[bpf-next v3 1/3] mm: add copy_remote_vm_str

[Jordan Rome <linux@jordanrome.com>]

Similar to `access_process_vm` but specific to strings.
Also chunks reads by page and utilizes `strscpy`
for handling null termination.

Signed-off-by: Jordan Rome <linux@jordanrome.com>
---
 include/linux/mm.h |   3 ++
 mm/memory.c        | 119 +++++++++++++++++++++++++++++++++++++++++++++
 mm/nommu.c         |  68 ++++++++++++++++++++++++++
 3 files changed, 190 insertions(+)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index f02925447e59..f3a05b3eb2f2 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2485,6 +2485,9 @@ extern int access_process_vm(struct task_struct *tsk, unsigned long addr,
 extern int access_remote_vm(struct mm_struct *mm, unsigned long addr,
 		void *buf, int len, unsigned int gup_flags);

+extern int copy_remote_vm_str(struct task_struct *tsk, unsigned long addr,
+		void *buf, int len, unsigned int gup_flags);
+
 long get_user_pages_remote(struct mm_struct *mm,
 			   unsigned long start, unsigned long nr_pages,
 			   unsigned int gup_flags, struct page **pages,
diff --git a/mm/memory.c b/mm/memory.c
index 398c031be9ba..905e3f10fad0 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -6714,6 +6714,125 @@ int access_process_vm(struct task_struct *tsk, unsigned long addr,
 }
 EXPORT_SYMBOL_GPL(access_process_vm);

+/*
+ * Copy a string from another process's address space as given in mm.
+ * If there is any error return -EFAULT.
+ */
+static int __copy_remote_vm_str(struct mm_struct *mm, unsigned long addr,
+			      void *buf, int len, unsigned int gup_flags)
+{
+	void *old_buf = buf;
+	int err = 0;
+
+	if (mmap_read_lock_killable(mm))
+		return -EFAULT;
+
+	/* Untag the address before looking up the VMA */
+	addr = untagged_addr_remote(mm, addr);
+
+	/* Avoid triggering the temporary warning in __get_user_pages */
+	if (!vma_lookup(mm, addr)) {
+		err = -EFAULT;
+		goto out;
+	}
+
+	while (len) {
+		int bytes, offset, retval, end;
+		void *maddr;
+		struct page *page;
+		struct vm_area_struct *vma = NULL;
+
+		page = get_user_page_vma_remote(mm, addr, gup_flags, &vma);
+
+		if (IS_ERR(page)) {
+			/*
+			 * Treat as a total failure for now until we decide how
+			 * to handle the CONFIG_HAVE_IOREMAP_PROT case and
+			 * stack expansion.
+			 */
+			err = -EFAULT;
+			goto out;
+		}
+
+		bytes = len;
+		offset = addr & (PAGE_SIZE - 1);
+		if (bytes > PAGE_SIZE - offset)
+			bytes = PAGE_SIZE - offset;
+
+		maddr = kmap_local_page(page);
+		retval = strscpy(buf, maddr + offset, bytes);
+		unmap_and_put_page(page, maddr);
+
+		if (retval > -1 && retval < bytes) {
+			/* found the end of the string */
+			buf += retval;
+			goto out;
+		}
+
+		if (retval == -E2BIG) {
+			retval = bytes;
+			/*
+			 * Because strscpy always null terminates we need to
+			 * copy the last byte in the page if we are going to
+			 * load more pages
+			 */
+			if (bytes < len) {
+				end = bytes - 1;
+				copy_from_user_page(vma,
+						page,
+						addr + end,
+						buf + end,
+						maddr + (PAGE_SIZE - 1),
+						1);
+			}
+		}
+
+		len -= retval;
+		buf += retval;
+		addr += retval;
+	}
+
+out:
+	mmap_read_unlock(mm);
+	if (err)
+		return err;
+
+	return buf - old_buf;
+}
+
+/**
+ * copy_remote_vm_str - copy a string from another process's address space.
+ * @tsk:	the task of the target address space
+ * @addr:	start address to read from
+ * @buf:	destination buffer
+ * @len:	number of bytes to transfer
+ * @gup_flags:	flags modifying lookup behaviour
+ *
+ * The caller must hold a reference on @mm.
+ *
+ * Return: number of bytes copied from @addr (source) to @buf (destination).
+ * If the source string is shorter than @len then return the length of the
+ * source string. If the source string is longer than @len, return @len.
+ * On any error, return -EFAULT.
+ */
+int copy_remote_vm_str(struct task_struct *tsk, unsigned long addr,
+		void *buf, int len, unsigned int gup_flags)
+{
+	struct mm_struct *mm;
+	int ret;
+
+	mm = get_task_mm(tsk);
+	if (!mm)
+		return -EFAULT;
+
+	ret = __copy_remote_vm_str(mm, addr, buf, len, gup_flags);
+
+	mmput(mm);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(copy_remote_vm_str);
+
 /*
  * Print the name of a VMA.
  */
diff --git a/mm/nommu.c b/mm/nommu.c
index 9cb6e99215e2..23281751b1eb 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -1701,6 +1701,74 @@ int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, in
 }
 EXPORT_SYMBOL_GPL(access_process_vm);

+/*
+ * Copy a string from another process's address space as given in mm.
+ * If there is any error return -EFAULT.
+ */
+static int __copy_remote_vm_str(struct mm_struct *mm, unsigned long addr,
+			      void *buf, int len)
+{
+	int ret = 0;
+
+	if (mmap_read_lock_killable(mm))
+		return -EFAULT;
+
+	/* the access must start within one of the target process's mappings */
+	vma = find_vma(mm, addr);
+	if (vma) {
+		/* don't overrun this mapping */
+		if (addr + len >= vma->vm_end)
+			len = vma->vm_end - addr;
+
+		/* only read mappings where it is permitted */
+		if (vma->vm_flags & VM_MAYREAD) {
+			ret = strscpy(buf, addr, len);
+			if (ret == -E2BIG)
+				ret = len;
+		} else {
+			ret = -EFAULT;
+		}
+	} else {
+		ret = -EFAULT;
+	}
+
+	mmap_read_unlock(mm);
+	return ret;
+}
+
+/**
+ * copy_remote_vm_str - copy a string from another process's address space.
+ * @tsk:	the task of the target address space
+ * @addr:	start address to read from
+ * @buf:	destination buffer
+ * @len:	number of bytes to transfer
+ * @gup_flags:	flags modifying lookup behaviour (unused)
+ *
+ * The caller must hold a reference on @mm.
+ *
+ * Return: number of bytes copied from @addr (source) to @buf (destination).
+ * If the source string is shorter than @len then return the length of the
+ * source string. If the source string is longer than @len, return @len.
+ * On any error, return -EFAULT.
+ */
+int copy_remote_vm_str(struct task_struct *tsk, unsigned long addr,
+		void *buf, int len, unsigned int gup_flags)
+{
+	struct mm_struct *mm;
+	int ret;
+
+	mm = get_task_mm(tsk);
+	if (!mm)
+		return -EFAULT;
+
+	ret = __copy_remote_vm_str(mm, addr, buf, len);
+
+	mmput(mm);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(copy_remote_vm_str);
+
 /**
  * nommu_shrink_inode_mappings - Shrink the shared mappings on an inode
  * @inode: The inode to check
--
2.43.5