[RFC PATCH v2 2/4] selftests/rseq: Add sched_state rseq field and getter

[Mathieu Desnoyers]

Extend struct rseq in the rseq selftests to include the sched_state
field. Implement a getter function for this field.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@xxxxxxxxxxxx>
---
 tools/testing/selftests/rseq/rseq-abi.h | 42 +++++++++++++++++++++++++
 tools/testing/selftests/rseq/rseq.c     | 13 ++++++++
 tools/testing/selftests/rseq/rseq.h     |  5 +++
 3 files changed, 60 insertions(+)

diff --git a/tools/testing/selftests/rseq/rseq-abi.h b/tools/testing/selftests/rseq/rseq-abi.h
index fb4ec8a75dd4..1092d6750386 100644
--- a/tools/testing/selftests/rseq/rseq-abi.h
+++ b/tools/testing/selftests/rseq/rseq-abi.h
@@ -37,6 +37,13 @@ enum rseq_abi_cs_flags {
 		(1U << RSEQ_ABI_CS_FLAG_NO_RESTART_ON_MIGRATE_BIT),
 };
 
+enum rseq_abi_sched_state_flags {
+	/*
+	 * Task is currently running on a CPU if bit is set.
+	 */
+	RSEQ_ABI_SCHED_STATE_FLAG_ON_CPU		= (1U << 0),
+};
+
 /*
  * struct rseq_abi_cs is aligned on 4 * 8 bytes to ensure it is always
  * contained within a single cache-line. It is usually declared as
@@ -53,6 +60,32 @@ struct rseq_abi_cs {
 	__u64 abort_ip;
 } __attribute__((aligned(4 * sizeof(__u64))));
 
+/*
+ * rseq_abi_sched_state should be aligned on the cache line size.
+ */
+struct rseq_abi_sched_state {
+	/*
+	 * Version of this structure. Populated by the kernel, read by
+	 * user-space.
+	 */
+	__u32 version;
+	/*
+	 * The state is updated by the kernel. Read by user-space with
+	 * single-copy atomicity semantics. This field can be read by any
+	 * userspace thread. Aligned on 32-bit, and ideally on cache line size.
+	 * Contains a bitmask of enum rseq_abi_sched_state_flags. This field is
+	 * provided as a hint by the scheduler, and requires that the page
+	 * holding this state is faulted-in for the state update to be
+	 * performed by the scheduler.
+	 */
+	__u32 state;
+	/*
+	 * Thread ID associated with the thread registering this structure.
+	 * Initialized by user-space before registration.
+	 */
+	__u32 tid;
+};
+
 /*
  * struct rseq_abi is aligned on 4 * 8 bytes to ensure it is always
  * contained within a single cache-line.
@@ -164,6 +197,15 @@ struct rseq_abi {
 	 */
 	__u32 mm_cid;
 
+	__u32 padding1;
+
+	/*
+	 * Restartable sequences sched_state_ptr field. Initialized by
+	 * userspace to the address at which the struct rseq_abi_sched_state is
+	 * located. Read by the kernel on rseq registration.
+	 */
+	__u64 sched_state_ptr;
+
 	/*
 	 * Flexible array member at end of structure, after last feature field.
 	 */
diff --git a/tools/testing/selftests/rseq/rseq.c b/tools/testing/selftests/rseq/rseq.c
index 4e4aa006004c..76925b116054 100644
--- a/tools/testing/selftests/rseq/rseq.c
+++ b/tools/testing/selftests/rseq/rseq.c
@@ -62,17 +62,28 @@ static int rseq_reg_success;	/* At least one rseq registration has succeded. */
 /* Allocate a large area for the TLS. */
 #define RSEQ_THREAD_AREA_ALLOC_SIZE	1024
 
+/* Approximation of cacheline size. */
+#define CACHELINE_SIZE			128
+
 /* Original struct rseq feature size is 20 bytes. */
 #define ORIG_RSEQ_FEATURE_SIZE		20
 
 /* Original struct rseq allocation size is 32 bytes. */
 #define ORIG_RSEQ_ALLOC_SIZE		32
 
+static
+__thread struct rseq_abi_sched_state __rseq_abi_sched_state __attribute__((tls_model("initial-exec"), aligned(CACHELINE_SIZE)));
+
 static
 __thread struct rseq_abi __rseq_abi __attribute__((tls_model("initial-exec"), aligned(RSEQ_THREAD_AREA_ALLOC_SIZE))) = {
 	.cpu_id = RSEQ_ABI_CPU_ID_UNINITIALIZED,
 };
 
+static pid_t rseq_gettid(void)
+{
+	return syscall(__NR_gettid);
+}
+
 static int sys_rseq(struct rseq_abi *rseq_abi, uint32_t rseq_len,
 		    int flags, uint32_t sig)
 {
@@ -109,6 +120,8 @@ int rseq_register_current_thread(void)
 		/* Treat libc's ownership as a successful registration. */
 		return 0;
 	}
+	__rseq_abi_sched_state.tid = rseq_gettid();
+	__rseq_abi.sched_state_ptr = (uint64_t)(unsigned long)&__rseq_abi_sched_state;
 	rc = sys_rseq(&__rseq_abi, rseq_size, 0, RSEQ_SIG);
 	if (rc) {
 		if (RSEQ_READ_ONCE(rseq_reg_success)) {
diff --git a/tools/testing/selftests/rseq/rseq.h b/tools/testing/selftests/rseq/rseq.h
index d7364ea4d201..4c14ef3f581f 100644
--- a/tools/testing/selftests/rseq/rseq.h
+++ b/tools/testing/selftests/rseq/rseq.h
@@ -236,6 +236,11 @@ static inline void rseq_prepare_unload(void)
 	rseq_clear_rseq_cs();
 }
 
+static inline struct rseq_abi_sched_state *rseq_get_sched_state(struct rseq_abi *rseq)
+{
+	return (struct rseq_abi_sched_state *)(unsigned long)rseq->sched_state_ptr;
+}
+
 static inline __attribute__((always_inline))
 int rseq_cmpeqv_storev(enum rseq_mo rseq_mo, enum rseq_percpu_mode percpu_mode,
 		       intptr_t *v, intptr_t expect,
-- 
2.25.1