Release 4.14 arch/x86/entry/vdso/vma.c

/*
 * 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/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 <asm/pvclock.h>
#include <asm/vgtod.h>
#include <asm/proto.h>
#include <asm/vdso.h>
#include <asm/vvar.h>
#include <asm/page.h>
#include <asm/desc.h>
#include <asm/cpufeature.h>
#include <asm/mshyperv.h>

#if defined(CONFIG_X86_64)

unsigned int __read_mostly vdso64_enabled = 1;
#endif



void __init init_vdso_image(const struct vdso_image *image)
{
	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));
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Andrew Lutomirski
47
78.33%
2
66.67%
H. J. Lu
13
21.67%
1
33.33%
Total
60
100.00%
3
100.00%

struct linux_binprm;



static int 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;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Andrew Lutomirski
85
100.00%
1
100.00%
Total
85
100.00%
1
100.00%



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
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Dmitry Safonov
85
93.41%
1
50.00%
Andrew Lutomirski
6
6.59%
1
50.00%
Total
91
100.00%
2
100.00%



static int vdso_mremap(const struct vm_special_mapping *sm,
		struct vm_area_struct *new_vma)
{
	unsigned long new_size = new_vma->vm_end - new_vma->vm_start;
	const struct vdso_image *image = current->mm->context.vdso_image;

	if (image->size != new_size)
		return -EINVAL;

	vdso_fix_landing(image, new_vma);
	current->mm->context.vdso = (void __user *)new_vma->vm_start;

	return 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Dmitry Safonov
80
97.56%
1
50.00%
Andrew Lutomirski
2
2.44%
1
50.00%
Total
82
100.00%
2
100.00%



static int 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;
	long sym_offset;
	int ret = -EFAULT;

	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) {
		ret = vm_insert_pfn(vma, vmf->address,
				    __pa_symbol(&__vvar_page) >> PAGE_SHIFT);
	} else if (sym_offset == image->sym_pvclock_page) {
		struct pvclock_vsyscall_time_info *pvti =
			pvclock_pvti_cpu0_va();
		if (pvti && vclock_was_used(VCLOCK_PVCLOCK)) {
			ret = vm_insert_pfn(
				vma,
				vmf->address,
				__pa(pvti) >> PAGE_SHIFT);
		}
	} else if (sym_offset == image->sym_hvclock_page) {
		struct ms_hyperv_tsc_page *tsc_pg = hv_get_tsc_page();

		if (tsc_pg && vclock_was_used(VCLOCK_HVCLOCK))
			ret = vm_insert_pfn(vma, vmf->address,
					    vmalloc_to_pfn(tsc_pg));
	}

	if (ret == 0 || ret == -EBUSY)
		return VM_FAULT_NOPAGE;

	return VM_FAULT_SIGBUS;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Andrew Lutomirski
172
78.90%
2
50.00%
Vitaly Kuznetsov
44
20.18%
1
25.00%
Jan Kara
2
0.92%
1
25.00%
Total
218
100.00%
4
100.00%


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,
};

/*
 * 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 (down_write_killable(&mm->mmap_sem))
		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,
				       -image->sym_vvar_start,
				       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);
	} else {
		current->mm->context.vdso = (void __user *)text_start;
		current->mm->context.vdso_image = image;
	}

up_fail:
	up_write(&mm->mmap_sem);
	return ret;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Andrew Lutomirski
103
42.74%
5
35.71%
Andi Kleen
89
36.93%
1
7.14%
Dmitry Safonov
36
14.94%
4
28.57%
Michal Hocko
6
2.49%
1
7.14%
H. J. Lu
4
1.66%
1
7.14%
Mike Rapoport
2
0.83%
1
7.14%
Peter Zijlstra
1
0.41%
1
7.14%
Total
241
100.00%
14
100.00%

#ifdef CONFIG_X86_64
/*
 * 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)
{
	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;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Ingo Molnar
115
100.00%
1
100.00%
Total
115
100.00%
1
100.00%



static int map_vdso_randomized(const struct vdso_image *image)
{
	unsigned long addr = vdso_addr(current->mm->start_stack, image->size-image->sym_vvar_start);

	return map_vdso(image, addr);
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Dmitry Safonov
41
100.00%
1
100.00%
Total
41
100.00%
1
100.00%

#endif



int map_vdso_once(const struct vdso_image *image, unsigned long addr)
{
	struct mm_struct *mm = current->mm;
	struct vm_area_struct *vma;

	down_write(&mm->mmap_sem);
	/*
         * Check if we have already mapped vdso blob - fail to prevent
         * abusing from userspace install_speciall_mapping, which may
         * not do accounting and rlimit right.
         * We could search vma near context.vdso, but it's a slowpath,
         * so let's explicitely check all VMAs to be completely sure.
         */
	for (vma = mm->mmap; vma; vma = vma->vm_next) {
		if (vma_is_special_mapping(vma, &vdso_mapping) ||
				vma_is_special_mapping(vma, &vvar_mapping)) {
			up_write(&mm->mmap_sem);
			return -EEXIST;
		}
	}
	up_write(&mm->mmap_sem);

	return map_vdso(image, addr);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Dmitry Safonov
104
100.00%
1
100.00%
Total
104
100.00%
1
100.00%

#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);
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Andrew Lutomirski
26
96.30%
2
66.67%
Dmitry Safonov
1
3.70%
1
33.33%
Total
27
100.00%
3
100.00%

#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_randomized(&vdso_image_64);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
H. J. Lu
17
60.71%
1
25.00%
Andrew Lutomirski
10
35.71%
2
50.00%
Dmitry Safonov
1
3.57%
1
25.00%
Total
28
100.00%
4
100.00%

#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_randomized(&vdso_image_x32);
	}
#endif
#ifdef CONFIG_IA32_EMULATION
	return load_vdso32();
#else
	return 0;
#endif
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Andrew Lutomirski
29
51.79%
2
40.00%
H. J. Lu
16
28.57%
1
20.00%
Brian Gerst
10
17.86%
1
20.00%
Dmitry Safonov
1
1.79%
1
20.00%
Total
56
100.00%
5
100.00%

#endif
#else


int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
{
	return load_vdso32();
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Andrew Lutomirski
17
100.00%
1
100.00%
Total
17
100.00%
1
100.00%

#endif

#ifdef CONFIG_X86_64


static __init int vdso_setup(char *s)
{
	vdso64_enabled = simple_strtoul(s, NULL, 0);
	return 0;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Andi Kleen
24
96.00%
1
50.00%
Andrew Lutomirski
1
4.00%
1
50.00%
Total
25
100.00%
2
100.00%

__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 (static_cpu_has(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.limit1 = 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_rw(cpu), GDT_ENTRY_PER_CPU, &d, DESCTYPE_S);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Andrew Lutomirski
115
86.47%
5
55.56%
Andrew Morton
15
11.28%
1
11.11%
Thomas Garnier
1
0.75%
1
11.11%
Borislav Petkov
1
0.75%
1
11.11%
Thomas Gleixner
1
0.75%
1
11.11%
Total
133
100.00%
9
100.00%



static int vgetcpu_online(unsigned int cpu)
{
	return smp_call_function_single(cpu, vgetcpu_cpu_init, NULL, 1);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Andrew Lutomirski
18
81.82%
2
66.67%
Sebastian Andrzej Siewior
4
18.18%
1
33.33%
Total
22
100.00%
3
100.00%



static int __init init_vdso(void)
{
	init_vdso_image(&vdso_image_64);

#ifdef CONFIG_X86_X32_ABI
	init_vdso_image(&vdso_image_x32);
#endif

	/* notifier priority > KVM */
	return cpuhp_setup_state(CPUHP_AP_X86_VDSO_VMA_ONLINE,
				 "x86/vdso/vma:online", vgetcpu_online, NULL);
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Andrew Lutomirski
32
82.05%
2
50.00%
Sebastian Andrzej Siewior
6
15.38%
1
25.00%
Thomas Gleixner
1
2.56%
1
25.00%
Total
39
100.00%
4
100.00%


subsys_initcall(init_vdso);
#endif /* CONFIG_X86_64 */
Overall Contributors
Person
Tokens
Prop
Commits
CommitProp
Andrew Lutomirski
725
46.59%
19
41.30%
Dmitry Safonov
394
25.32%
5
10.87%
Andi Kleen
143
9.19%
1
2.17%
Ingo Molnar
124
7.97%
2
4.35%
H. J. Lu
54
3.47%
1
2.17%
Vitaly Kuznetsov
47
3.02%
1
2.17%
Andrew Morton
15
0.96%
1
2.17%
Brian Gerst
11
0.71%
1
2.17%
Sebastian Andrzej Siewior
10
0.64%
1
2.17%
Michal Hocko
6
0.39%
1
2.17%
Borislav Petkov
4
0.26%
2
4.35%
Roland McGrath
4
0.26%
1
2.17%
Tejun Heo
3
0.19%
1
2.17%
Jaswinder Singh Rajput
3
0.19%
1
2.17%
Alexey Dobriyan
3
0.19%
1
2.17%
Thomas Gleixner
2
0.13%
2
4.35%
Mike Rapoport
2
0.13%
1
2.17%
Jan Kara
2
0.13%
1
2.17%
Hirofumi Ogawa
2
0.13%
1
2.17%
Thomas Garnier
1
0.06%
1
2.17%
Peter Zijlstra
1
0.06%
1
2.17%
Total
1556
100.00%
46
100.00%
Directory: arch/x86/entry/vdso

Information contained on this website is for historical information purposes only and does not indicate or represent copyright ownership.