[patch 15/16] x86/ldt: Add VMA management code

[Thomas Gleixner]

From: Thomas Gleixner <tglx@xxxxxxxxxxxxx>

Add the VMA management code to LDT which allows to install the LDT as a
special mapping, like VDSO and uprobes. The mapping is in the user address
space, but without the usr bit set and read only. Split out for ease of
review.

Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
---
 arch/x86/kernel/ldt.c |  103 +++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 102 insertions(+), 1 deletion(-)

--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -31,6 +31,7 @@
 struct ldt_mapping {
 	struct ldt_struct		ldts[2];
 	unsigned int			ldt_index;
+	unsigned int			ldt_mapped;
 };
 
 /* After calling this, the LDT is immutable. */
@@ -208,6 +209,105 @@ bool __ldt_write_fault(unsigned long add
 	return true;
 }
 
+static int ldt_fault(const struct vm_special_mapping *sm,
+		     struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	struct ldt_mapping *lmap = vma->vm_mm->context.ldt_mapping;
+	struct ldt_struct *ldt = lmap->ldts;
+	pgoff_t pgo = vmf->pgoff;
+	struct page *page;
+
+	if (pgo >= LDT_ENTRIES_PAGES) {
+		pgo -= LDT_ENTRIES_PAGES;
+		ldt++;
+	}
+	if (pgo >= LDT_ENTRIES_PAGES)
+		return VM_FAULT_SIGBUS;
+
+	page = ldt->pages[pgo];
+	if (!page)
+		return VM_FAULT_SIGBUS;
+	get_page(page);
+	vmf->page = page;
+	return 0;
+}
+
+static int ldt_mremap(const struct vm_special_mapping *sm,
+		      struct vm_area_struct *new_vma)
+{
+	return -EINVAL;
+}
+
+static void ldt_close(const struct vm_special_mapping *sm,
+		      struct vm_area_struct *vma)
+{
+	struct mm_struct *mm = vma->vm_mm;
+	struct ldt_struct *ldt;
+
+	/*
+	 * Orders against ldt_install().
+	 */
+	mutex_lock(&mm->context.lock);
+	ldt = mm->context.ldt;
+	ldt_install_mm(mm, NULL);
+	cleanup_ldt_struct(ldt);
+	mm->context.ldt_mapping->ldt_mapped = 0;
+	mutex_unlock(&mm->context.lock);
+}
+
+static const struct vm_special_mapping ldt_special_mapping = {
+	.name	= "[ldt]",
+	.fault	= ldt_fault,
+	.mremap	= ldt_mremap,
+	.close	= ldt_close,
+};
+
+static struct vm_area_struct *ldt_alloc_vma(struct mm_struct *mm,
+					    struct ldt_mapping *lmap)
+{
+	unsigned long vm_flags, size;
+	struct vm_area_struct *vma;
+	unsigned long addr;
+
+	size = 2 * LDT_ENTRIES_MAP_SIZE;
+	addr = get_unmapped_area(NULL, TASK_SIZE - PAGE_SIZE, size, 0, 0);
+	if (IS_ERR_VALUE(addr))
+		return ERR_PTR(addr);
+
+	vm_flags = VM_READ | VM_LOCKED | VM_WIPEONFORK | VM_NOUSER | VM_SHARED;
+	vma = _install_special_mapping(mm, addr, size, vm_flags,
+				       &ldt_special_mapping);
+	if (IS_ERR(vma))
+		return vma;
+
+	lmap->ldts[0].entries = (struct desc_struct *) addr;
+	addr += LDT_ENTRIES_MAP_SIZE;
+	lmap->ldts[1].entries = (struct desc_struct *) addr;
+	return vma;
+}
+
+static int ldt_mmap(struct mm_struct *mm, struct ldt_mapping *lmap)
+{
+	struct vm_area_struct *vma;
+	int ret = 0;
+
+	if (down_write_killable(&mm->mmap_sem))
+		return -EINTR;
+	vma = ldt_alloc_vma(mm, lmap);
+	if (IS_ERR(vma)) {
+		ret = PTR_ERR(vma);
+	} else {
+		/*
+		 * The moment mmap_sem() is released munmap() can observe
+		 * the mapping and make it go away through ldt_close(). But
+		 * for now there is mapping.
+		 */
+		lmap->ldt_mapped = 1;
+	}
+	up_write(&mm->mmap_sem);
+	return ret;
+}
+
 /* The caller must call finalize_ldt_struct on the result. LDT starts zeroed. */
 static struct ldt_struct *alloc_ldt_struct(unsigned int num_entries)
 {
@@ -350,7 +450,8 @@ static int read_ldt(void __user *ptr, un
 
 	down_read(&mm->context.ldt_usr_sem);
 
-	ldt = mm->context.ldt;
+	/* Might race against vm_unmap, which installs a NULL LDT */
+	ldt = READ_ONCE(mm->context.ldt);
 	if (!ldt)
 		goto out_unlock;