rseq/membarrier: Add MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ

This patchset is based on Google-internal RSEQ work done by Paul
Turner and Andrew Hunter.

When working with per-CPU RSEQ-based memory allocations, it is
sometimes important to make sure that a global memory location is no
longer accessed from RSEQ critical sections. For example, there can be
two per-CPU lists, one is "active" and accessed per-CPU, while another
one is inactive and worked on asynchronously "off CPU" (e.g.  garbage
collection is performed). Then at some point the two lists are
swapped, and a fast RCU-like mechanism is required to make sure that
the previously active list is no longer accessed.

This patch introduces such a mechanism: in short, membarrier() syscall
issues an IPI to a CPU, restarting a potentially active RSEQ critical
section on the CPU.

Signed-off-by: Peter Oskolkov <posk@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://lkml.kernel.org/r/20200923233618.2572849-1-posk@google.com

3 files changed, 30 insertions, 1 deletions

diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index f889e332912f..15bfb06f2884 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -348,10 +348,13 @@ enum {
 	MEMBARRIER_STATE_GLOBAL_EXPEDITED			= (1U << 3),
 	MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY	= (1U << 4),
 	MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE		= (1U << 5),
+	MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ_READY		= (1U << 6),
+	MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ			= (1U << 7),
 };
 
 enum {
 	MEMBARRIER_FLAG_SYNC_CORE	= (1U << 0),
+	MEMBARRIER_FLAG_RSEQ		= (1U << 1),
 };
 
 #ifdef CONFIG_ARCH_HAS_MEMBARRIER_CALLBACKS
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 75ac7f8ae93c..06db09875aa4 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -974,7 +974,7 @@ asmlinkage long sys_execveat(int dfd, const char __user *filename,
 			const char __user *const __user *argv,
 			const char __user *const __user *envp, int flags);
 asmlinkage long sys_userfaultfd(int flags);
-asmlinkage long sys_membarrier(int cmd, int flags);
+asmlinkage long sys_membarrier(int cmd, unsigned int flags, int cpu_id);
 asmlinkage long sys_mlock2(unsigned long start, size_t len, int flags);
 asmlinkage long sys_copy_file_range(int fd_in, loff_t __user *off_in,
 				    int fd_out, loff_t __user *off_out,
diff --git a/include/uapi/linux/membarrier.h b/include/uapi/linux/membarrier.h
index 5891d7614c8c..737605897f36 100644
--- a/include/uapi/linux/membarrier.h
+++ b/include/uapi/linux/membarrier.h
@@ -114,6 +114,26 @@
  *                          If this command is not implemented by an
  *                          architecture, -EINVAL is returned.
  *                          Returns 0 on success.
+ * @MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ:
+ *                          Ensure the caller thread, upon return from
+ *                          system call, that all its running thread
+ *                          siblings have any currently running rseq
+ *                          critical sections restarted if @flags
+ *                          parameter is 0; if @flags parameter is
+ *                          MEMBARRIER_CMD_FLAG_CPU,
+ *                          then this operation is performed only
+ *                          on CPU indicated by @cpu_id. If this command is
+ *                          not implemented by an architecture, -EINVAL
+ *                          is returned. A process needs to register its
+ *                          intent to use the private expedited rseq
+ *                          command prior to using it, otherwise
+ *                          this command returns -EPERM.
+ * @MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ:
+ *                          Register the process intent to use
+ *                          MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ.
+ *                          If this command is not implemented by an
+ *                          architecture, -EINVAL is returned.
+ *                          Returns 0 on success.
  * @MEMBARRIER_CMD_SHARED:
  *                          Alias to MEMBARRIER_CMD_GLOBAL. Provided for
  *                          header backward compatibility.
@@ -131,9 +151,15 @@ enum membarrier_cmd {
 	MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED		= (1 << 4),
 	MEMBARRIER_CMD_PRIVATE_EXPEDITED_SYNC_CORE		= (1 << 5),
 	MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_SYNC_CORE	= (1 << 6),
+	MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ			= (1 << 7),
+	MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ		= (1 << 8),
 
 	/* Alias for header backward compatibility. */
 	MEMBARRIER_CMD_SHARED			= MEMBARRIER_CMD_GLOBAL,
 };
 
+enum membarrier_cmd_flag {
+	MEMBARRIER_CMD_FLAG_CPU		= (1 << 0),
+};
+
 #endif /* _UAPI_LINUX_MEMBARRIER_H */