prctl: Introduce PR_{SET,GET}_MEM_MODEL

On some architectures, it is possible to query and/or change the CPU
memory model. This allows userspace to switch to a stricter memory model
for performance reasons, such as when emulating code for another
architecture where that model is the default.

Introduce two prctls to allow userspace to query and set the memory
model for a thread. Two models are initially defined:

- PR_SET_MEM_MODEL_DEFAULT requests the default memory model for the
  architecture.
- PR_SET_MEM_MODEL_TSO requests the x86 TSO memory model.

PR_SET_MEM_MODEL is allowed to set a stricter memory model than
requested if available, in which case it will return successfully. If
the requested memory model cannot be fulfilled, it will return an error.
The memory model that was actually set can be queried by a subsequent
call to PR_GET_MEM_MODEL.

Examples:
- On a CPU with not support for a memory model at least as strong as
  TSO, PR_SET_MEM_MODEL(PR_SET_MEM_MODEL_TSO) fails.
- On a CPU with runtime-configurable TSO support, PR_SET_MEM_MODEL can
  toggle the memory model between DEFAULT and TSO at will.
- On a CPU where the only memory model is at least as strict as TSO,
  PR_GET_MEM_MODEL will return PR_SET_MEM_MODEL_DEFAULT, and
  PR_SET_MEM_MODEL(PR_SET_MEM_MODEL_TSO) will return success but leave
  the memory model at PR_SET_MEM_MODEL_DEFAULT. This implies that the
  default is in fact at least as strict as TSO.

Signed-off-by: Hector Martin <marcan@marcan.st>
Reviewed-by: Neal Gompa <neal@gompa.dev>

Author: marcan

include/linux/memory_ordering_model.h

@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_MEMORY_ORDERING_MODEL_H
+#define __ASM_MEMORY_ORDERING_MODEL_H
+
+/* Arch hooks to implement the PR_{GET_SET}_MEM_MODEL prctls */
+
+struct task_struct;
+int arch_prctl_mem_model_get(struct task_struct *t);
+int arch_prctl_mem_model_set(struct task_struct *t, unsigned long val);
+
+#endif

include/uapi/linux/prctl.h

@@ -328,4 +328,9 @@ struct prctl_mm_map {
 # define PR_PPC_DEXCR_CTRL_CLEAR_ONEXEC	0x10 /* Clear the aspect on exec */
 # define PR_PPC_DEXCR_CTRL_MASK		0x1f
 
-#endif /* _LINUX_PRCTL_H */
+#define PR_GET_MEM_MODEL	0x6d4d444c
+#define PR_SET_MEM_MODEL	0x4d4d444c
+# define PR_SET_MEM_MODEL_DEFAULT	0
+# define PR_SET_MEM_MODEL_TSO		1
+
+endif /* _LINUX_PRCTL_H */

kernel/sys.c

@@ -45,6 +45,7 @@
 #include <linux/version.h>
 #include <linux/ctype.h>
 #include <linux/syscall_user_dispatch.h>
+#include <linux/memory_ordering_model.h>
 
 #include <linux/compat.h>
 #include <linux/syscalls.h>
@@ -2454,6 +2455,16 @@ static int prctl_get_auxv(void __user *addr, unsigned long len)
 	return sizeof(mm->saved_auxv);
 }
 
+int __weak arch_prctl_mem_model_get(struct task_struct *t)
+{
+	return -EINVAL;
+}
+
+int __weak arch_prctl_mem_model_set(struct task_struct *t, unsigned long val)
+{
+	return -EINVAL;
+}
+
 SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 		unsigned long, arg4, unsigned long, arg5)
 {
@@ -2782,6 +2793,16 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 	case PR_RISCV_SET_ICACHE_FLUSH_CTX:
 		error = RISCV_SET_ICACHE_FLUSH_CTX(arg2, arg3);
 		break;
+	case PR_GET_MEM_MODEL:
+		if (arg2 || arg3 || arg4 || arg5)
+			return -EINVAL;
+		error = arch_prctl_mem_model_get(me);
+		break;
+	case PR_SET_MEM_MODEL:
+		if (arg3 || arg4 || arg5)
+			return -EINVAL;
+		error = arch_prctl_mem_model_set(me, arg2);
+		break;
 	default:
 		error = -EINVAL;
 		break;