Contributors: 40
| Author |
Tokens |
Token Proportion |
Commits |
Commit Proportion |
| Andrew Lutomirski |
532 |
32.50% |
19 |
23.46% |
| Dmitry Safonov |
387 |
23.64% |
9 |
11.11% |
| Andi Kleen |
219 |
13.38% |
2 |
2.47% |
| Thomas Weißschuh |
163 |
9.96% |
2 |
2.47% |
| H. J. Lu |
49 |
2.99% |
1 |
1.23% |
| Gabriel Krisman Bertazi |
49 |
2.99% |
2 |
2.47% |
| Stefani Seibold |
46 |
2.81% |
1 |
1.23% |
| Matthew Wilcox |
40 |
2.44% |
2 |
2.47% |
| Brian Gerst |
16 |
0.98% |
2 |
2.47% |
| Thomas Gleixner |
16 |
0.98% |
4 |
4.94% |
| Roland McGrath |
13 |
0.79% |
3 |
3.70% |
| Vitaly Kuznetsov |
11 |
0.67% |
1 |
1.23% |
| Brijesh Singh |
7 |
0.43% |
1 |
1.23% |
| Mike Rapoport |
6 |
0.37% |
2 |
2.47% |
| Daniel Micay |
6 |
0.37% |
1 |
1.23% |
| Vojtech Pavlik |
6 |
0.37% |
2 |
2.47% |
| Matt Tolentino |
6 |
0.37% |
1 |
1.23% |
| David Howells |
5 |
0.31% |
2 |
2.47% |
| Michel Lespinasse |
5 |
0.31% |
1 |
1.23% |
| Michal Hocko |
5 |
0.31% |
1 |
1.23% |
| Andrey Vagin |
5 |
0.31% |
1 |
1.23% |
| Peter Zijlstra |
4 |
0.24% |
1 |
1.23% |
| Stanislav Kinsburskiy |
4 |
0.24% |
1 |
1.23% |
| Ingo Molnar |
4 |
0.24% |
2 |
2.47% |
| Alexey Dobriyan |
3 |
0.18% |
1 |
1.23% |
| Jan Kara |
3 |
0.18% |
1 |
1.23% |
| Martin Schwidefsky |
3 |
0.18% |
1 |
1.23% |
| Gerd Hoffmann |
3 |
0.18% |
1 |
1.23% |
| Jaswinder Singh Rajput |
3 |
0.18% |
1 |
1.23% |
| Al Viro |
3 |
0.18% |
1 |
1.23% |
| Linus Torvalds |
2 |
0.12% |
2 |
2.47% |
| Christian Brauner |
2 |
0.12% |
1 |
1.23% |
| OGAWA Hirofumi |
2 |
0.12% |
1 |
1.23% |
| Richard Henderson |
2 |
0.12% |
1 |
1.23% |
| Linus Torvalds (pre-git) |
2 |
0.12% |
1 |
1.23% |
| Joao Martins |
1 |
0.06% |
1 |
1.23% |
| Randy Dunlap |
1 |
0.06% |
1 |
1.23% |
| Christophe Leroy |
1 |
0.06% |
1 |
1.23% |
| Mike Kravetz |
1 |
0.06% |
1 |
1.23% |
| Michael Kelley |
1 |
0.06% |
1 |
1.23% |
| Total |
1637 |
|
81 |
|
123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407
// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright 2007 Andi Kleen, SUSE Labs.
*
* This contains most of the x86 vDSO kernel-side code.
*/
#include <linux/mm.h>
#include <linux/err.h>
#include <linux/sched.h>
#include <linux/sched/task_stack.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/random.h>
#include <linux/elf.h>
#include <linux/cpu.h>
#include <linux/ptrace.h>
#include <linux/time_namespace.h>
#include <asm/pvclock.h>
#include <asm/vgtod.h>
#include <asm/proto.h>
#include <asm/vdso.h>
#include <asm/tlb.h>
#include <asm/page.h>
#include <asm/desc.h>
#include <asm/cpufeature.h>
#include <asm/vdso/vsyscall.h>
#include <clocksource/hyperv_timer.h>
struct vdso_data *arch_get_vdso_data(void *vvar_page)
{
return (struct vdso_data *)vvar_page;
}
static union vdso_data_store vdso_data_store __page_aligned_data;
struct vdso_data *vdso_data = vdso_data_store.data;
unsigned int vclocks_used __read_mostly;
#if defined(CONFIG_X86_64)
unsigned int __read_mostly vdso64_enabled = 1;
#endif
int __init init_vdso_image(const struct vdso_image *image)
{
BUILD_BUG_ON(VDSO_CLOCKMODE_MAX >= 32);
BUG_ON(image->size % PAGE_SIZE != 0);
apply_alternatives((struct alt_instr *)(image->data + image->alt),
(struct alt_instr *)(image->data + image->alt +
image->alt_len),
NULL);
return 0;
}
static const struct vm_special_mapping vvar_mapping;
struct linux_binprm;
static vm_fault_t vdso_fault(const struct vm_special_mapping *sm,
struct vm_area_struct *vma, struct vm_fault *vmf)
{
const struct vdso_image *image = vma->vm_mm->context.vdso_image;
if (!image || (vmf->pgoff << PAGE_SHIFT) >= image->size)
return VM_FAULT_SIGBUS;
vmf->page = virt_to_page(image->data + (vmf->pgoff << PAGE_SHIFT));
get_page(vmf->page);
return 0;
}
static void vdso_fix_landing(const struct vdso_image *image,
struct vm_area_struct *new_vma)
{
#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
if (in_ia32_syscall() && image == &vdso_image_32) {
struct pt_regs *regs = current_pt_regs();
unsigned long vdso_land = image->sym_int80_landing_pad;
unsigned long old_land_addr = vdso_land +
(unsigned long)current->mm->context.vdso;
/* Fixing userspace landing - look at do_fast_syscall_32 */
if (regs->ip == old_land_addr)
regs->ip = new_vma->vm_start + vdso_land;
}
#endif
}
static int vdso_mremap(const struct vm_special_mapping *sm,
struct vm_area_struct *new_vma)
{
const struct vdso_image *image = current->mm->context.vdso_image;
vdso_fix_landing(image, new_vma);
current->mm->context.vdso = (void __user *)new_vma->vm_start;
return 0;
}
#ifdef CONFIG_TIME_NS
/*
* The vvar page layout depends on whether a task belongs to the root or
* non-root time namespace. Whenever a task changes its namespace, the VVAR
* page tables are cleared and then they will re-faulted with a
* corresponding layout.
* See also the comment near timens_setup_vdso_data() for details.
*/
int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
{
struct mm_struct *mm = task->mm;
struct vm_area_struct *vma;
VMA_ITERATOR(vmi, mm, 0);
mmap_read_lock(mm);
for_each_vma(vmi, vma) {
if (vma_is_special_mapping(vma, &vvar_mapping))
zap_vma_pages(vma);
}
mmap_read_unlock(mm);
return 0;
}
#endif
static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
struct vm_area_struct *vma, struct vm_fault *vmf)
{
const struct vdso_image *image = vma->vm_mm->context.vdso_image;
unsigned long pfn;
long sym_offset;
if (!image)
return VM_FAULT_SIGBUS;
sym_offset = (long)(vmf->pgoff << PAGE_SHIFT) +
image->sym_vvar_start;
/*
* Sanity check: a symbol offset of zero means that the page
* does not exist for this vdso image, not that the page is at
* offset zero relative to the text mapping. This should be
* impossible here, because sym_offset should only be zero for
* the page past the end of the vvar mapping.
*/
if (sym_offset == 0)
return VM_FAULT_SIGBUS;
if (sym_offset == image->sym_vvar_page) {
struct page *timens_page = find_timens_vvar_page(vma);
pfn = __pa_symbol(vdso_data) >> PAGE_SHIFT;
/*
* If a task belongs to a time namespace then a namespace
* specific VVAR is mapped with the sym_vvar_page offset and
* the real VVAR page is mapped with the sym_timens_page
* offset.
* See also the comment near timens_setup_vdso_data().
*/
if (timens_page) {
unsigned long addr;
vm_fault_t err;
/*
* Optimization: inside time namespace pre-fault
* VVAR page too. As on timens page there are only
* offsets for clocks on VVAR, it'll be faulted
* shortly by VDSO code.
*/
addr = vmf->address + (image->sym_timens_page - sym_offset);
err = vmf_insert_pfn(vma, addr, pfn);
if (unlikely(err & VM_FAULT_ERROR))
return err;
pfn = page_to_pfn(timens_page);
}
return vmf_insert_pfn(vma, vmf->address, pfn);
} else if (sym_offset == image->sym_timens_page) {
struct page *timens_page = find_timens_vvar_page(vma);
if (!timens_page)
return VM_FAULT_SIGBUS;
pfn = __pa_symbol(vdso_data) >> PAGE_SHIFT;
return vmf_insert_pfn(vma, vmf->address, pfn);
}
return VM_FAULT_SIGBUS;
}
static vm_fault_t vvar_vclock_fault(const struct vm_special_mapping *sm,
struct vm_area_struct *vma, struct vm_fault *vmf)
{
switch (vmf->pgoff) {
#ifdef CONFIG_PARAVIRT_CLOCK
case VDSO_PAGE_PVCLOCK_OFFSET:
{
struct pvclock_vsyscall_time_info *pvti =
pvclock_get_pvti_cpu0_va();
if (pvti && vclock_was_used(VDSO_CLOCKMODE_PVCLOCK))
return vmf_insert_pfn_prot(vma, vmf->address,
__pa(pvti) >> PAGE_SHIFT,
pgprot_decrypted(vma->vm_page_prot));
break;
}
#endif /* CONFIG_PARAVIRT_CLOCK */
#ifdef CONFIG_HYPERV_TIMER
case VDSO_PAGE_HVCLOCK_OFFSET:
{
unsigned long pfn = hv_get_tsc_pfn();
if (pfn && vclock_was_used(VDSO_CLOCKMODE_HVCLOCK))
return vmf_insert_pfn(vma, vmf->address, pfn);
break;
}
#endif /* CONFIG_HYPERV_TIMER */
}
return VM_FAULT_SIGBUS;
}
static const struct vm_special_mapping vdso_mapping = {
.name = "[vdso]",
.fault = vdso_fault,
.mremap = vdso_mremap,
};
static const struct vm_special_mapping vvar_mapping = {
.name = "[vvar]",
.fault = vvar_fault,
};
static const struct vm_special_mapping vvar_vclock_mapping = {
.name = "[vvar_vclock]",
.fault = vvar_vclock_fault,
};
/*
* Add vdso and vvar mappings to current process.
* @image - blob to map
* @addr - request a specific address (zero to map at free addr)
*/
static int map_vdso(const struct vdso_image *image, unsigned long addr)
{
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
unsigned long text_start;
int ret = 0;
if (mmap_write_lock_killable(mm))
return -EINTR;
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;
/*
* 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,
&vdso_mapping);
if (IS_ERR(vma)) {
ret = PTR_ERR(vma);
goto up_fail;
}
vma = _install_special_mapping(mm,
addr,
(__VVAR_PAGES - VDSO_NR_VCLOCK_PAGES) * PAGE_SIZE,
VM_READ|VM_MAYREAD|VM_IO|VM_DONTDUMP|
VM_PFNMAP,
&vvar_mapping);
if (IS_ERR(vma)) {
ret = PTR_ERR(vma);
do_munmap(mm, text_start, image->size, NULL);
goto up_fail;
}
vma = _install_special_mapping(mm,
addr + (__VVAR_PAGES - VDSO_NR_VCLOCK_PAGES) * PAGE_SIZE,
VDSO_NR_VCLOCK_PAGES * PAGE_SIZE,
VM_READ|VM_MAYREAD|VM_IO|VM_DONTDUMP|
VM_PFNMAP,
&vvar_vclock_mapping);
if (IS_ERR(vma)) {
ret = PTR_ERR(vma);
do_munmap(mm, text_start, image->size, NULL);
do_munmap(mm, addr, image->size, NULL);
goto up_fail;
}
current->mm->context.vdso = (void __user *)text_start;
current->mm->context.vdso_image = image;
up_fail:
mmap_write_unlock(mm);
return ret;
}
int map_vdso_once(const struct vdso_image *image, unsigned long addr)
{
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
VMA_ITERATOR(vmi, mm, 0);
mmap_write_lock(mm);
/*
* Check if we have already mapped vdso blob - fail to prevent
* abusing from userspace install_special_mapping, which may
* not do accounting and rlimit right.
* We could search vma near context.vdso, but it's a slowpath,
* so let's explicitly check all VMAs to be completely sure.
*/
for_each_vma(vmi, vma) {
if (vma_is_special_mapping(vma, &vdso_mapping) ||
vma_is_special_mapping(vma, &vvar_mapping) ||
vma_is_special_mapping(vma, &vvar_vclock_mapping)) {
mmap_write_unlock(mm);
return -EEXIST;
}
}
mmap_write_unlock(mm);
return map_vdso(image, addr);
}
#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
static int load_vdso32(void)
{
if (vdso32_enabled != 1) /* Other values all mean "disabled" */
return 0;
return map_vdso(&vdso_image_32, 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, 0);
}
#ifdef CONFIG_COMPAT
int compat_arch_setup_additional_pages(struct linux_binprm *bprm,
int uses_interp, bool x32)
{
#ifdef CONFIG_X86_X32_ABI
if (x32) {
if (!vdso64_enabled)
return 0;
return map_vdso(&vdso_image_x32, 0);
}
#endif
#ifdef CONFIG_IA32_EMULATION
return load_vdso32();
#else
return 0;
#endif
}
#endif
#else
int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
{
return load_vdso32();
}
#endif
bool arch_syscall_is_vdso_sigreturn(struct pt_regs *regs)
{
#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
const struct vdso_image *image = current->mm->context.vdso_image;
unsigned long vdso = (unsigned long) current->mm->context.vdso;
if (in_ia32_syscall() && image == &vdso_image_32) {
if (regs->ip == vdso + image->sym_vdso32_sigreturn_landing_pad ||
regs->ip == vdso + image->sym_vdso32_rt_sigreturn_landing_pad)
return true;
}
#endif
return false;
}
#ifdef CONFIG_X86_64
static __init int vdso_setup(char *s)
{
vdso64_enabled = simple_strtoul(s, NULL, 0);
return 1;
}
__setup("vdso=", vdso_setup);
#endif /* CONFIG_X86_64 */