[PATCH bpf-next v3 2/7] bpf: Add user memory access kfuncs for mm_struct

[Anastasios Papagiannis]

On CONFIG_MMU kernels, when security_bprm_check() runs, the argument and
environment strings for the exec have been copied into bprm->mm. The new
address space is not associated with a task_struct until exec_mmap(), so
existing BPF user memory helpers can only read from the calling task's old
address space.

Add bpf_copy_from_user_mm() and bpf_copy_from_user_mm_str() kfuncs. Both
take a struct mm_struct pointer directly, allowing callers to access
trusted address spaces that are not associated with a task_struct.

bpf_copy_from_user_mm() has similar semantics to
bpf_copy_from_user_task(). bpf_copy_from_user_mm_str() copies one
NUL-terminated string and returns its size including the NUL terminator.
It accepts BPF_F_PAD_ZEROS to clear unused destination bytes on success.

Register both kfuncs and mark them KF_SLEEPABLE because accessing the
remote address space can fault.

On !CONFIG_MMU, exec argument and environment strings remain in
bprm->page[] until the binary loader transfers them to the new process
stack. They are therefore not accessible through bprm->mm at the
bprm_check_security hook. The linux_binprm use described above is
CONFIG_MMU-only, although the new kfuncs remain available for other
address spaces on !CONFIG_MMU.

Signed-off-by: Anastasios Papagiannis <tasos.papagiannnis@xxxxxxxxx>
---
 kernel/bpf/helpers.c | 115 +++++++++++++++++++++++++++++++++++++------
 1 file changed, 101 insertions(+), 14 deletions(-)

diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index b3cc5c8fc875..19c01aa734ae 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -32,6 +32,13 @@
 
 #include "../../lib/kstrtox.h"
 
+int bpf_copy_from_user_mm(void *dst, u32 dst__sz,
+			  const void __user *unsafe_ptr__ign,
+			  struct mm_struct *mm, u64 flags);
+int bpf_copy_from_user_mm_str(void *dst, u32 dst__sz,
+			      const void __user *unsafe_ptr__ign,
+			      struct mm_struct *mm, u64 flags);
+
 /* If kernel subsystem is allowing eBPF programs to call this function,
  * inside its own verifier_ops->get_func_proto() callback it should return
  * bpf_map_lookup_elem_proto, so that verifier can properly check the arguments
@@ -682,22 +689,15 @@ const struct bpf_func_proto bpf_copy_from_user_proto = {
 BPF_CALL_5(bpf_copy_from_user_task, void *, dst, u32, size,
 	   const void __user *, user_ptr, struct task_struct *, tsk, u64, flags)
 {
+	struct mm_struct *mm;
 	int ret;
 
-	/* flags is not used yet */
-	if (unlikely(flags))
-		return -EINVAL;
-
-	if (unlikely(!size))
-		return 0;
-
-	ret = access_process_vm(tsk, (unsigned long)user_ptr, dst, size, 0);
-	if (ret == size)
-		return 0;
+	mm = get_task_mm(tsk);
+	ret = bpf_copy_from_user_mm(dst, size, user_ptr, mm, flags);
+	if (mm)
+		mmput(mm);
 
-	memset(dst, 0, size);
-	/* Return -EFAULT for partial read */
-	return ret < 0 ? ret : -EFAULT;
+	return ret;
 }
 
 const struct bpf_func_proto bpf_copy_from_user_task_proto = {
@@ -3680,6 +3680,83 @@ __bpf_kfunc int bpf_copy_from_user_str(void *dst, u32 dst__sz, const void __user
 __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)
+{
+	struct mm_struct *mm;
+	int ret;
+
+	mm = get_task_mm(tsk);
+	ret = bpf_copy_from_user_mm_str(dst, dst__sz, unsafe_ptr__ign,
+					mm, flags);
+	if (mm)
+		mmput(mm);
+
+	return ret;
+}
+
+/**
+ * bpf_copy_from_user_mm() - Copy data from an address space
+ * @dst:             Destination address, in kernel space
+ * @dst__sz:         Number of bytes to copy
+ * @unsafe_ptr__ign: Source address in the address space
+ * @mm:              Address space to copy from
+ * @flags:           Reserved for future use; must be zero
+ *
+ * Copies data from the user address space associated with @mm. The destination
+ * is zeroed if an attempted copy cannot be completed in full. Unsupported
+ * flags return -EINVAL without modifying @dst.
+ *
+ * Return: 0 on success, -EINVAL if @flags is non-zero, or -EFAULT if the copy
+ * fails or is partial.
+ */
+__bpf_kfunc int bpf_copy_from_user_mm(void *dst, u32 dst__sz,
+				      const void __user *unsafe_ptr__ign,
+				      struct mm_struct *mm, u64 flags)
+{
+	int ret;
+
+	if (unlikely(flags))
+		return -EINVAL;
+
+	if (unlikely(!dst__sz))
+		return 0;
+
+	if (unlikely(!mm)) {
+		memset(dst, 0, dst__sz);
+		return -EFAULT;
+	}
+
+	ret = access_remote_vm(mm, (unsigned long)unsafe_ptr__ign,
+			       dst, dst__sz, 0);
+	if (ret == dst__sz)
+		return 0;
+
+	memset(dst, 0, dst__sz);
+	return ret < 0 ? ret : -EFAULT;
+}
+
+/**
+ * bpf_copy_from_user_mm_str() - Copy a string from an 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, including the trailing NUL
+ * @unsafe_ptr__ign: Source address in the address space
+ * @mm:              Address space to copy from
+ * @flags:           The only supported flag is BPF_F_PAD_ZEROS
+ *
+ * Copies a NUL-terminated string from the user address space associated with
+ * @mm. If the string is too long, @dst is still NUL-terminated unless @dst__sz
+ * is zero.
+ *
+ * If the flags are valid and BPF_F_PAD_ZEROS is set, the unused portion of
+ * @dst is cleared on success and all of @dst is cleared on a copy failure.
+ * Unsupported flags return -EINVAL without modifying @dst.
+ *
+ * Return: The number of copied bytes including the NUL terminator on success,
+ * or a negative error code on failure.
+ */
+__bpf_kfunc int bpf_copy_from_user_mm_str(void *dst, u32 dst__sz,
+					  const void __user *unsafe_ptr__ign,
+					  struct mm_struct *mm, u64 flags)
 {
 	int ret;
 
@@ -3689,7 +3766,15 @@ __bpf_kfunc int bpf_copy_from_user_task_str(void *dst, u32 dst__sz,
 	if (unlikely(dst__sz == 0))
 		return 0;
 
-	ret = copy_remote_vm_str(tsk, (unsigned long)unsafe_ptr__ign, dst, dst__sz, 0);
+	if (unlikely(!mm)) {
+		if (flags & BPF_F_PAD_ZEROS)
+			memset(dst, 0, dst__sz);
+		else
+			*(char *)dst = '\0';
+		return -EFAULT;
+	}
+
+	ret = copy_remote_mm_str(mm, (unsigned long)unsafe_ptr__ign, dst, dst__sz, 0);
 	if (ret < 0) {
 		if (flags & BPF_F_PAD_ZEROS)
 			memset(dst, 0, dst__sz);
@@ -4924,6 +5009,8 @@ 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_mm, KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_copy_from_user_mm_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)
-- 
2.55.0