[RFC PATCH for 4.18] rseq: use __u64 for rseq_cs fields, validate user inputs

[Mathieu Desnoyers]

Change the rseq ABI so rseq_cs start_ip, post_commit_offset and abort_ip
fields are seen as 64-bit fields by both 32-bit and 64-bit kernels rather
that ignoring the 32 upper bits on 32-bit kernels. This ensures we have a
consistent behavior for a 32-bit binary executed on 32-bit kernels and in
compat mode on 64-bit kernels.

Validating the value of abort_ip field to be below TASK_SIZE ensures the
kernel don't return to an invalid address when returning to userspace
after an abort. I don't fully trust each architecture code to consistently
deal with invalid return addresses.

Validating the value of the start_ip and post_commit_offset fields
prevents overflow on arithmetic performed on those values, used to
check whether abort_ip is within the rseq critical section.

On 32-bit kernels, the rseq->rseq_cs_padding field is never read by the
kernel. However, 64-bit kernels dealing with 32-bit compat tasks read the
full 64-bit in its entirety, and terminates the offending process with
a segmentation fault if the upper 32 bits are set due to failure of
copy_from_user().

Ensure that both 32-bit and 64-bit kernels dealing with 32-bit tasks end
up terminating offending tasks with a segmentation fault if the upper
32-bit padding bits (rseq->rseq_cs_padding) are set by explicitly ensuring
that padding is zero on 32-bit kernels.

If validation fails, the process is killed with a segmentation fault.

When the signature encountered before abort_ip does not match the expected
signature, return -EINVAL rather than -EPERM to be consistent with other
input validation return codes from rseq_get_rseq_cs().

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@xxxxxxxxxxxx>
CC: "Paul E. McKenney" <paulmck@xxxxxxxxxxxxxxxxxx>
CC: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
CC: Paul Turner <pjt@xxxxxxxxxx>
CC: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
CC: Andy Lutomirski <luto@xxxxxxxxxxxxxx>
CC: Andi Kleen <andi@xxxxxxxxxxxxxx>
CC: Dave Watson <davejwatson@xxxxxx>
CC: Chris Lameter <cl@xxxxxxxxx>
CC: Ingo Molnar <mingo@xxxxxxxxxx>
CC: "H. Peter Anvin" <hpa@xxxxxxxxx>
CC: Ben Maurer <bmaurer@xxxxxx>
CC: Steven Rostedt <rostedt@xxxxxxxxxxx>
CC: Josh Triplett <josh@xxxxxxxxxxxxxxxx>
CC: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
CC: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
CC: Russell King <linux@xxxxxxxxxxxxxxxx>
CC: Catalin Marinas <catalin.marinas@xxxxxxx>
CC: Will Deacon <will.deacon@xxxxxxx>
CC: Michael Kerrisk <mtk.manpages@xxxxxxxxx>
CC: Boqun Feng <boqun.feng@xxxxxxxxx>
CC: linux-api@xxxxxxxxxxxxxxx
---
 include/uapi/linux/rseq.h |  6 +++---
 kernel/rseq.c             | 39 +++++++++++++++++++++++++++++++++++----
 2 files changed, 38 insertions(+), 7 deletions(-)

diff --git a/include/uapi/linux/rseq.h b/include/uapi/linux/rseq.h
index d620fa43756c..519ad6e176d1 100644
--- a/include/uapi/linux/rseq.h
+++ b/include/uapi/linux/rseq.h
@@ -52,10 +52,10 @@ struct rseq_cs {
 	__u32 version;
 	/* enum rseq_cs_flags */
 	__u32 flags;
-	LINUX_FIELD_u32_u64(start_ip);
+	__u64 start_ip;
 	/* Offset from start_ip. */
-	LINUX_FIELD_u32_u64(post_commit_offset);
-	LINUX_FIELD_u32_u64(abort_ip);
+	__u64 post_commit_offset;
+	__u64 abort_ip;
 } __attribute__((aligned(4 * sizeof(__u64))));
 
 /*
diff --git a/kernel/rseq.c b/kernel/rseq.c
index 22b6acf1ad63..1d1dd6aa43f8 100644
--- a/kernel/rseq.c
+++ b/kernel/rseq.c
@@ -112,6 +112,29 @@ static int rseq_reset_rseq_cpu_id(struct task_struct *t)
 	return 0;
 }
 
+#ifndef __LP64__
+/*
+ * Check that padding is zero.
+ */
+static int check_rseq_cs_padding(struct task_struct *t)
+{
+	u32 pad;
+	int ret;
+
+	ret = __get_user(pad, &t->rseq->rseq_cs_padding);
+	if (ret)
+		return ret;
+	if (pad)
+		return -EINVAL;
+	return 0;
+}
+#else
+static int check_rseq_cs_padding(struct task_struct *t)
+{
+	return 0;
+}
+#endif
+
 static int rseq_get_rseq_cs(struct task_struct *t, struct rseq_cs *rseq_cs)
 {
 	struct rseq_cs __user *urseq_cs;
@@ -123,6 +146,8 @@ static int rseq_get_rseq_cs(struct task_struct *t, struct rseq_cs *rseq_cs)
 	ret = __get_user(ptr, &t->rseq->rseq_cs);
 	if (ret)
 		return ret;
+	if (check_rseq_cs_padding(t))
+		return -EINVAL;
 	if (!ptr) {
 		memset(rseq_cs, 0, sizeof(*rseq_cs));
 		return 0;
@@ -130,14 +155,20 @@ static int rseq_get_rseq_cs(struct task_struct *t, struct rseq_cs *rseq_cs)
 	urseq_cs = (struct rseq_cs __user *)ptr;
 	if (copy_from_user(rseq_cs, urseq_cs, sizeof(*rseq_cs)))
 		return -EFAULT;
-	if (rseq_cs->version > 0)
-		return -EINVAL;
 
+	if (rseq_cs->start_ip >= TASK_SIZE ||
+	    rseq_cs->start_ip + rseq_cs->post_commit_offset >= TASK_SIZE ||
+	    rseq_cs->abort_ip >= TASK_SIZE ||
+	    rseq_cs->version > 0)
+		return -EINVAL;
+	/* Check for overflow. */
+	if (rseq_cs->start_ip + rseq_cs->post_commit_offset < rseq_cs->start_ip)
+		return -EINVAL;
 	/* Ensure that abort_ip is not in the critical section. */
 	if (rseq_cs->abort_ip - rseq_cs->start_ip < rseq_cs->post_commit_offset)
 		return -EINVAL;
 
-	usig = (u32 __user *)(rseq_cs->abort_ip - sizeof(u32));
+	usig = (u32 __user *)(unsigned long)(rseq_cs->abort_ip - sizeof(u32));
 	ret = get_user(sig, usig);
 	if (ret)
 		return ret;
@@ -146,7 +177,7 @@ static int rseq_get_rseq_cs(struct task_struct *t, struct rseq_cs *rseq_cs)
 		printk_ratelimited(KERN_WARNING
 			"Possible attack attempt. Unexpected rseq signature 0x%x, expecting 0x%x (pid=%d, addr=%p).\n",
 			sig, current->rseq_sig, current->pid, usig);
-		return -EPERM;
+		return -EINVAL;
 	}
 	return 0;
 }
-- 
2.11.0