linux-kernel - [RFC PATCH v0.1 1/9] sched/umcg: add UMCG syscall stubs and CONFIG

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date:   Thu, 20 May 2021 11:36:06 -0700
From:   Peter Oskolkov <posk@...gle.com>
To:     Peter Zijlstra <peterz@...radead.org>,
        Ingo Molnar <mingo@...hat.com>,
        Thomas Gleixner <tglx@...utronix.de>,
        linux-kernel@...r.kernel.org, linux-api@...r.kernel.org
Cc:     Paul Turner <pjt@...gle.com>, Ben Segall <bsegall@...gle.com>,
        Peter Oskolkov <posk@...gle.com>,
        Peter Oskolkov <posk@...k.io>,
        Joel Fernandes <joel@...lfernandes.org>,
        Andrew Morton <akpm@...ux-foundation.org>,
        Andrei Vagin <avagin@...gle.com>,
        Jim Newsome <jnewsome@...project.org>
Subject: [RFC PATCH v0.1 1/9] sched/umcg: add UMCG syscall stubs and CONFIG_UMCG

User Managed Concurrency Groups is a fast context switching and
in-process userspace scheduling framework.

Two main use cases are security sandboxes and userspace scheduling.

Security sandboxes: fast X-process context switching will open up a
bunch of light-weight security tools, e.g. gVisor, or Tor Project's
Shadow simulator, to more use cases.

In-process userspace scheduling is used extensively at Google to provide
latency control and isolation guarantees for diverse workloads while
maintaining high CPU utilization.

Signed-off-by: Peter Oskolkov <posk@...gle.com>
---
 arch/x86/entry/syscalls/syscall_64.tbl | 11 +++++++++++
 include/uapi/asm-generic/unistd.h      | 25 ++++++++++++++++++++++++-
 init/Kconfig                           | 10 ++++++++++
 kernel/sys_ni.c                        | 13 +++++++++++++
 4 files changed, 58 insertions(+), 1 deletion(-)

diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index ecd551b08d05..2e984a77eb23 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -368,6 +368,17 @@
 444	common	landlock_create_ruleset	sys_landlock_create_ruleset
 445	common	landlock_add_rule	sys_landlock_add_rule
 446	common	landlock_restrict_self	sys_landlock_restrict_self
+447	common	umcg_api_version	sys_umcg_api_version
+448	common	umcg_register_task	sys_umcg_register_task
+449	common	umcg_unregister_task	sys_umcg_unregister_task
+450	common	umcg_wait		sys_umcg_wait
+451	common	umcg_wake		sys_umcg_wake
+452	common	umcg_swap		sys_umcg_swap
+453	common	umcg_create_group	sys_umcg_create_group
+454	common	umcg_destroy_group	sys_umcg_destroy_group
+455	common	umcg_poll_worker	sys_umcg_poll_worker
+456	common	umcg_run_worker		sys_umcg_run_worker
+457	common	umcg_preempt_worker	sys_umcg_preempt_worker
 
 #
 # Due to a historical design error, certain syscalls are numbered differently
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 6de5a7fc066b..cb8504e7ae07 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -873,8 +873,31 @@ __SYSCALL(__NR_landlock_add_rule, sys_landlock_add_rule)
 #define __NR_landlock_restrict_self 446
 __SYSCALL(__NR_landlock_restrict_self, sys_landlock_restrict_self)
 
+#define __NR_umcg_api_version 447
+__SYSCALL(__NR_umcg_api_version, sys_umcg_api_version)
+#define __NR_umcg_register_task 448
+__SYSCALL(__NR_umcg_register_task, sys_umcg_register_task)
+#define __NR_umcg_unregister_task 449
+__SYSCALL(__NR_umcg_unregister_task, sys_umcg_unregister_task)
+#define __NR_umcg_wait 450
+__SYSCALL(__NR_umcg_wait, sys_umcg_wait)
+#define __NR_umcg_wake 451
+__SYSCALL(__NR_umcg_wake, sys_umcg_wake)
+#define __NR_umcg_swap 452
+__SYSCALL(__NR_umcg_swap, sys_umcg_swap)
+#define __NR_umcg_create_group 453
+__SYSCALL(__NR_umcg_create_group, sys_umcg_create_group)
+#define __NR_umcg_destroy_group 454
+__SYSCALL(__NR_umcg_destroy_group, sys_umcg_destroy_group)
+#define __NR_umcg_poll_worker 455
+__SYSCALL(__NR_umcg_poll_worker, sys_umcg_poll_worker)
+#define __NR_umcg_run_worker 456
+__SYSCALL(__NR_umcg_run_worker, sys_umcg_run_worker)
+#define __NR_umcg_preempt_worker 457
+__SYSCALL(__NR_umcg_preempt_worker, sys_umcg_preempt_worker)
+
 #undef __NR_syscalls
-#define __NR_syscalls 447
+#define __NR_syscalls 458
 
 /*
  * 32 bit systems traditionally used different
diff --git a/init/Kconfig b/init/Kconfig
index 1ea12c64e4c9..bfac88dd5d73 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1661,6 +1661,16 @@ config MEMBARRIER
 
 	  If unsure, say Y.
 
+config UMCG
+	bool "Enable User Managed Concurrency Groups API"
+	default n
+	help
+	  Enable UMCG core wait/wake/swap operations as well as UMCG
+	  group/server/worker API. The core API is useful for fast IPC
+	  and context switching, while the group/server/worker API, together
+	  with the core API, form the basis for an in-process M:N userspace
+	  scheduling framework implemented in lib/umcg.
+
 config KALLSYMS
 	bool "Load all symbols for debugging/ksymoops" if EXPERT
 	default y
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 0ea8128468c3..fea55aa0222a 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -272,6 +272,19 @@ COND_SYSCALL(landlock_create_ruleset);
 COND_SYSCALL(landlock_add_rule);
 COND_SYSCALL(landlock_restrict_self);
 
+/* kernel/sched/umcg.c */
+COND_SYSCALL(umcg_api_version);
+COND_SYSCALL(umcg_register_task);
+COND_SYSCALL(umcg_unregister_task);
+COND_SYSCALL(umcg_wait);
+COND_SYSCALL(umcg_wake);
+COND_SYSCALL(umcg_swap);
+COND_SYSCALL(umcg_create_group);
+COND_SYSCALL(umcg_destroy_group);
+COND_SYSCALL(umcg_poll_worker);
+COND_SYSCALL(umcg_run_worker);
+COND_SYSCALL(umcg_preempt_worker);
+
 /* arch/example/kernel/sys_example.c */
 
 /* mm/fadvise.c */
-- 
2.31.1.818.g46aad6cb9e-goog