT) += 32-syscall +vdso_img-$(VDSO32-y) += 32-sysenter + +obj-$(VDSO32-y) += vdso32-setup.o + +vobjs := $(foreach F,$(vobjs-y),$(obj)/$F) + +$(obj)/vdso.o: $(obj)/vdso.so + +targets += vdso.lds $(vobjs-y) + +# Build the vDSO image C files and link them in. +vdso_img_objs := $(vdso_img-y:%=vdso-image-%.o) +vdso_img_cfiles := $(vdso_img-y:%=vdso-image-%.c) +vdso_img_sodbg := $(vdso_img-y:%=vdso%.so.dbg) +obj-y += $(vdso_img_objs) +targets += $(vdso_img_cfiles) +targets += $(vdso_img_sodbg) +.SECONDARY: $(vdso_img-y:%=$(obj)/vdso-image-%.c) \ + $(vdso_img-y:%=$(obj)/vdso%.so) + +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 \ + $(DISABLE_LTO) + +$(obj)/vdso64.so.dbg: $(src)/vdso.lds $(vobjs) FORCE + $(call if_changed,vdso) + +HOST_EXTRACFLAGS += -I$(srctree)/tools/include -I$(srctree)/include/uapi -I$(srctree)/arch/x86/include/uapi +hostprogs-y += vdso2c + +quiet_cmd_vdso2c = VDSO2C $@ +define cmd_vdso2c + $(obj)/vdso2c $< $(<:%.dbg=%) $@ +endef + +$(obj)/vdso-image-%.c: $(obj)/vdso%.so.dbg $(obj)/vdso%.so $(obj)/vdso2c FORCE + $(call if_changed,vdso2c) + +# +# Don't omit frame pointers for ease of userspace debugging, but do +# optimize sibling calls. +# +CFL := $(PROFILING) -mcmodel=small -fPIC -O2 -fasynchronous-unwind-tables -m64 \ + $(filter -g%,$(KBUILD_CFLAGS)) $(call cc-option, -fno-stack-protector) \ + -fno-omit-frame-pointer -foptimize-sibling-calls \ + -DDISABLE_BRANCH_PROFILING + +$(vobjs): KBUILD_CFLAGS += $(CFL) + +# +# vDSO code runs in userspace and -pg doesn't help with profiling anyway. +# +CFLAGS_REMOVE_vdso-note.o = -pg +CFLAGS_REMOVE_vclock_gettime.o = -pg +CFLAGS_REMOVE_vgetcpu.o = -pg +CFLAGS_REMOVE_vvar.o = -pg + +# +# X32 processes use x32 vDSO to access 64bit kernel data. +# +# Build x32 vDSO image: +# 1. Compile x32 vDSO as 64bit. +# 2. Convert object files to x32. +# 3. Build x32 VDSO image with x32 objects, which contains 64bit codes +# so that it can reach 64bit address space with 64bit pointers. +# + +CPPFLAGS_vdsox32.lds = $(CPPFLAGS_vdso.lds) +VDSO_LDFLAGS_vdsox32.lds = -Wl,-m,elf32_x86_64 \ + -Wl,-soname=linux-vdso.so.1 \ + -Wl,-z,max-page-size=4096 \ + -Wl,-z,common-page-size=4096 + +# 64-bit objects to re-brand as x32 +vobjs64-for-x32 := $(filter-out $(vobjs-nox32),$(vobjs-y)) + +# x32-rebranded versions +vobjx32s-y := $(vobjs64-for-x32:.o=-x32.o) + +# same thing, but in the output directory +vobjx32s := $(foreach F,$(vobjx32s-y),$(obj)/$F) + +# Convert 64bit object file to x32 for x32 vDSO. +quiet_cmd_x32 = X32 $@ + cmd_x32 = $(OBJCOPY) -O elf32-x86-64 $< $@ + +$(obj)/%-x32.o: $(obj)/%.o FORCE + $(call if_changed,x32) + +targets += vdsox32.lds $(vobjx32s-y) + +$(obj)/%.so: OBJCOPYFLAGS := -S +$(obj)/%.so: $(obj)/%.so.dbg + $(call if_changed,objcopy) + +$(obj)/vdsox32.so.dbg: $(src)/vdsox32.lds $(vobjx32s) FORCE + $(call if_changed,vdso) + +# +# Build multiple 32-bit vDSO images to choose from at boot time. +# +vdso32.so-$(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,-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. +override obj-dirs = $(dir $(obj)) $(obj)/vdso32/ + +targets += vdso32/vdso32.lds +targets += vdso32/note.o vdso32/vclock_gettime.o $(vdso32.so-y:%=vdso32/%.o) +targets += vdso32/vclock_gettime.o + +$(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 + +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 += $(call cc-option, -foptimize-sibling-calls) +KBUILD_CFLAGS_32 += -fno-omit-frame-pointer +KBUILD_CFLAGS_32 += -DDISABLE_BRANCH_PROFILING +$(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) + +# +# 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,$^) $(filter %.o,$^) && \ + sh $(srctree)/$(src)/checkundef.sh '$(NM)' '$@' + +VDSO_LDFLAGS = -fPIC -shared $(call cc-ldoption, -Wl$(comma)--hash-style=sysv) \ + $(call cc-ldoption, -Wl$(comma)--build-id) -Wl,-Bsymbolic $(LTO_CFLAGS) +GCOV_PROFILE := n + +# +# Install the unstripped copies of vdso*.so. If our toolchain supports +# build-id, install .build-id links as well. +# +quiet_cmd_vdso_install = INSTALL $(@:install_%=%) +define cmd_vdso_install + cp $< "$(MODLIB)/vdso/$(@:install_%=%)"; \ + if readelf -n $< |grep -q 'Build ID'; then \ + buildid=`readelf -n $< |grep 'Build ID' |sed -e 's/^.*Build ID: \(.*\)$$/\1/'`; \ + first=`echo $$buildid | cut -b-2`; \ + last=`echo $$buildid | cut -b3-`; \ + mkdir -p "$(MODLIB)/vdso/.build-id/$$first"; \ + ln -sf "../../$(@:install_%=%)" "$(MODLIB)/vdso/.build-id/$$first/$$last.debug"; \ + fi +endef + +vdso_img_insttargets := $(vdso_img_sodbg:%.dbg=install_%) + +$(MODLIB)/vdso: FORCE + @mkdir -p $(MODLIB)/vdso + +$(vdso_img_insttargets): install_%: $(obj)/%.dbg $(MODLIB)/vdso FORCE + $(call cmd,vdso_install) + +PHONY += vdso_install $(vdso_img_insttargets) +vdso_install: $(vdso_img_insttargets) FORCE + +clean-files := vdso32-syscall* vdso32-sysenter* vdso32-int80* vdso64* vdso-image-*.c vdsox32.so* diff --git a/kernel/arch/x86/vdso/checkundef.sh b/kernel/arch/x86/vdso/checkundef.sh new file mode 100755 index 000000000..7ee90a9b5 --- /dev/null +++ b/kernel/arch/x86/vdso/checkundef.sh @@ -0,0 +1,10 @@ +#!/bin/sh +nm="$1" +file="$2" +$nm "$file" | grep '^ *U' > /dev/null 2>&1 +if [ $? -eq 1 ]; then + exit 0 +else + echo "$file: undefined symbols found" >&2 + exit 1 +fi diff --git a/kernel/arch/x86/vdso/vclock_gettime.c b/kernel/arch/x86/vdso/vclock_gettime.c new file mode 100644 index 000000000..979332275 --- /dev/null +++ b/kernel/arch/x86/vdso/vclock_gettime.c @@ -0,0 +1,351 @@ +/* + * Copyright 2006 Andi Kleen, SUSE Labs. + * Subject to the GNU Public License, v.2 + * + * 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. + */ + +#include <uapi/linux/time.h> +#include <asm/vgtod.h> +#include <asm/hpet.h> +#include <asm/vvar.h> +#include <asm/unistd.h> +#include <asm/msr.h> +#include <linux/math64.h> +#include <linux/time.h> + +#define gtod (&VVAR(vsyscall_gtod_data)) + +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 +extern u8 hpet_page + __attribute__((visibility("hidden"))); + +static notrace cycle_t vread_hpet(void) +{ + return *(const volatile u32 *)(&hpet_page + HPET_COUNTER); +} +#endif + +#ifndef BUILD_VDSO32 + +#include <linux/kernel.h> +#include <asm/vsyscall.h> +#include <asm/fixmap.h> +#include <asm/pvclock.h> + +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 long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz) +{ + long ret; + + asm("syscall" : "=a" (ret) : + "0" (__NR_gettimeofday), "D" (tv), "S" (tz) : "memory"); + return ret; +} + +#ifdef CONFIG_PARAVIRT_CLOCK + +static notrace const struct pvclock_vsyscall_time_info *get_pvti(int cpu) +{ + const struct pvclock_vsyscall_time_info *pvti_base; + int idx = cpu / (PAGE_SIZE/PVTI_SIZE); + int offset = cpu % (PAGE_SIZE/PVTI_SIZE); + + BUG_ON(PVCLOCK_FIXMAP_BEGIN + idx > PVCLOCK_FIXMAP_END); + + pvti_base = (struct pvclock_vsyscall_time_info *) + __fix_to_virt(PVCLOCK_FIXMAP_BEGIN+idx); + + return &pvti_base[offset]; +} + +static notrace cycle_t vread_pvclock(int *mode) +{ + const struct pvclock_vsyscall_time_info *pvti; + cycle_t ret; + u64 last; + u32 version; + u8 flags; + unsigned cpu, cpu1; + + + /* + * Note: hypervisor must guarantee that: + * 1. cpu ID number maps 1:1 to per-CPU pvclock time info. + * 2. that per-CPU pvclock time info is updated if the + * underlying CPU changes. + * 3. that version is increased whenever underlying CPU + * changes. + * + */ + do { + cpu = __getcpu() & VGETCPU_CPU_MASK; + /* TODO: We can put vcpu id into higher bits of pvti.version. + * This will save a couple of cycles by getting rid of + * __getcpu() calls (Gleb). + */ + + pvti = get_pvti(cpu); + + version = __pvclock_read_cycles(&pvti->pvti, &ret, &flags); + + /* + * Test we're still on the cpu as well as the version. + * We could have been migrated just after the first + * vgetcpu but before fetching the version, so we + * wouldn't notice a version change. + */ + cpu1 = __getcpu() & VGETCPU_CPU_MASK; + } while (unlikely(cpu != cpu1 || + (pvti->pvti.version & 1) || + pvti->pvti.version != version)); + + if (unlikely(!(flags & PVCLOCK_TSC_STABLE_BIT))) + *mode = VCLOCK_NONE; + + /* refer to tsc.c read_tsc() comment for rationale */ + last = gtod->cycle_last; + + if (likely(ret >= last)) + return ret; + + return last; +} +#endif + +#else + +notrace static long vdso_fallback_gettime(long clock, struct timespec *ts) +{ + long ret; + + asm( + "mov %%ebx, %%edx \n" + "mov %2, %%ebx \n" + "call __kernel_vsyscall \n" + "mov %%edx, %%ebx \n" + : "=a" (ret) + : "0" (__NR_clock_gettime), "g" (clock), "c" (ts) + : "memory", "edx"); + return ret; +} + +notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz) +{ + long ret; + + asm( + "mov %%ebx, %%edx \n" + "mov %2, %%ebx \n" + "call __kernel_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) +{ + u64 v; + cycles_t cycles; + + if (gtod->vclock_mode == VCLOCK_TSC) + cycles = vread_tsc(); +#ifdef CONFIG_HPET_TIMER + else if (gtod->vclock_mode == VCLOCK_HPET) + cycles = vread_hpet(); +#endif +#ifdef CONFIG_PARAVIRT_CLOCK + else if (gtod->vclock_mode == VCLOCK_PVCLOCK) + cycles = vread_pvclock(mode); +#endif + else + return 0; + v = (cycles - gtod->cycle_last) & gtod->mask; + return v * gtod->mult; +} + +/* Code size doesn't matter (vdso is 4k anyway) and this is faster. */ +notrace static int __always_inline do_realtime(struct timespec *ts) +{ + unsigned long seq; + u64 ns; + int mode; + + do { + 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->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 __always_inline do_monotonic(struct timespec *ts) +{ + unsigned long seq; + u64 ns; + int mode; + + do { + 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->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 void do_realtime_coarse(struct timespec *ts) +{ + unsigned long seq; + do { + 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 void do_monotonic_coarse(struct timespec *ts) +{ + unsigned long seq; + do { + 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) +{ + switch (clock) { + case CLOCK_REALTIME: + if (do_realtime(ts) == VCLOCK_NONE) + goto fallback; + break; + case CLOCK_MONOTONIC: + if (do_monotonic(ts) == VCLOCK_NONE) + goto fallback; + break; + case CLOCK_REALTIME_COARSE: + do_realtime_coarse(ts); + break; + case CLOCK_MONOTONIC_COARSE: + do_monotonic_coarse(ts); + break; + default: + goto fallback; + } + + 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) +{ + if (likely(tv != NULL)) { + if (unlikely(do_realtime((struct timespec *)tv) == VCLOCK_NONE)) + return vdso_fallback_gtod(tv, tz); + tv->tv_usec /= 1000; + } + if (unlikely(tz != NULL)) { + tz->tz_minuteswest = gtod->tz_minuteswest; + tz->tz_dsttime = gtod->tz_dsttime; + } + + return 0; +} +int gettimeofday(struct timeval *, struct timezone *) + __attribute__((weak, alias("__vdso_gettimeofday"))); + +/* + * This will break when the xtime seconds get inaccurate, but that is + * unlikely + */ +notrace time_t __vdso_time(time_t *t) +{ + /* 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; + return result; +} +int time(time_t *t) + __attribute__((weak, alias("__vdso_time"))); diff --git a/kernel/arch/x86/vdso/vdso-layout.lds.S b/kernel/arch/x86/vdso/vdso-layout.lds.S new file mode 100644 index 000000000..de2c92102 --- /dev/null +++ b/kernel/arch/x86/vdso/vdso-layout.lds.S @@ -0,0 +1,118 @@ +#include <asm/vdso.h> + +/* + * 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. + */ + +#if defined(BUILD_VDSO64) +# define SHDR_SIZE 64 +#elif defined(BUILD_VDSO32) || defined(BUILD_VDSOX32) +# define SHDR_SIZE 40 +#else +# error unknown VDSO target +#endif + +#define NUM_FAKE_SHDRS 13 + +SECTIONS +{ + /* + * User/kernel shared data is before the vDSO. This may be a little + * uglier than putting it after the vDSO, but it avoids issues with + * non-allocatable things that dangle past the end of the PT_LOAD + * segment. + */ + + vvar_start = . - 2 * PAGE_SIZE; + vvar_page = vvar_start; + + /* Place all vvars at the offsets in asm/vvar.h. */ +#define EMIT_VVAR(name, offset) vvar_ ## name = vvar_page + offset; +#define __VVAR_KERNEL_LDS +#include <asm/vvar.h> +#undef __VVAR_KERNEL_LDS +#undef EMIT_VVAR + + hpet_page = vvar_start + PAGE_SIZE; + + . = 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) } + + .dynamic : { *(.dynamic) } :text :dynamic + + .rodata : { + *(.rodata*) + *(.data*) + *(.sdata*) + *(.got.plt) *(.got) + *(.gnu.linkonce.d.*) + *(.bss*) + *(.dynbss*) + *(.gnu.linkonce.b.*) + + /* + * Ideally this would live in a C file, but that won't + * work cleanly for x32 until we start building the x32 + * C code using an x32 toolchain. + */ + VDSO_FAKE_SECTION_TABLE_START = .; + . = . + NUM_FAKE_SHDRS * SHDR_SIZE; + VDSO_FAKE_SECTION_TABLE_END = .; + } :text + + .fake_shstrtab : { *(.fake_shstrtab) } :text + + + .note : { *(.note.*) } :text :note + + .eh_frame_hdr : { *(.eh_frame_hdr) } :text :eh_frame_hdr + .eh_frame : { KEEP (*(.eh_frame)) } :text + + + /* + * Text is well-separated from actual data: there's plenty of + * stuff that isn't used at runtime in between. + */ + + .text : { *(.text*) } :text =0x90909090, + + /* + * At the end so that eu-elflint stays happy when vdso2c strips + * these. A better implementation would avoid allocating space + * for these. + */ + .altinstructions : { *(.altinstructions) } :text + .altinstr_replacement : { *(.altinstr_replacement) } :text + + /DISCARD/ : { + *(.discard) + *(.discard.*) + *(__bug_table) + } +} + +/* + * 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; +} diff --git a/kernel/arch/x86/vdso/vdso-note.S b/kernel/arch/x86/vdso/vdso-note.S new file mode 100644 index 000000000..79a071e43 --- /dev/null +++ b/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 diff --git a/kernel/arch/x86/vdso/vdso.lds.S b/kernel/arch/x86/vdso/vdso.lds.S new file mode 100644 index 000000000..680793264 --- /dev/null +++ b/kernel/arch/x86/vdso/vdso.lds.S @@ -0,0 +1,29 @@ +/* + * Linker script for 64-bit vDSO. + * We #include the file to define the layout details. + * + * This file defines the version script giving the user-exported symbols in + * the DSO. + */ + +#define BUILD_VDSO64 + +#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; + time; + __vdso_time; + local: *; + }; +} diff --git a/kernel/arch/x86/vdso/vdso2c.c b/kernel/arch/x86/vdso/vdso2c.c new file mode 100644 index 000000000..8627db24a --- /dev/null +++ b/kernel/arch/x86/vdso/vdso2c.c @@ -0,0 +1,253 @@ +/* + * vdso2c - A vdso image preparation tool + * Copyright (c) 2014 Andy Lutomirski and others + * Licensed under the GPL v2 + * + * vdso2c requires stripped and unstripped input. It would be trivial + * to fully strip the input in here, but, for reasons described below, + * we need to write a section table. Doing this is more or less + * equivalent to dropping all non-allocatable sections, but it's + * easier to let objcopy handle that instead of doing it ourselves. + * If we ever need to do something fancier than what objcopy provides, + * it would be straightforward to add here. + * + * We're keep a section table for a few reasons: + * + * The Go runtime had a couple of bugs: it would read the section + * table to try to figure out how many dynamic symbols there were (it + * shouldn't have looked at the section table at all) and, if there + * were no SHT_SYNDYM section table entry, it would use an + * uninitialized value for the number of symbols. An empty DYNSYM + * table would work, but I see no reason not to write a valid one (and + * keep full performance for old Go programs). This hack is only + * needed on x86_64. + * + * The bug was introduced on 2012-08-31 by: + * https://code.google.com/p/go/source/detail?r=56ea40aac72b + * and was fixed on 2014-06-13 by: + * https://code.google.com/p/go/source/detail?r=fc1cd5e12595 + * + * Binutils has issues debugging the vDSO: it reads the section table to + * find SHT_NOTE; it won't look at PT_NOTE for the in-memory vDSO, which + * would break build-id if we removed the section table. Binutils + * also requires that shstrndx != 0. See: + * https://sourceware.org/bugzilla/show_bug.cgi?id=17064 + * + * elfutils might not look for PT_NOTE if there is a section table at + * all. I don't know whether this matters for any practical purpose. + * + * For simplicity, rather than hacking up a partial section table, we + * just write a mostly complete one. We omit non-dynamic symbols, + * though, since they're rather large. + * + * Once binutils gets fixed, we might be able to drop this for all but + * the 64-bit vdso, since build-id only works in kernel RPMs, and + * systems that update to new enough kernel RPMs will likely update + * binutils in sync. build-id has never worked for home-built kernel + * RPMs without manual symlinking, and I suspect that no one ever does + * that. + */ + +#include <inttypes.h> +#include <stdint.h> +#include <unistd.h> +#include <stdarg.h> +#include <stdlib.h> +#include <stdio.h> +#include <string.h> +#include <fcntl.h> +#include <err.h> + +#include <sys/mman.h> +#include <sys/types.h> + +#include <tools/le_byteshift.h> + +#include <linux/elf.h> +#include <linux/types.h> + +const char *outfilename; + +/* Symbols that we need in vdso2c. */ +enum { + sym_vvar_start, + sym_vvar_page, + sym_hpet_page, + sym_VDSO_FAKE_SECTION_TABLE_START, + sym_VDSO_FAKE_SECTION_TABLE_END, +}; + +const int special_pages[] = { + sym_vvar_page, + sym_hpet_page, +}; + +struct vdso_sym { + const char *name; + bool export; +}; + +struct vdso_sym required_syms[] = { + [sym_vvar_start] = {"vvar_start", true}, + [sym_vvar_page] = {"vvar_page", true}, + [sym_hpet_page] = {"hpet_page", true}, + [sym_VDSO_FAKE_SECTION_TABLE_START] = { + "VDSO_FAKE_SECTION_TABLE_START", false + }, + [sym_VDSO_FAKE_SECTION_TABLE_END] = { + "VDSO_FAKE_SECTION_TABLE_END", false + }, + {"VDSO32_NOTE_MASK", true}, + {"VDSO32_SYSENTER_RETURN", true}, + {"__kernel_vsyscall", true}, + {"__kernel_sigreturn", true}, + {"__kernel_rt_sigreturn", true}, +}; + +__attribute__((format(printf, 1, 2))) __attribute__((noreturn)) +static void fail(const char *format, ...) +{ + va_list ap; + va_start(ap, format); + fprintf(stderr, "Error: "); + vfprintf(stderr, format, ap); + if (outfilename) + unlink(outfilename); + exit(1); + va_end(ap); +} + +/* + * Evil macros for little-endian reads and writes + */ +#define GLE(x, bits, ifnot) \ + __builtin_choose_expr( \ + (sizeof(*(x)) == bits/8), \ + (__typeof__(*(x)))get_unaligned_le##bits(x), ifnot) + +extern void bad_get_le(void); +#define LAST_GLE(x) \ + __builtin_choose_expr(sizeof(*(x)) == 1, *(x), bad_get_le()) + +#define GET_LE(x) \ + GLE(x, 64, GLE(x, 32, GLE(x, 16, LAST_GLE(x)))) + +#define PLE(x, val, bits, ifnot) \ + __builtin_choose_expr( \ + (sizeof(*(x)) == bits/8), \ + put_unaligned_le##bits((val), (x)), ifnot) + +extern void bad_put_le(void); +#define LAST_PLE(x, val) \ + __builtin_choose_expr(sizeof(*(x)) == 1, *(x) = (val), bad_put_le()) + +#define PUT_LE(x, val) \ + PLE(x, val, 64, PLE(x, val, 32, PLE(x, val, 16, LAST_PLE(x, val)))) + + +#define NSYMS (sizeof(required_syms) / sizeof(required_syms[0])) + +#define BITSFUNC3(name, bits, suffix) name##bits##suffix +#define BITSFUNC2(name, bits, suffix) BITSFUNC3(name, bits, suffix) +#define BITSFUNC(name) BITSFUNC2(name, ELF_BITS, ) + +#define INT_BITS BITSFUNC2(int, ELF_BITS, _t) + +#define ELF_BITS_XFORM2(bits, x) Elf##bits##_##x +#define ELF_BITS_XFORM(bits, x) ELF_BITS_XFORM2(bits, x) +#define ELF(x) ELF_BITS_XFORM(ELF_BITS, x) + +#define ELF_BITS 64 +#include "vdso2c.h" +#undef ELF_BITS + +#define ELF_BITS 32 +#include "vdso2c.h" +#undef ELF_BITS + +static void go(void *raw_addr, size_t raw_len, + void *stripped_addr, size_t stripped_len, + FILE *outfile, const char *name) +{ + Elf64_Ehdr *hdr = (Elf64_Ehdr *)raw_addr; + + if (hdr->e_ident[EI_CLASS] == ELFCLASS64) { + go64(raw_addr, raw_len, stripped_addr, stripped_len, + outfile, name); + } else if (hdr->e_ident[EI_CLASS] == ELFCLASS32) { + go32(raw_addr, raw_len, stripped_addr, stripped_len, + outfile, name); + } else { + fail("unknown ELF class\n"); + } +} + +static void map_input(const char *name, void **addr, size_t *len, int prot) +{ + off_t tmp_len; + + int fd = open(name, O_RDONLY); + if (fd == -1) + err(1, "%s", name); + + tmp_len = lseek(fd, 0, SEEK_END); + if (tmp_len == (off_t)-1) + err(1, "lseek"); + *len = (size_t)tmp_len; + + *addr = mmap(NULL, tmp_len, prot, MAP_PRIVATE, fd, 0); + if (*addr == MAP_FAILED) + err(1, "mmap"); + + close(fd); +} + +int main(int argc, char **argv) +{ + size_t raw_len, stripped_len; + void *raw_addr, *stripped_addr; + FILE *outfile; + char *name, *tmp; + int namelen; + + if (argc != 4) { + printf("Usage: vdso2c RAW_INPUT STRIPPED_INPUT OUTPUT\n"); + return 1; + } + + /* + * Figure out the struct name. If we're writing to a .so file, + * generate raw output insted. + */ + name = strdup(argv[3]); + namelen = strlen(name); + if (namelen >= 3 && !strcmp(name + namelen - 3, ".so")) { + name = NULL; + } else { + tmp = strrchr(name, '/'); + if (tmp) + name = tmp + 1; + tmp = strchr(name, '.'); + if (tmp) + *tmp = '\0'; + for (tmp = name; *tmp; tmp++) + if (*tmp == '-') + *tmp = '_'; + } + + map_input(argv[1], &raw_addr, &raw_len, PROT_READ); + map_input(argv[2], &stripped_addr, &stripped_len, PROT_READ); + + outfilename = argv[3]; + outfile = fopen(outfilename, "w"); + if (!outfile) + err(1, "%s", argv[2]); + + go(raw_addr, raw_len, stripped_addr, stripped_len, outfile, name); + + munmap(raw_addr, raw_len); + munmap(stripped_addr, stripped_len); + fclose(outfile); + + return 0; +} diff --git a/kernel/arch/x86/vdso/vdso2c.h b/kernel/arch/x86/vdso/vdso2c.h new file mode 100644 index 000000000..022498755 --- /dev/null +++ b/kernel/arch/x86/vdso/vdso2c.h @@ -0,0 +1,175 @@ +/* + * This file is included twice from vdso2c.c. It generates code for 32-bit + * and 64-bit vDSOs. We need both for 64-bit builds, since 32-bit vDSOs + * are built for 32-bit userspace. + */ + +static void BITSFUNC(go)(void *raw_addr, size_t raw_len, + void *stripped_addr, size_t stripped_len, + FILE *outfile, const char *name) +{ + int found_load = 0; + unsigned long load_size = -1; /* Work around bogus warning */ + unsigned long mapping_size; + ELF(Ehdr) *hdr = (ELF(Ehdr) *)raw_addr; + int i; + unsigned long j; + ELF(Shdr) *symtab_hdr = NULL, *strtab_hdr, *secstrings_hdr, + *alt_sec = NULL; + ELF(Dyn) *dyn = 0, *dyn_end = 0; + const char *secstrings; + INT_BITS syms[NSYMS] = {}; + + ELF(Phdr) *pt = (ELF(Phdr) *)(raw_addr + GET_LE(&hdr->e_phoff)); + + /* Walk the segment table. */ + for (i = 0; i < GET_LE(&hdr->e_phnum); i++) { + if (GET_LE(&pt[i].p_type) == PT_LOAD) { + if (found_load) + fail("multiple PT_LOAD segs\n"); + + if (GET_LE(&pt[i].p_offset) != 0 || + GET_LE(&pt[i].p_vaddr) != 0) + fail("PT_LOAD in wrong place\n"); + + if (GET_LE(&pt[i].p_memsz) != GET_LE(&pt[i].p_filesz)) + fail("cannot handle memsz != filesz\n"); + + load_size = GET_LE(&pt[i].p_memsz); + found_load = 1; + } else if (GET_LE(&pt[i].p_type) == PT_DYNAMIC) { + dyn = raw_addr + GET_LE(&pt[i].p_offset); + dyn_end = raw_addr + GET_LE(&pt[i].p_offset) + + GET_LE(&pt[i].p_memsz); + } + } + if (!found_load) + fail("no PT_LOAD seg\n"); + + if (stripped_len < load_size) + fail("stripped input is too short\n"); + + /* Walk the dynamic table */ + for (i = 0; dyn + i < dyn_end && + GET_LE(&dyn[i].d_tag) != DT_NULL; i++) { + typeof(dyn[i].d_tag) tag = GET_LE(&dyn[i].d_tag); + if (tag == DT_REL || tag == DT_RELSZ || tag == DT_RELA || + tag == DT_RELENT || tag == DT_TEXTREL) + fail("vdso image contains dynamic relocations\n"); + } + + /* Walk the section table */ + secstrings_hdr = raw_addr + GET_LE(&hdr->e_shoff) + + GET_LE(&hdr->e_shentsize)*GET_LE(&hdr->e_shstrndx); + secstrings = raw_addr + GET_LE(&secstrings_hdr->sh_offset); + for (i = 0; i < GET_LE(&hdr->e_shnum); i++) { + ELF(Shdr) *sh = raw_addr + GET_LE(&hdr->e_shoff) + + GET_LE(&hdr->e_shentsize) * i; + if (GET_LE(&sh->sh_type) == SHT_SYMTAB) + symtab_hdr = sh; + + if (!strcmp(secstrings + GET_LE(&sh->sh_name), + ".altinstructions")) + alt_sec = sh; + } + + if (!symtab_hdr) + fail("no symbol table\n"); + + strtab_hdr = raw_addr + GET_LE(&hdr->e_shoff) + + GET_LE(&hdr->e_shentsize) * GET_LE(&symtab_hdr->sh_link); + + /* Walk the symbol table */ + for (i = 0; + i < GET_LE(&symtab_hdr->sh_size) / GET_LE(&symtab_hdr->sh_entsize); + i++) { + int k; + ELF(Sym) *sym = raw_addr + GET_LE(&symtab_hdr->sh_offset) + + GET_LE(&symtab_hdr->sh_entsize) * i; + const char *name = raw_addr + GET_LE(&strtab_hdr->sh_offset) + + GET_LE(&sym->st_name); + + for (k = 0; k < NSYMS; k++) { + if (!strcmp(name, required_syms[k].name)) { + if (syms[k]) { + fail("duplicate symbol %s\n", + required_syms[k].name); + } + + /* + * Careful: we use negative addresses, but + * st_value is unsigned, so we rely + * on syms[k] being a signed type of the + * correct width. + */ + syms[k] = GET_LE(&sym->st_value); + } + } + } + + /* Validate mapping addresses. */ + for (i = 0; i < sizeof(special_pages) / sizeof(special_pages[0]); i++) { + INT_BITS symval = syms[special_pages[i]]; + + if (!symval) + continue; /* The mapping isn't used; ignore it. */ + + if (symval % 4096) + fail("%s must be a multiple of 4096\n", + required_syms[i].name); + if (symval + 4096 < syms[sym_vvar_start]) + fail("%s underruns vvar_start\n", + required_syms[i].name); + if (symval + 4096 > 0) + fail("%s is on the wrong side of the vdso text\n", + required_syms[i].name); + } + if (syms[sym_vvar_start] % 4096) + fail("vvar_begin must be a multiple of 4096\n"); + + if (!name) { + fwrite(stripped_addr, stripped_len, 1, outfile); + return; + } + + mapping_size = (stripped_len + 4095) / 4096 * 4096; + + fprintf(outfile, "/* AUTOMATICALLY GENERATED -- DO NOT EDIT */\n\n"); + fprintf(outfile, "#include <linux/linkage.h>\n"); + fprintf(outfile, "#include <asm/page_types.h>\n"); + fprintf(outfile, "#include <asm/vdso.h>\n"); + fprintf(outfile, "\n"); + fprintf(outfile, + "static unsigned char raw_data[%lu] __page_aligned_data = {", + mapping_size); + for (j = 0; j < stripped_len; j++) { + if (j % 10 == 0) + fprintf(outfile, "\n\t"); + fprintf(outfile, "0x%02X, ", + (int)((unsigned char *)stripped_addr)[j]); + } + fprintf(outfile, "\n};\n\n"); + + fprintf(outfile, "static struct page *pages[%lu];\n\n", + mapping_size / 4096); + + fprintf(outfile, "const struct vdso_image %s = {\n", name); + fprintf(outfile, "\t.data = raw_data,\n"); + fprintf(outfile, "\t.size = %lu,\n", mapping_size); + fprintf(outfile, "\t.text_mapping = {\n"); + fprintf(outfile, "\t\t.name = \"[vdso]\",\n"); + fprintf(outfile, "\t\t.pages = pages,\n"); + fprintf(outfile, "\t},\n"); + if (alt_sec) { + fprintf(outfile, "\t.alt = %lu,\n", + (unsigned long)GET_LE(&alt_sec->sh_offset)); + fprintf(outfile, "\t.alt_len = %lu,\n", + (unsigned long)GET_LE(&alt_sec->sh_size)); + } + for (i = 0; i < NSYMS; i++) { + if (required_syms[i].export && syms[i]) + fprintf(outfile, "\t.sym_%s = %" PRIi64 ",\n", + required_syms[i].name, (int64_t)syms[i]); + } + fprintf(outfile, "};\n"); +} diff --git a/kernel/arch/x86/vdso/vdso32-setup.c b/kernel/arch/x86/vdso/vdso32-setup.c new file mode 100644 index 000000000..e904c2705 --- /dev/null +++ b/kernel/arch/x86/vdso/vdso32-setup.c @@ -0,0 +1,120 @@ +/* + * (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/kernel.h> +#include <linux/mm_types.h> + +#include <asm/cpufeature.h> +#include <asm/processor.h> +#include <asm/vdso.h> + +#ifdef CONFIG_COMPAT_VDSO +#define VDSO_DEFAULT 0 +#else +#define VDSO_DEFAULT 1 +#endif + +/* + * Should the kernel map a VDSO page into processes and pass its + * address down to glibc upon exec()? + */ +unsigned int __read_mostly vdso32_enabled = VDSO_DEFAULT; + +static int __init vdso32_setup(char *s) +{ + vdso32_enabled = simple_strtoul(s, NULL, 0); + + if (vdso32_enabled > 1) + pr_warn("vdso32 values other than 0 and 1 are no longer allowed; vdso disabled\n"); + + 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=", vdso32_setup); + +#ifdef CONFIG_X86_32 +__setup_param("vdso=", vdso_setup, vdso32_setup, 0); +#endif + +#ifdef CONFIG_X86_64 + +#define vdso32_sysenter() (boot_cpu_has(X86_FEATURE_SYSENTER32)) +#define vdso32_syscall() (boot_cpu_has(X86_FEATURE_SYSCALL32)) + +#else /* CONFIG_X86_32 */ + +#define vdso32_sysenter() (boot_cpu_has(X86_FEATURE_SEP)) +#define vdso32_syscall() (0) + +#endif /* CONFIG_X86_64 */ + +#if defined(CONFIG_X86_32) || defined(CONFIG_COMPAT) +const struct vdso_image *selected_vdso32; +#endif + +int __init sysenter_setup(void) +{ +#ifdef CONFIG_COMPAT + if (vdso32_syscall()) + selected_vdso32 = &vdso_image_32_syscall; + else +#endif + if (vdso32_sysenter()) + selected_vdso32 = &vdso_image_32_sysenter; + else + selected_vdso32 = &vdso_image_32_int80; + + init_vdso_image(selected_vdso32); + + return 0; +} + +#ifdef CONFIG_X86_64 + +subsys_initcall(sysenter_setup); + +#ifdef CONFIG_SYSCTL +/* Register vsyscall32 into the ABI table */ +#include <linux/sysctl.h> + +static struct ctl_table abi_table2[] = { + { + .procname = "vsyscall32", + .data = &vdso32_enabled, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + {} +}; + +static struct ctl_table abi_root_table2[] = { + { + .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 /* CONFIG_SYSCTL */ + +#endif /* CONFIG_X86_64 */ diff --git a/kernel/arch/x86/vdso/vdso32/.gitignore b/kernel/arch/x86/vdso/vdso32/.gitignore new file mode 100644 index 000000000..e45fba9d0 --- /dev/null +++ b/kernel/arch/x86/vdso/vdso32/.gitignore @@ -0,0 +1 @@ +vdso32.lds diff --git a/kernel/arch/x86/vdso/vdso32/int80.S b/kernel/arch/x86/vdso/vdso32/int80.S new file mode 100644 index 000000000..b15b7c01a --- /dev/null +++ b/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 diff --git a/kernel/arch/x86/vdso/vdso32/note.S b/kernel/arch/x86/vdso/vdso32/note.S new file mode 100644 index 000000000..c83f25734 --- /dev/null +++ b/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 diff --git a/kernel/arch/x86/vdso/vdso32/sigreturn.S b/kernel/arch/x86/vdso/vdso32/sigreturn.S new file mode 100644 index 000000000..d7ec4e251 --- /dev/null +++ b/kernel/arch/x86/vdso/vdso32/sigreturn.S @@ -0,0 +1,145 @@ +/* + * 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 + nop /* this guy is needed for .LSTARTFDEDLSI1 below (watch for HACK) */ + 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 diff --git a/kernel/arch/x86/vdso/vdso32/syscall.S b/kernel/arch/x86/vdso/vdso32/syscall.S new file mode 100644 index 000000000..6b286bb52 --- /dev/null +++ b/kernel/arch/x86/vdso/vdso32/syscall.S @@ -0,0 +1,75 @@ +/* + * 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 %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 diff --git a/kernel/arch/x86/vdso/vdso32/sysenter.S b/kernel/arch/x86/vdso/vdso32/sysenter.S new file mode 100644 index 000000000..e354bceee --- /dev/null +++ b/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) */ + int $0x80 + /* 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) diff --git a/kernel/arch/x86/vdso/vdso32/vclock_gettime.c b/kernel/arch/x86/vdso/vdso32/vclock_gettime.c new file mode 100644 index 000000000..175cc72c0 --- /dev/null +++ b/kernel/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/kernel/arch/x86/vdso/vdso32/vdso-fakesections.c b/kernel/arch/x86/vdso/vdso32/vdso-fakesections.c new file mode 100644 index 000000000..541468e25 --- /dev/null +++ b/kernel/arch/x86/vdso/vdso32/vdso-fakesections.c @@ -0,0 +1 @@ +#include "../vdso-fakesections.c" diff --git a/kernel/arch/x86/vdso/vdso32/vdso32.lds.S b/kernel/arch/x86/vdso/vdso32/vdso32.lds.S new file mode 100644 index 000000000..31056cf29 --- /dev/null +++ b/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. + * + * This file defines the version script giving the user-exported symbols in + * the DSO. + */ + +#include <asm/page.h> + +#define BUILD_VDSO32 + +#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_2.6 { + global: + __vdso_clock_gettime; + __vdso_gettimeofday; + __vdso_time; + }; + + LINUX_2.5 { + global: + __kernel_vsyscall; + __kernel_sigreturn; + __kernel_rt_sigreturn; + local: *; + }; +} diff --git a/kernel/arch/x86/vdso/vdsox32.lds.S b/kernel/arch/x86/vdso/vdsox32.lds.S new file mode 100644 index 000000000..697c11ece --- /dev/null +++ b/kernel/arch/x86/vdso/vdsox32.lds.S @@ -0,0 +1,25 @@ +/* + * Linker script for x32 vDSO. + * We #include the file to define the layout details. + * + * This file defines the version script giving the user-exported symbols in + * the DSO. + */ + +#define BUILD_VDSOX32 + +#include "vdso-layout.lds.S" + +/* + * This controls what userland symbols we export from the vDSO. + */ +VERSION { + LINUX_2.6 { + global: + __vdso_clock_gettime; + __vdso_gettimeofday; + __vdso_getcpu; + __vdso_time; + local: *; + }; +} diff --git a/kernel/arch/x86/vdso/vgetcpu.c b/kernel/arch/x86/vdso/vgetcpu.c new file mode 100644 index 000000000..8ec3d1f4c --- /dev/null +++ b/kernel/arch/x86/vdso/vgetcpu.c @@ -0,0 +1,28 @@ +/* + * 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/time.h> +#include <asm/vgtod.h> + +notrace long +__vdso_getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *unused) +{ + unsigned int p; + + p = __getcpu(); + + if (cpu) + *cpu = p & VGETCPU_CPU_MASK; + 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/kernel/arch/x86/vdso/vma.c b/kernel/arch/x86/vdso/vma.c new file mode 100644 index 000000000..1c9f750c3 --- /dev/null +++ b/kernel/arch/x86/vdso/vma.c @@ -0,0 +1,300 @@ +/* + * Copyright 2007 Andi Kleen, SUSE Labs. + * Subject to the GPL, v.2 + * + * This contains most of the x86 vDSO kernel-side code. + */ +#include <linux/mm.h> +#include <linux/err.h> +#include <linux/sched.h> +#include <linux/slab.h> +#include <linux/init.h> +#include <linux/random.h> +#include <linux/elf.h> +#include <linux/cpu.h> +#include <asm/vgtod.h> +#include <asm/proto.h> +#include <asm/vdso.h> +#include <asm/vvar.h> +#include <asm/page.h> +#include <asm/hpet.h> +#include <asm/desc.h> + +#if defined(CONFIG_X86_64) +unsigned int __read_mostly vdso64_enabled = 1; +#endif + +void __init init_vdso_image(const struct vdso_image *image) +{ + int i; + int npages = (image->size) / PAGE_SIZE; + + BUG_ON(image->size % PAGE_SIZE != 0); + for (i = 0; i < npages; i++) + image->text_mapping.pages[i] = + virt_to_page(image->data + i*PAGE_SIZE); + + apply_alternatives((struct alt_instr *)(image->data + image->alt), + (struct alt_instr *)(image->data + image->alt + + image->alt_len)); +} + +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. + * + * Note that this algorithm is imperfect: the distribution of the vdso + * start address within a PMD is biased toward the end. + * + * Only used for the 64-bit and x32 vdsos. + */ +static unsigned long vdso_addr(unsigned long start, unsigned len) +{ +#ifdef CONFIG_X86_32 + return 0; +#else + unsigned long addr, end; + unsigned offset; + + /* + * Round up the start address. It can start out unaligned as a result + * of stack start randomization. + */ + start = PAGE_ALIGN(start); + + /* Round the lowest possible end address up to a PMD boundary. */ + end = (start + len + PMD_SIZE - 1) & PMD_MASK; + if (end >= TASK_SIZE_MAX) + end = TASK_SIZE_MAX; + end -= len; + + if (end > start) { + offset = get_random_int() % (((end - start) >> PAGE_SHIFT) + 1); + addr = start + (offset << PAGE_SHIFT); + } else { + addr = start; + } + + /* + * Forcibly align the final address in case we have a hardware + * issue that requires alignment for performance reasons. + */ + addr = align_vdso_addr(addr); + + return addr; +#endif +} + +static int map_vdso(const struct vdso_image *image, bool calculate_addr) +{ + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma; + unsigned long addr, text_start; + int ret = 0; + static struct page *no_pages[] = {NULL}; + static struct vm_special_mapping vvar_mapping = { + .name = "[vvar]", + .pages = no_pages, + }; + + if (calculate_addr) { + addr = vdso_addr(current->mm->start_stack, + image->size - image->sym_vvar_start); + } else { + addr = 0; + } + + down_write(&mm->mmap_sem); + + addr = get_unmapped_area(NULL, addr, + image->size - image->sym_vvar_start, 0, 0); + if (IS_ERR_VALUE(addr)) { + ret = addr; + goto up_fail; + } + + text_start = addr - image->sym_vvar_start; + current->mm->context.vdso = (void __user *)text_start; + + /* + * MAYWRITE to allow gdb to COW and set breakpoints + */ + vma = _install_special_mapping(mm, + text_start, + image->size, + VM_READ|VM_EXEC| + VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC, + &image->text_mapping); + + if (IS_ERR(vma)) { + ret = PTR_ERR(vma); + goto up_fail; + } + + vma = _install_special_mapping(mm, + addr, + -image->sym_vvar_start, + VM_READ|VM_MAYREAD, + &vvar_mapping); + + if (IS_ERR(vma)) { + ret = PTR_ERR(vma); + goto up_fail; + } + + if (image->sym_vvar_page) + ret = remap_pfn_range(vma, + text_start + image->sym_vvar_page, + __pa_symbol(&__vvar_page) >> PAGE_SHIFT, + PAGE_SIZE, + PAGE_READONLY); + + if (ret) + goto up_fail; + +#ifdef CONFIG_HPET_TIMER + if (hpet_address && image->sym_hpet_page) { + ret = io_remap_pfn_range(vma, + text_start + image->sym_hpet_page, + hpet_address >> PAGE_SHIFT, + PAGE_SIZE, + pgprot_noncached(PAGE_READONLY)); + + if (ret) + goto up_fail; + } +#endif + +up_fail: + if (ret) + current->mm->context.vdso = NULL; + + up_write(&mm->mmap_sem); + return ret; +} + +#if defined(CONFIG_X86_32) || defined(CONFIG_COMPAT) +static int load_vdso32(void) +{ + int ret; + + if (vdso32_enabled != 1) /* Other values all mean "disabled" */ + return 0; + + ret = map_vdso(selected_vdso32, false); + if (ret) + return ret; + + if (selected_vdso32->sym_VDSO32_SYSENTER_RETURN) + current_thread_info()->sysenter_return = + current->mm->context.vdso + + selected_vdso32->sym_VDSO32_SYSENTER_RETURN; + + return 0; +} +#endif + +#ifdef CONFIG_X86_64 +int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) +{ + if (!vdso64_enabled) + return 0; + + return map_vdso(&vdso_image_64, true); +} + +#ifdef CONFIG_COMPAT +int compat_arch_setup_additional_pages(struct linux_binprm *bprm, + int uses_interp) +{ +#ifdef CONFIG_X86_X32_ABI + if (test_thread_flag(TIF_X32)) { + if (!vdso64_enabled) + return 0; + + return map_vdso(&vdso_image_x32, true); + } +#endif + + return load_vdso32(); +} +#endif +#else +int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) +{ + return load_vdso32(); +} +#endif + +#ifdef CONFIG_X86_64 +static __init int vdso_setup(char *s) +{ + vdso64_enabled = simple_strtoul(s, NULL, 0); + return 0; +} +__setup("vdso=", vdso_setup); +#endif + +#ifdef CONFIG_X86_64 +static void vgetcpu_cpu_init(void *arg) +{ + int cpu = smp_processor_id(); + struct desc_struct d = { }; + unsigned long node = 0; +#ifdef CONFIG_NUMA + node = cpu_to_node(cpu); +#endif + if (cpu_has(&cpu_data(cpu), X86_FEATURE_RDTSCP)) + write_rdtscp_aux((node << 12) | cpu); + + /* + * Store cpu number in limit so that it can be loaded + * quickly in user space in vgetcpu. (12 bits for the CPU + * and 8 bits for the node) + */ + d.limit0 = cpu | ((node & 0xf) << 12); + d.limit = node >> 4; + d.type = 5; /* RO data, expand down, accessed */ + d.dpl = 3; /* Visible to user code */ + d.s = 1; /* Not a system segment */ + d.p = 1; /* Present */ + d.d = 1; /* 32-bit */ + + write_gdt_entry(get_cpu_gdt_table(cpu), GDT_ENTRY_PER_CPU, &d, DESCTYPE_S); +} + +static int +vgetcpu_cpu_notifier(struct notifier_block *n, unsigned long action, void *arg) +{ + long cpu = (long)arg; + + if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN) + smp_call_function_single(cpu, vgetcpu_cpu_init, NULL, 1); + + return NOTIFY_DONE; +} + +static int __init init_vdso(void) +{ + init_vdso_image(&vdso_image_64); + +#ifdef CONFIG_X86_X32_ABI + init_vdso_image(&vdso_image_x32); +#endif + + cpu_notifier_register_begin(); + + on_each_cpu(vgetcpu_cpu_init, NULL, 1); + /* notifier priority > KVM */ + __hotcpu_notifier(vgetcpu_cpu_notifier, 30); + + cpu_notifier_register_done(); + + return 0; +} +subsys_initcall(init_vdso); +#endif /* CONFIG_X86_64 */ |