[patch 08/10] rseq: Implement read only ABI enforcement for optimized RSEQ V2 mode

[Thomas Gleixner <tglx@kernel.org>]

The optimized RSEQ V2 mode requires that user space adheres to the ABI
specification and does not modify the read-only fields cpu_id_start,
cpu_id, node_id and mm_cid behind the kernel's back.

While the kernel does not rely on these fields, the adherence to this is a
fundamental prerequisite to allow multiple entities, e.g. libraries, in an
application to utilize the full potential of RSEQ without stepping on each
other toes.

Validate this adherence on every update of these fields. If the kernel
detects that user space modified the fields, the application is force
terminated.

Fixes: d6200245c75e ("rseq: Allow registering RSEQ with slice extension")
Signed-off-by: Thomas Gleixner <tglx@kernel.org>
Cc: stable@vger.kernel.org
---
 include/linux/rseq_entry.h |   71 +++++++++++++++++----------------------------
 1 file changed, 28 insertions(+), 43 deletions(-)

--- a/include/linux/rseq_entry.h
+++ b/include/linux/rseq_entry.h
@@ -248,7 +248,6 @@ static __always_inline bool rseq_grant_s
 #endif /* !CONFIG_RSEQ_SLICE_EXTENSION */
 
 bool rseq_debug_update_user_cs(struct task_struct *t, struct pt_regs *regs, unsigned long csaddr);
-bool rseq_debug_validate_ids(struct task_struct *t);
 
 static __always_inline void rseq_note_user_irq_entry(void)
 {
@@ -368,43 +367,6 @@ bool rseq_debug_update_user_cs(struct ta
 	return false;
 }
 
-/*
- * On debug kernels validate that user space did not mess with it if the
- * debug branch is enabled.
- */
-bool rseq_debug_validate_ids(struct task_struct *t)
-{
-	struct rseq __user *rseq = t->rseq.usrptr;
-	u32 cpu_id, uval, node_id;
-
-	/*
-	 * On the first exit after registering the rseq region CPU ID is
-	 * RSEQ_CPU_ID_UNINITIALIZED and node_id in user space is 0!
-	 */
-	node_id = t->rseq.ids.cpu_id != RSEQ_CPU_ID_UNINITIALIZED ?
-		  cpu_to_node(t->rseq.ids.cpu_id) : 0;
-
-	scoped_user_read_access(rseq, efault) {
-		unsafe_get_user(cpu_id, &rseq->cpu_id_start, efault);
-		if (cpu_id != t->rseq.ids.cpu_id)
-			goto die;
-		unsafe_get_user(uval, &rseq->cpu_id, efault);
-		if (uval != cpu_id)
-			goto die;
-		unsafe_get_user(uval, &rseq->node_id, efault);
-		if (uval != node_id)
-			goto die;
-		unsafe_get_user(uval, &rseq->mm_cid, efault);
-		if (uval != t->rseq.ids.mm_cid)
-			goto die;
-	}
-	return true;
-die:
-	t->rseq.event.fatal = true;
-efault:
-	return false;
-}
-
 #endif /* RSEQ_BUILD_SLOW_PATH */
 
 /*
@@ -519,12 +481,32 @@ bool rseq_set_ids_get_csaddr(struct task
 {
 	struct rseq __user *rseq = t->rseq.usrptr;
 
-	if (static_branch_unlikely(&rseq_debug_enabled)) {
-		if (!rseq_debug_validate_ids(t))
-			return false;
-	}
-
 	scoped_user_rw_access(rseq, efault) {
+		/* Validate the R/O fields for debug and optimized mode */
+		if (static_branch_unlikely(&rseq_debug_enabled) || rseq_v2(t)) {
+			u32 cpu_id, uval, node_id;
+
+			/*
+			 * On the first exit after registering the rseq region CPU ID is
+			 * RSEQ_CPU_ID_UNINITIALIZED and node_id in user space is 0!
+			 */
+			node_id = t->rseq.ids.cpu_id != RSEQ_CPU_ID_UNINITIALIZED ?
+				cpu_to_node(t->rseq.ids.cpu_id) : 0;
+
+			unsafe_get_user(cpu_id, &rseq->cpu_id_start, efault);
+			if (cpu_id != t->rseq.ids.cpu_id)
+				goto die;
+			unsafe_get_user(uval, &rseq->cpu_id, efault);
+			if (uval != cpu_id)
+				goto die;
+			unsafe_get_user(uval, &rseq->node_id, efault);
+			if (uval != node_id)
+				goto die;
+			unsafe_get_user(uval, &rseq->mm_cid, efault);
+			if (uval != t->rseq.ids.mm_cid)
+				goto die;
+		}
+
 		unsafe_put_user(ids->cpu_id, &rseq->cpu_id_start, efault);
 		unsafe_put_user(ids->cpu_id, &rseq->cpu_id, efault);
 		unsafe_put_user(node_id, &rseq->node_id, efault);
@@ -543,6 +525,9 @@ bool rseq_set_ids_get_csaddr(struct task
 	rseq_stat_inc(rseq_stats.ids);
 	rseq_trace_update(t, ids);
 	return true;
+
+die:
+	t->rseq.event.fatal = true;
 efault:
 	return false;
 }