x86/vdso: Add mremap hook to vm_special_mapping

Add possibility for 32-bit user-space applications to move
the vDSO mapping.

Previously, when a user-space app called mremap() for the vDSO
address, in the syscall return path it would land on the previous
address of the vDSOpage, resulting in segmentation violation.

Now it lands fine and returns to userspace with a remapped vDSO.

This will also fix the context.vdso pointer for 64-bit, which does
not affect the user of vDSO after mremap() currently, but this
may change in the future.

As suggested by Andy, return -EINVAL for mremap() that would
split the vDSO image: that operation cannot possibly result in
a working system so reject it.

Renamed and moved the text_mapping structure declaration inside
map_vdso(), as it used only there and now it complements the
vvar_mapping variable.

There is still a problem for remapping the vDSO in glibc
applications: the linker relocates addresses for syscalls
on the vDSO page, so you need to relink with the new
addresses.

Without that the next syscall through glibc may fail:

  Program received signal SIGSEGV, Segmentation fault.
  #0  0xf7fd9b80 in __kernel_vsyscall ()
  #1  0xf7ec8238 in _exit () from /usr/lib32/libc.so.6

Signed-off-by: Dmitry Safonov <dsafonov@virtuozzo.com>
Acked-by: Andy Lutomirski <luto@kernel.org>
Cc: 0x7f454c46@gmail.com
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-mm@kvack.org
Link: http://lkml.kernel.org/r/20160628113539.13606-2-dsafonov@virtuozzo.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

3 files changed, 55 insertions, 5 deletions

diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index ab220ac9b3b9..3329844e3c43 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
@@ -12,6 +12,7 @@
 #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>
@@ -97,10 +98,40 @@ static int vdso_fault(const struct vm_special_mapping *sm,
 	return 0;
 }
 
-static const struct vm_special_mapping text_mapping = {
-	.name = "[vdso]",
-	.fault = vdso_fault,
-};
+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)
+{
+	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;
+
+	if (WARN_ON_ONCE(current->mm != new_vma->vm_mm))
+		return -EFAULT;
+
+	vdso_fix_landing(image, new_vma);
+	current->mm->context.vdso = (void __user *)new_vma->vm_start;
+
+	return 0;
+}
 
 static int vvar_fault(const struct vm_special_mapping *sm,
 		      struct vm_area_struct *vma, struct vm_fault *vmf)
@@ -151,6 +182,12 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr)
 	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,
+		.mremap = vdso_mremap,
+	};
 	static const struct vm_special_mapping vvar_mapping = {
 		.name = "[vvar]",
 		.fault = vvar_fault,
@@ -185,7 +222,7 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr)
 				       image->size,
 				       VM_READ|VM_EXEC|
 				       VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
-				       &text_mapping);
+				       &vdso_mapping);
 
 	if (IS_ERR(vma)) {
 		ret = PTR_ERR(vma);
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index ca3e517980a0..917f2b6a0cde 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -594,6 +594,9 @@ struct vm_special_mapping {
 	int (*fault)(const struct vm_special_mapping *sm,
 		     struct vm_area_struct *vma,
 		     struct vm_fault *vmf);
+
+	int (*mremap)(const struct vm_special_mapping *sm,
+		     struct vm_area_struct *new_vma);
 };
 
 enum tlb_flush_reason {
diff --git a/mm/mmap.c b/mm/mmap.c
index de2c1769cc68..234edffec1d0 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2943,9 +2943,19 @@ static const char *special_mapping_name(struct vm_area_struct *vma)
 	return ((struct vm_special_mapping *)vma->vm_private_data)->name;
 }
 
+static int special_mapping_mremap(struct vm_area_struct *new_vma)
+{
+	struct vm_special_mapping *sm = new_vma->vm_private_data;
+
+	if (sm->mremap)
+		return sm->mremap(sm, new_vma);
+	return 0;
+}
+
 static const struct vm_operations_struct special_mapping_vmops = {
 	.close = special_mapping_close,
 	.fault = special_mapping_fault,
+	.mremap = special_mapping_mremap,
 	.name = special_mapping_name,
 };