Commit 8e4ef638 authored by Linus Torvalds's avatar Linus Torvalds
Browse files

Merge branch 'x86-vdso-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 

Pull x86 vdso updates from Ingo Molnar:
 "The main changes in this cycle centered around adding support for
  32-bit compatible C/R of the vDSO on 64-bit kernels, by Dmitry
  Safonov"

* 'x86-vdso-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/vdso: Use CONFIG_X86_X32_ABI to enable vdso prctl
  x86/vdso: Only define map_vdso_randomized() if CONFIG_X86_64
  x86/vdso: Only define prctl_map_vdso() if CONFIG_CHECKPOINT_RESTORE
  x86/signal: Add SA_{X32,IA32}_ABI sa_flags
  x86/ptrace: Down with test_thread_flag(TIF_IA32)
  x86/coredump: Use pr_reg size, rather that TIF_IA32 flag
  x86/arch_prctl/vdso: Add ARCH_MAP_VDSO_*
  x86/vdso: Replace calculate_addr in map_vdso() with addr
  x86/vdso: Unmap vdso blob on vvar mapping failure
parents 6aebe7f9 6e68b087

arch/x86/entry/vdso/vma.c

+102 −73
Original line number Diff line number Diff line
@@ -37,54 +37,6 @@ void __init init_vdso_image(const struct vdso_image *image) 


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 vdso_fault(const struct vm_special_mapping *sm,

		      struct vm_area_struct *vma, struct vm_fault *vmf)

{
@@ -176,13 +128,6 @@ static int vvar_fault(const struct vm_special_mapping *sm, 
	return VM_FAULT_SIGBUS;

}



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 const struct vm_special_mapping vdso_mapping = {

	.name = "[vdso]",

	.fault = vdso_fault,
@@ -193,12 +138,17 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr) 
	.fault = vvar_fault,

};



	if (calculate_addr) {

		addr = vdso_addr(current->mm->start_stack,

				 image->size - image->sym_vvar_start);

	} else {

		addr = 0;

	}

/*

 * 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;
@@ -238,24 +188,104 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr) 


	if (IS_ERR(vma)) {

		ret = PTR_ERR(vma);

		goto up_fail;

		do_munmap(mm, text_start, image->size);

	}



up_fail:

	if (ret)

	if (ret) {

		current->mm->context.vdso = NULL;

		current->mm->context.vdso_image = NULL;

	}



	up_write(&mm->mmap_sem);

	return ret;

}



#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;

}



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);

}

#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);

}



#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, false);

	return map_vdso(&vdso_image_32, 0);

}

#endif
@@ -265,7 +295,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) 
	if (!vdso64_enabled)

		return 0;



	return map_vdso(&vdso_image_64, true);

	return map_vdso_randomized(&vdso_image_64);

}



#ifdef CONFIG_COMPAT
@@ -276,8 +306,7 @@ int compat_arch_setup_additional_pages(struct linux_binprm *bprm, 
	if (test_thread_flag(TIF_X32)) {

		if (!vdso64_enabled)

			return 0;



		return map_vdso(&vdso_image_x32, true);

		return map_vdso_randomized(&vdso_image_x32);

	}

#endif

#ifdef CONFIG_IA32_EMULATION

arch/x86/ia32/ia32_signal.c

+1 −1
Original line number Diff line number Diff line
@@ -378,7 +378,7 @@ int ia32_setup_rt_frame(int sig, struct ksignal *ksig, 
		put_user_ex(*((u64 *)&code), (u64 __user *)frame->retcode);

	} put_user_catch(err);



	err |= copy_siginfo_to_user32(&frame->info, &ksig->info);

	err |= __copy_siginfo_to_user32(&frame->info, &ksig->info, false);

	err |= ia32_setup_sigcontext(&frame->uc.uc_mcontext, fpstate,

				     regs, set->sig[0]);

	err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));

arch/x86/include/asm/compat.h

+4 −4
Original line number Diff line number Diff line
@@ -275,10 +275,10 @@ struct compat_shmid64_ds { 
#ifdef CONFIG_X86_X32_ABI

typedef struct user_regs_struct compat_elf_gregset_t;



#define PR_REG_SIZE(S) (test_thread_flag(TIF_IA32) ? 68 : 216)

#define PRSTATUS_SIZE(S) (test_thread_flag(TIF_IA32) ? 144 : 296)

#define SET_PR_FPVALID(S,V) \

  do { *(int *) (((void *) &((S)->pr_reg)) + PR_REG_SIZE(0)) = (V); } \

/* Full regset -- prstatus on x32, otherwise on ia32 */

#define PRSTATUS_SIZE(S, R) (R != sizeof(S.pr_reg) ? 144 : 296)

#define SET_PR_FPVALID(S, V, R) \

  do { *(int *) (((void *) &((S)->pr_reg)) + R) = (V); } \

  while (0)



#define COMPAT_USE_64BIT_TIME \

arch/x86/include/asm/fpu/signal.h

+6 −0
Original line number Diff line number Diff line
@@ -19,6 +19,12 @@ int ia32_setup_frame(int sig, struct ksignal *ksig, 
# define ia32_setup_rt_frame	__setup_rt_frame

#endif



#ifdef CONFIG_COMPAT

int __copy_siginfo_to_user32(compat_siginfo_t __user *to,

		const siginfo_t *from, bool x32_ABI);

#endif





extern void convert_from_fxsr(struct user_i387_ia32_struct *env,

			      struct task_struct *tsk);

extern void convert_to_fxsr(struct task_struct *tsk,

arch/x86/include/asm/signal.h

+4 −0
Original line number Diff line number Diff line
@@ -23,6 +23,10 @@ typedef struct { 
	unsigned long sig[_NSIG_WORDS];

} sigset_t;



/* non-uapi in-kernel SA_FLAGS for those indicates ABI for a signal frame */

#define SA_IA32_ABI	0x02000000u

#define SA_X32_ABI	0x01000000u



#ifndef CONFIG_COMPAT

typedef sigset_t compat_sigset_t;

#endif

CRA Git | Maintained and supported by SUSTech CRA and CCSE