[bpf-next,v1,1/2] bpf: Add bpf_copy_from_user_task_str kfunc

Commit Message

Jordan Rome Dec. 20, 2024, 7:10 p.m. UTC

This new kfunc will be able to copy a string
from another process's/task's address space.
This is similar to `bpf_copy_from_user_str`
but accepts a `struct task_struct*` argument.

This required adding an additional function
in memory.c, namely `copy_str_from_process_vm`,
which works similar to `access_process_vm`
but utilizes the `strncpy_from_user` helper
and only supports reading/copying and not writing.

Signed-off-by: Jordan Rome <[e-mail]>
---
 include/linux/mm.h   |   3 ++
 kernel/bpf/helpers.c |  46 ++++++++++++++++++++
 mm/memory.c          | 101 +++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 150 insertions(+)

--
2.43.5

Patch

diff --git a/include/linux/mm.h b/include/linux/mm.h
index c39c4945946c..52b304b20630 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2484,6 +2484,9 @@  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_str_from_process_vm(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/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 751c150f9e1c..b282dd6aa95f 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -3057,6 +3057,51 @@  __bpf_kfunc int bpf_copy_from_user_str(void *dst, u32 dst__sz, const void __user
 	return ret + 1;
 }

+/**
+ * bpf_copy_from_user_task_str() - Copy a string from an task's address space
+ * @dst:             Destination address, in kernel space.  This buffer must be
+ *                   at least @dst__sz bytes long.
+ * @dst__sz:         Maximum number of bytes to copy, includes the trailing NUL.
+ * @unsafe_ptr__ign: Source address in the task's address space.
+ * @tsk:             The task whose address space will be used
+ * @flags:           The only supported flag is BPF_F_PAD_ZEROS
+ *
+ * Copies a NULL-terminated string from a task's address space to BPF space.
+ * If user string is too long this will still ensure zero termination in the
+ * dst buffer unless buffer size is 0.
+ *
+ * If BPF_F_PAD_ZEROS flag is set, memset the tail of @dst to 0 on success and
+ * memset all of @dst on failure.
+ */
+__bpf_kfunc int bpf_copy_from_user_task_str(void *dst, u32 dst__sz, const void __user *unsafe_ptr__ign, struct task_struct *tsk, u64 flags)
+{
+	int count = dst__sz - 1;
+	int ret = 0;
+
+	if (unlikely(flags & ~BPF_F_PAD_ZEROS))
+		return -EINVAL;
+
+	if (unlikely(!dst__sz))
+		return 0;
+
+	ret = copy_str_from_process_vm(tsk, (unsigned long)unsafe_ptr__ign, dst, count, 0);
+
+	if (ret <= 0) {
+		if (flags & BPF_F_PAD_ZEROS)
+			memset((char *)dst, 0, dst__sz);
+		return ret;
+	}
+
+	if (ret < count) {
+		if (flags & BPF_F_PAD_ZEROS)
+			memset((char *)dst + ret, 0, dst__sz - ret);
+	} else {
+		((char *)dst)[count] = '\0';
+	}
+
+	return ret + 1;
+}
+
 __bpf_kfunc_end_defs();

 BTF_KFUNCS_START(generic_btf_ids)
@@ -3145,6 +3190,7 @@  BTF_ID_FLAGS(func, bpf_iter_bits_new, KF_ITER_NEW)
 BTF_ID_FLAGS(func, bpf_iter_bits_next, KF_ITER_NEXT | KF_RET_NULL)
 BTF_ID_FLAGS(func, bpf_iter_bits_destroy, KF_ITER_DESTROY)
 BTF_ID_FLAGS(func, bpf_copy_from_user_str, KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_copy_from_user_task_str, KF_SLEEPABLE)
 BTF_ID_FLAGS(func, bpf_get_kmem_cache)
 BTF_ID_FLAGS(func, bpf_iter_kmem_cache_new, KF_ITER_NEW | KF_SLEEPABLE)
 BTF_ID_FLAGS(func, bpf_iter_kmem_cache_next, KF_ITER_NEXT | KF_RET_NULL | KF_SLEEPABLE)
diff --git a/mm/memory.c b/mm/memory.c
index 75c2dfd04f72..514490bd7d6d 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -6673,6 +6673,75 @@  static int __access_remote_vm(struct mm_struct *mm, unsigned long addr,
 	return buf - old_buf;
 }

+/*
+ * Copy a string from another process's address space as given in mm.
+ * Don't return partial results. If there is any error return -EFAULT.
+ */
+static int __copy_str_from_remote_vm(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)) {
+		mmap_read_unlock(mm);
+		return -EFAULT;
+	}
+
+	while (len) {
+		int bytes, offset, retval;
+		void *maddr;
+		struct vm_area_struct *vma = NULL;
+		struct page *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;
+			break;
+		}
+
+		bytes = len;
+		offset = addr & (PAGE_SIZE - 1);
+		if (bytes > PAGE_SIZE - offset)
+			bytes = PAGE_SIZE - offset;
+
+		maddr = kmap_local_page(page);
+		retval = strncpy_from_user(buf, (const char __user *)addr, bytes);
+		unmap_and_put_page(page, maddr);
+
+		if (retval < 0) {
+			err = retval;
+			break;
+		}
+
+		len -= retval;
+		buf += retval;
+		addr += retval;
+
+		/* Found the end of the string */
+		if (retval < bytes)
+			break;
+	}
+	mmap_read_unlock(mm);
+
+	if (err)
+		return err;
+
+	return buf - old_buf;
+}
+
 /**
  * access_remote_vm - access another process' address space
  * @mm:		the mm_struct of the target address space
@@ -6714,6 +6783,38 @@  int access_process_vm(struct task_struct *tsk, unsigned long addr,
 }
 EXPORT_SYMBOL_GPL(access_process_vm);

+/**
+ * copy_str_from_process_vm - copy a string from another process's address space.
+ * @tsk:	the task of the target address space
+ * @addr:	start address to access
+ * @buf:	source or 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 source to destination. If the string
+ * is shorter than @len then return the length of the string.
+ * On any error, return -EFAULT.
+ */
+int copy_str_from_process_vm(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_str_from_remote_vm(mm, addr, buf, len, gup_flags);
+
+	mmput(mm);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(copy_str_from_process_vm);
+
 /*
  * Print the name of a VMA.
  */