4 files changed, 39 insertions, 8 deletions
diff --git a/include/linux/rseq.h b/include/linux/rseq.h
index 7a01a0760405..b9d62fc2140d 100644
--- a/include/linux/rseq.h
+++ b/include/linux/rseq.h
@@ -146,6 +146,18 @@ static inline void rseq_fork(struct task_struct *t, u64 clone_flags)
 		t->rseq = current->rseq;
 }
 
+/*
+ * Value returned by getauxval(AT_RSEQ_ALIGN) and expected by rseq
+ * registration. This is the active rseq area size rounded up to next
+ * power of 2, which guarantees that the rseq structure will always be
+ * aligned on the nearest power of two large enough to contain it, even
+ * as it grows.
+ */
+static inline unsigned int rseq_alloc_align(void)
+{
+	return 1U << get_count_order(offsetof(struct rseq, end));
+}
+
 #else /* CONFIG_RSEQ */
 static inline void rseq_handle_slowpath(struct pt_regs *regs) { }
 static inline void rseq_signal_deliver(struct ksignal *ksig, struct pt_regs *regs) { }
diff --git a/include/linux/rseq_entry.h b/include/linux/rseq_entry.h
index cbc4a791618b..c6831c93cd6e 100644
--- a/include/linux/rseq_entry.h
+++ b/include/linux/rseq_entry.h
@@ -216,10 +216,10 @@ efault:
 }
 
 #else /* CONFIG_RSEQ_SLICE_EXTENSION */
-static inline bool rseq_slice_extension_enabled(void) { return false; }
-static inline bool rseq_arm_slice_extension_timer(void) { return false; }
-static inline void rseq_slice_clear_grant(struct task_struct *t) { }
-static inline bool rseq_grant_slice_extension(bool work_pending) { return false; }
+static __always_inline bool rseq_slice_extension_enabled(void) { return false; }
+static __always_inline bool rseq_arm_slice_extension_timer(void) { return false; }
+static __always_inline void rseq_slice_clear_grant(struct task_struct *t) { }
+static __always_inline bool rseq_grant_slice_extension(bool work_pending) { return false; }
 #endif /* !CONFIG_RSEQ_SLICE_EXTENSION */
 
 bool rseq_debug_update_user_cs(struct task_struct *t, struct pt_regs *regs, unsigned long csaddr);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 074ad4ef3d81..a7b4a980eb2f 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -579,6 +579,7 @@ struct sched_entity {
 	u64				deadline;
 	u64				min_vruntime;
 	u64				min_slice;
+	u64				max_slice;
 
 	struct list_head		group_node;
 	unsigned char			on_rq;
diff --git a/include/uapi/linux/rseq.h b/include/uapi/linux/rseq.h
index 863c4a00a66b..f69344fe6c08 100644
--- a/include/uapi/linux/rseq.h
+++ b/include/uapi/linux/rseq.h
@@ -87,10 +87,17 @@ struct rseq_slice_ctrl {
 };
 
 /*
- * struct rseq is aligned on 4 * 8 bytes to ensure it is always
- * contained within a single cache-line.
+ * The original size and alignment of the allocation for struct rseq is
+ * 32 bytes.
  *
- * A single struct rseq per thread is allowed.
+ * The allocation size needs to be greater or equal to
+ * max(getauxval(AT_RSEQ_FEATURE_SIZE), 32), and the allocation needs to
+ * be aligned on max(getauxval(AT_RSEQ_ALIGN), 32).
+ *
+ * As an alternative, userspace is allowed to use both the original size
+ * and alignment of 32 bytes for backward compatibility.
+ *
+ * A single active struct rseq registration per thread is allowed.
  */
 struct rseq {
 	/*
@@ -181,9 +188,20 @@ struct rseq {
 	struct rseq_slice_ctrl slice_ctrl;
 
 	/*
+	 * Before rseq became extensible, its original size was 32 bytes even
+	 * though the active rseq area was only 20 bytes.
+	 * Exposing a 32 bytes feature size would make life needlessly painful
+	 * for userspace. Therefore, add a reserved byte after byte 32
+	 * to bump the rseq feature size from 32 to 33.
+	 * The next field to be added to the rseq area will be larger
+	 * than one byte, and will replace this reserved byte.
+	 */
+	__u8 __reserved;
+
+	/*
 	 * Flexible array member at end of structure, after last feature field.
 	 */
 	char end[];
-} __attribute__((aligned(4 * sizeof(__u64))));
+} __attribute__((aligned(32)));
 
 #endif /* _UAPI_LINUX_RSEQ_H */