rseq: Introduce struct rseq_data

In preparation for a major rewrite of this code, provide a data structure
for rseq management.

Put all the rseq related data into it (except for the debug part), which
allows to simplify fork/execve by using memset() and memcpy() instead of
adding new fields to initialize over and over.

Create a storage struct for event management as well and put the
sched_switch event and a indicator for RSEQ on a task into it as a
start. That uses a union, which allows to mask and clear the whole lot
efficiently.

The indicators are explicitly not a bit field. Bit fields generate abysmal
code.

The boolean members are defined as u8 as that actually guarantees that it
fits. There seem to be strange architecture ABIs which need more than 8
bits for a boolean.

The has_rseq member is redundant vs. task::rseq, but it turns out that
boolean operations and quick checks on the union generate better code than
fiddling with separate entities and data types.

This struct will be extended over time to carry more information.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://patch.msgid.link/20251027084306.527086690@linutronix.de

3 files changed, 76 insertions, 37 deletions

diff --git a/include/linux/rseq.h b/include/linux/rseq.h
index c6267f70c746..ab91b1e6bb4a 100644
--- a/include/linux/rseq.h
+++ b/include/linux/rseq.h
@@ -9,22 +9,22 @@ void __rseq_handle_notify_resume(struct ksignal *sig, struct pt_regs *regs);
 
 static inline void rseq_handle_notify_resume(struct pt_regs *regs)
 {
-	if (current->rseq)
+	if (current->rseq.event.has_rseq)
 		__rseq_handle_notify_resume(NULL, regs);
 }
 
 static inline void rseq_signal_deliver(struct ksignal *ksig, struct pt_regs *regs)
 {
-	if (current->rseq) {
-		current->rseq_event_pending = true;
+	if (current->rseq.event.has_rseq) {
+		current->rseq.event.sched_switch = true;
 		__rseq_handle_notify_resume(ksig, regs);
 	}
 }
 
 static inline void rseq_sched_switch_event(struct task_struct *t)
 {
-	if (t->rseq) {
-		t->rseq_event_pending = true;
+	if (t->rseq.event.has_rseq) {
+		t->rseq.event.sched_switch = true;
 		set_tsk_thread_flag(t, TIF_NOTIFY_RESUME);
 	}
 }
@@ -32,8 +32,9 @@ static inline void rseq_sched_switch_event(struct task_struct *t)
 static __always_inline void rseq_exit_to_user_mode(void)
 {
 	if (IS_ENABLED(CONFIG_DEBUG_RSEQ)) {
-		if (WARN_ON_ONCE(current->rseq && current->rseq_event_pending))
-			current->rseq_event_pending = false;
+		if (WARN_ON_ONCE(current->rseq.event.has_rseq &&
+				 current->rseq.event.events))
+			current->rseq.event.events = 0;
 	}
 }
 
@@ -49,35 +50,30 @@ static __always_inline void rseq_exit_to_user_mode(void)
  */
 static inline void rseq_virt_userspace_exit(void)
 {
-	if (current->rseq_event_pending)
+	if (current->rseq.event.sched_switch)
 		set_tsk_thread_flag(current, TIF_NOTIFY_RESUME);
 }
 
+static inline void rseq_reset(struct task_struct *t)
+{
+	memset(&t->rseq, 0, sizeof(t->rseq));
+}
+
+static inline void rseq_execve(struct task_struct *t)
+{
+	rseq_reset(t);
+}
+
 /*
  * If parent process has a registered restartable sequences area, the
  * child inherits. Unregister rseq for a clone with CLONE_VM set.
  */
 static inline void rseq_fork(struct task_struct *t, u64 clone_flags)
 {
-	if (clone_flags & CLONE_VM) {
-		t->rseq = NULL;
-		t->rseq_len = 0;
-		t->rseq_sig = 0;
-		t->rseq_event_pending = false;
-	} else {
+	if (clone_flags & CLONE_VM)
+		rseq_reset(t);
+	else
 		t->rseq = current->rseq;
-		t->rseq_len = current->rseq_len;
-		t->rseq_sig = current->rseq_sig;
-		t->rseq_event_pending = current->rseq_event_pending;
-	}
-}
-
-static inline void rseq_execve(struct task_struct *t)
-{
-	t->rseq = NULL;
-	t->rseq_len = 0;
-	t->rseq_sig = 0;
-	t->rseq_event_pending = false;
 }
 
 #else /* CONFIG_RSEQ */
diff --git a/include/linux/rseq_types.h b/include/linux/rseq_types.h
new file mode 100644
index 000000000000..f7a60c8eddc9
--- /dev/null
+++ b/include/linux/rseq_types.h
@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_RSEQ_TYPES_H
+#define _LINUX_RSEQ_TYPES_H
+
+#include <linux/types.h>
+
+#ifdef CONFIG_RSEQ
+struct rseq;
+
+/**
+ * struct rseq_event - Storage for rseq related event management
+ * @all:		Compound to initialize and clear the data efficiently
+ * @events:		Compound to access events with a single load/store
+ * @sched_switch:	True if the task was scheduled out
+ * @has_rseq:		True if the task has a rseq pointer installed
+ */
+struct rseq_event {
+	union {
+		u32				all;
+		struct {
+			union {
+				u16		events;
+				struct {
+					u8	sched_switch;
+				};
+			};
+
+			u8			has_rseq;
+		};
+	};
+};
+
+/**
+ * struct rseq_data - Storage for all rseq related data
+ * @usrptr:	Pointer to the registered user space RSEQ memory
+ * @len:	Length of the RSEQ region
+ * @sig:	Signature of critial section abort IPs
+ * @event:	Storage for event management
+ */
+struct rseq_data {
+	struct rseq __user		*usrptr;
+	u32				len;
+	u32				sig;
+	struct rseq_event		event;
+};
+
+#else /* CONFIG_RSEQ */
+struct rseq_data { };
+#endif /* !CONFIG_RSEQ */
+
+#endif
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 6627c527c2c7..15627769409d 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -41,6 +41,7 @@
 #include <linux/task_io_accounting.h>
 #include <linux/posix-timers_types.h>
 #include <linux/restart_block.h>
+#include <linux/rseq_types.h>
 #include <uapi/linux/rseq.h>
 #include <linux/seqlock_types.h>
 #include <linux/kcsan.h>
@@ -1406,16 +1407,8 @@ struct task_struct {
 	unsigned long			numa_pages_migrated;
 #endif /* CONFIG_NUMA_BALANCING */
 
-#ifdef CONFIG_RSEQ
-	struct rseq __user		*rseq;
-	u32				rseq_len;
-	u32				rseq_sig;
-	/*
-	 * RmW on rseq_event_pending must be performed atomically
-	 * with respect to preemption.
-	 */
-	bool				rseq_event_pending;
-# ifdef CONFIG_DEBUG_RSEQ
+	struct rseq_data		rseq;
+#ifdef CONFIG_DEBUG_RSEQ
 	/*
 	 * This is a place holder to save a copy of the rseq fields for
 	 * validation of read-only fields. The struct rseq has a
@@ -1423,7 +1416,6 @@ struct task_struct {
 	 * directly. Reserve a size large enough for the known fields.
 	 */
 	char				rseq_fields[sizeof(struct rseq)];
-# endif
 #endif
 
 #ifdef CONFIG_SCHED_MM_CID