Skip to contentSkip to conversation

rseq/membarrier: add MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ

PATCH Superseded Peter Oskolkov 3 participants 5 messages Aug 31, 2020 – Sep 15, 2020

Subsystems (5)

v6 of 8 Superseded Latest is v8 →

lore
Share & tools
lore
#0 lore raw

PATCH v6 1/2 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.

v1->v2:
- removed the ability to IPI all CPUs in a single sycall;
- use task->mm rather than task->group_leader to identify tasks belonging to the same process.
v2->v3:
- re-added the ability to IPI all CPUs in a single syscall;
- integrated with membarrier_private_expedited() to make sure only CPUs running tasks with the same mm as the current task are interrupted;
- also added MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ;
- flags in membarrier_private_expedited are never actually bit flags but always distinct values (i.e. never two flags are combined), so I modified bit testing to full equation comparison for simplicity (otherwise the code needs to work when several bits are set, for example).
v3->v4:
- added the third parameter to membarrier syscall: @cpu_id:
if @flags == MEMBARRIER_CMD_FLAG_CPU, then @cpu_id indicates the cpu on which RSEQ CS should be restarted.
v4->v5:
- added @cpu_id parameter to sys_membarrier in syscalls.h.
v5->v6:
- made membarrier_private_expedited more efficient in a

    single-cpu case;

- a couple of other minor refactorings.

The second patch in the patchset adds a selftest of this feature.

---
 include/linux/sched/mm.h        |   3 +
 include/linux/syscalls.h        |   2 +-
 include/uapi/linux/membarrier.h |  29 +++++++
 kernel/sched/membarrier.c       | 140 +++++++++++++++++++++++++-------
 4 files changed, 143 insertions(+), 31 deletions(-)
include/linux/sched/mm.h +3 -0
index f889e332912f..15bfb06f2884 100644
@@ -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
include/linux/syscalls.h +1 -1
index 75ac7f8ae93c..466c993e52bf 100644
@@ -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, 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,
include/uapi/linux/membarrier.h +29 -0
index 5891d7614c8c..98c2b0e7c0d8 100644
@@ -114,6 +114,29 @@
  *                          If this command is not implemented by an
  *                          architecture, -EINVAL is returned.
  *                          Returns 0 on success.
+ * @MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ:
+ *                          In addition to provide memory ordering
+ *                          guarantees described in
+ *                          MEMBARRIER_CMD_PRIVATE_EXPEDITED_SYNC_CORE,
+ *                          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 +154,15 @@ 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 */
kernel/sched/membarrier.c +110 -30

224 lines not on this page · raw message

Signature · 1 line
2.28.0.402.g5ffc5be6b7-goog
#1 lore raw

PATCH v6 2/2 rseq/selftests: test MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ

Based on Google-internal RSEQ work done by
Paul Turner and Andrew Hunter.

This patch adds a selftest for MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ. The test quite often fails without the previous patch in this patchset, but consistently passes with it.

v3: added rseq_offset_deref_addv() to x86_64 to make the test
more explicit; on other architectures I kept using existing rseq_cmpeqv_cmpeqv_storev() as I have no easy way to test there. Added a comment explaining why the test works this way.
v4: skipped the test if rseq_offset_deref_addv() is not present
(that is, on all architectures other than x86_64).

---
 .../selftests/rseq/basic_percpu_ops_test.c    | 187 ++++++++++++++++++
 tools/testing/selftests/rseq/rseq-x86.h       |  57 ++++++
 2 files changed, 244 insertions(+)
tools/testing/selftests/rseq/basic_percpu_ops_test.c +187 -0
index eb3f6db36d36..e6e10ba4b9ed 100644
@@ -3,16 +3,24 @@
 #include <assert.h>
 #include <pthread.h>
 #include <sched.h>
+#include <stdatomic.h>
 #include <stdint.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
 #include <stddef.h>
+#include <syscall.h>
+#include <unistd.h>
 
 #include "rseq.h"
 
 #define ARRAY_SIZE(arr)	(sizeof(arr) / sizeof((arr)[0]))
 
+/* The local <linux/membarrier.h> may not contain the commands below. */
+#define MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ	(1<<7)
+#define MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ	(1<<8)
+#define MEMBARRIER_CMD_FLAG_CPU		(1<<0)
+
 struct percpu_lock_entry {
 	intptr_t v;
 } __attribute__((aligned(128)));
@@ -289,6 +297,183 @@ void test_percpu_list(void)
 	assert(sum == expected_sum);
 }
 
+struct test_membarrier_thread_args {
+	int stop;
+	intptr_t percpu_list_ptr;
+};
+
+/* Worker threads modify data in their "active" percpu lists. */
+void *test_membarrier_worker_thread(void *arg)
+{
+	struct test_membarrier_thread_args *args =
+		(struct test_membarrier_thread_args *)arg;
+	const int iters = 10 * 1000 * 1000;
+	int i;
+
+	if (rseq_register_current_thread()) {
+		fprintf(stderr, "Error: rseq_register_current_thread(...) failed(%d): %s\n",
+			errno, strerror(errno));
+		abort();
+	}
+
+	/* Wait for initialization. */
+	while (!atomic_load(&args->percpu_list_ptr)) {}
+
+	for (i = 0; i < iters; ++i) {
+		int ret;
+
+		do {
+			int cpu = rseq_cpu_start();
+
+			ret = rseq_offset_deref_addv(&args->percpu_list_ptr,
+							128 * cpu, 1, cpu);
+		} while (rseq_unlikely(ret));
+	}
+
+	if (rseq_unregister_current_thread()) {
+		fprintf(stderr, "Error: rseq_unregister_current_thread(...) failed(%d): %s\n",
+			errno, strerror(errno));
+		abort();
+	}
+	return NULL;
+}
+
+void test_membarrier_init_percpu_list(struct percpu_list *list)
+{
+	int i;
+
+	memset(list, 0, sizeof(*list));
+	for (i = 0; i < CPU_SETSIZE; i++) {
+		struct percpu_list_node *node;
+
+		node = malloc(sizeof(*node));
+		assert(node);
+		node->data = 0;
+		node->next = NULL;
+		list->c[i].head = node;
+	}
+}
+
+void test_membarrier_free_percpu_list(struct percpu_list *list)
+{
+	int i;
+
+	for (i = 0; i < CPU_SETSIZE; i++)
+		free(list->c[i].head);
+}
+
+static int sys_membarrier(int cmd, int flags, int cpu_id)
+{
+	return syscall(__NR_membarrier, cmd, flags, cpu_id);
+}
+
+/*
+ * The manager thread swaps per-cpu lists that worker threads see,
+ * and validates that there are no unexpected modifications.
+ */
+void *test_membarrier_manager_thread(void *arg)
+{
+	struct test_membarrier_thread_args *args =
+		(struct test_membarrier_thread_args *)arg;
+	struct percpu_list list_a, list_b;
+	intptr_t expect_a = 0, expect_b = 0;
+	int cpu_a = 0, cpu_b = 0;
+
+	if (rseq_register_current_thread()) {
+		fprintf(stderr, "Error: rseq_register_current_thread(...) failed(%d): %s\n",
+			errno, strerror(errno));
+		abort();
+	}
+
+	/* Init lists. */
+	test_membarrier_init_percpu_list(&list_a);
+	test_membarrier_init_percpu_list(&list_b);
+
+	atomic_store(&args->percpu_list_ptr, (intptr_t)&list_a);
+
+	while (!atomic_load(&args->stop)) {
+		/* list_a is "active". */
+		cpu_a = rand() % CPU_SETSIZE;
+		/*
+		 * As list_b is "inactive", we should never see changes
+		 * to list_b.
+		 */
+		if (expect_b != atomic_load(&list_b.c[cpu_b].head->data)) {
+			fprintf(stderr, "Membarrier test failed\n");
+			abort();
+		}
+
+		/* Make list_b "active". */
+		atomic_store(&args->percpu_list_ptr, (intptr_t)&list_b);
+		sys_membarrier(MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ,
+			       MEMBARRIER_CMD_FLAG_CPU, cpu_a);
+		/*
+		 * Cpu A should now only modify list_b, so we values
+		 * in list_a should be stable.
+		 */
+		expect_a = atomic_load(&list_a.c[cpu_a].head->data);
+
+		cpu_b = rand() % CPU_SETSIZE;
+		/*
+		 * As list_a is "inactive", we should never see changes
+		 * to list_a.
+		 */
+		if (expect_a != atomic_load(&list_a.c[cpu_a].head->data)) {
+			fprintf(stderr, "Membarrier test failed\n");
+			abort();
+		}
+
+		/* Make list_a "active". */
+		atomic_store(&args->percpu_list_ptr, (intptr_t)&list_a);
+		sys_membarrier(MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ,
+			       MEMBARRIER_CMD_FLAG_CPU, cpu_b);
+		/* Remember a value from list_b. */
+		expect_b = atomic_load(&list_b.c[cpu_b].head->data);
+	}
+
+	test_membarrier_free_percpu_list(&list_a);
+	test_membarrier_free_percpu_list(&list_b);
+
+	if (rseq_unregister_current_thread()) {
+		fprintf(stderr, "Error: rseq_unregister_current_thread(...) failed(%d): %s\n",
+			errno, strerror(errno));
+		abort();
+	}
+	return NULL;
+}
+
+/* Test MEMBARRIER_CMD_PRIVATE_RESTART_RSEQ_ON_CPU membarrier command. */
+void test_membarrier(void)
+{
+#ifndef RSEQ_ARCH_HAS_OFFSET_DEREF_ADDV
+	fprintf(stderr, "rseq_offset_deref_addv is not implemented on this architecture. "
+			"Skipping membarrier test.\n");
+	return;
+#else
+	struct test_membarrier_thread_args thread_args;
+	pthread_t worker_threads[CPU_SETSIZE];
+	pthread_t manager_thread;
+	int i;
+
+	sys_membarrier(MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ, 0, 0);
+
+	thread_args.stop = 0;
+	thread_args.percpu_list_ptr = 0;
+	pthread_create(&manager_thread, NULL,
+		       test_membarrier_manager_thread, &thread_args);
+
+	for (i = 0; i < CPU_SETSIZE; i++)
+		pthread_create(&worker_threads[i], NULL,
+		       test_membarrier_worker_thread, &thread_args);
+
+	for (i = 0; i < CPU_SETSIZE; i++)
+		pthread_join(worker_threads[i], NULL);
+
+	atomic_store(&thread_args.stop, 1);
+	pthread_join(manager_thread, NULL);
+#endif
+}
+
 int main(int argc, char **argv)
 {
 	if (rseq_register_current_thread()) {
@@ -300,6 +485,8 @@ int main(int argc, char **argv)
 	test_percpu_spinlock();
 	printf("percpu_list\n");
 	test_percpu_list();
+	printf("membarrier\n");
+	test_membarrier();
 	if (rseq_unregister_current_thread()) {
 		fprintf(stderr, "Error: rseq_unregister_current_thread(...) failed(%d): %s\n",
 			errno, strerror(errno));
tools/testing/selftests/rseq/rseq-x86.h +57 -0

63 lines not on this page · raw message

Signature · 1 line
2.28.0.402.g5ffc5be6b7-goog
#2 lore raw
In reply to Peter Oskolkov

Any comments here? Should I change anything?

Thanks,
Peter

Quoted 377 lines · Peter Oskolkov

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.

v1->v2:
- removed the ability to IPI all CPUs in a single sycall;
- use task->mm rather than task->group_leader to identify tasks belonging to the same process.
v2->v3:
- re-added the ability to IPI all CPUs in a single syscall;
- integrated with membarrier_private_expedited() to make sure only CPUs running tasks with the same mm as the current task are interrupted;
- also added MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ;
- flags in membarrier_private_expedited are never actually bit flags but always distinct values (i.e. never two flags are combined), so I modified bit testing to full equation comparison for simplicity (otherwise the code needs to work when several bits are set, for example).
v3->v4:
- added the third parameter to membarrier syscall: @cpu_id:
if @flags == MEMBARRIER_CMD_FLAG_CPU, then @cpu_id indicates the cpu on which RSEQ CS should be restarted.
v4->v5:
- added @cpu_id parameter to sys_membarrier in syscalls.h.
v5->v6:
- made membarrier_private_expedited more efficient in a

    single-cpu case;

- a couple of other minor refactorings.

The second patch in the patchset adds a selftest of this feature.

---
 include/linux/sched/mm.h        |   3 +
 include/linux/syscalls.h        |   2 +-
 include/uapi/linux/membarrier.h |  29 +++++++
 kernel/sched/membarrier.c       | 140 +++++++++++++++++++++++++-------
 4 files changed, 143 insertions(+), 31 deletions(-)
include/linux/sched/mm.h +3 -0
index f889e332912f..15bfb06f2884 100644
@@ -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
include/linux/syscalls.h +1 -1
index 75ac7f8ae93c..466c993e52bf 100644
@@ -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, 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,
include/uapi/linux/membarrier.h +29 -0
index 5891d7614c8c..98c2b0e7c0d8 100644
@@ -114,6 +114,29 @@
  *                          If this command is not implemented by an
  *                          architecture, -EINVAL is returned.
  *                          Returns 0 on success.
+ * @MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ:
+ *                          In addition to provide memory ordering
+ *                          guarantees described in
+ *                          MEMBARRIER_CMD_PRIVATE_EXPEDITED_SYNC_CORE,
+ *                          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 +154,15 @@ 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 */
kernel/sched/membarrier.c +110 -31
index 168479a7d61b..e32e9476ccf3 100644
@@ -18,6 +18,14 @@
 #define MEMBARRIER_PRIVATE_EXPEDITED_SYNC_CORE_BITMASK 0
 #endif
 
+#ifdef CONFIG_RSEQ
+#define MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ_BITMASK          \
+       (MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ                  \
+       | MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ_BITMASK)
+#else
+#define MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ_BITMASK  0
+#endif
+
 #define MEMBARRIER_CMD_BITMASK                                         \
        (MEMBARRIER_CMD_GLOBAL | MEMBARRIER_CMD_GLOBAL_EXPEDITED        \
        | MEMBARRIER_CMD_REGISTER_GLOBAL_EXPEDITED                      \
@@ -30,6 +38,13 @@ static void ipi_mb(void *info)
        smp_mb();       /* IPIs should be serializing but paranoid. */
 }
 
+#ifdef CONFIG_RSEQ
+static void ipi_rseq(void *info)
+{
+       rseq_preempt(current);
+}
+#endif
+
 static void ipi_sync_rq_state(void *info)
 {
        struct mm_struct *mm = (struct mm_struct *) info;
@@ -129,19 +144,29 @@ static int membarrier_global_expedited(void)
        return 0;
 }
 
-static int membarrier_private_expedited(int flags)
+static int membarrier_private_expedited(int flags, int cpu_id)
 {
-       int cpu;
        cpumask_var_t tmpmask;
        struct mm_struct *mm = current->mm;
+       smp_call_func_t ipi_func = ipi_mb;
 
-       if (flags & MEMBARRIER_FLAG_SYNC_CORE) {
+       if (flags == MEMBARRIER_FLAG_SYNC_CORE) {
                if (!IS_ENABLED(CONFIG_ARCH_HAS_MEMBARRIER_SYNC_CORE))
                        return -EINVAL;
                if (!(atomic_read(&mm->membarrier_state) &
                      MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY))
                        return -EPERM;
+       } else if (flags == MEMBARRIER_FLAG_RSEQ) {
+#ifdef CONFIG_RSEQ
+               if (!(atomic_read(&mm->membarrier_state) &
+                     MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ_READY))
+                       return -EPERM;
+               ipi_func = ipi_rseq;
+#else
+               return -EINVAL;
+#endif
        } else {
+               BUG_ON(flags != 0);
                if (!(atomic_read(&mm->membarrier_state) &
                      MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY))
                        return -EPERM;
@@ -156,35 +181,59 @@ static int membarrier_private_expedited(int flags)
         */
        smp_mb();       /* system call entry is not a mb. */
 
-       if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL))
+       if (cpu_id < 0 && !zalloc_cpumask_var(&tmpmask, GFP_KERNEL))
                return -ENOMEM;
 
        cpus_read_lock();
-       rcu_read_lock();
-       for_each_online_cpu(cpu) {
+
+       if (cpu_id >= 0) {
                struct task_struct *p;
 
-               /*
-                * Skipping the current CPU is OK even through we can be
-                * migrated at any point. The current CPU, at the point
-                * where we read raw_smp_processor_id(), is ensured to
-                * be in program order with respect to the caller
-                * thread. Therefore, we can skip this CPU from the
-                * iteration.
-                */
-               if (cpu == raw_smp_processor_id())
-                       continue;
-               p = rcu_dereference(cpu_rq(cpu)->curr);
-               if (p && p->mm == mm)
-                       __cpumask_set_cpu(cpu, tmpmask);
+               if (cpu_id >= nr_cpu_ids || !cpu_online(cpu_id))
+                       goto out;
+               if (cpu_id == raw_smp_processor_id())
+                       goto out;
+               rcu_read_lock();
+               p = rcu_dereference(cpu_rq(cpu_id)->curr);
+               if (!p || p->mm != mm) {
+                       rcu_read_unlock();
+                       goto out;
+               }
+               rcu_read_unlock();
+       } else {
+               int cpu;
+
+               rcu_read_lock();
+               for_each_online_cpu(cpu) {
+                       struct task_struct *p;
+
+                       /*
+                        * Skipping the current CPU is OK even through we can be
+                        * migrated at any point. The current CPU, at the point
+                        * where we read raw_smp_processor_id(), is ensured to
+                        * be in program order with respect to the caller
+                        * thread. Therefore, we can skip this CPU from the
+                        * iteration.
+                        */
+                       if (cpu == raw_smp_processor_id())
+                               continue;
+                       p = rcu_dereference(cpu_rq(cpu)->curr);
+                       if (p && p->mm == mm)
+                               __cpumask_set_cpu(cpu, tmpmask);
+               }
+               rcu_read_unlock();
        }
-       rcu_read_unlock();
 
        preempt_disable();
-       smp_call_function_many(tmpmask, ipi_mb, NULL, 1);
+       if (cpu_id >= 0)
+               smp_call_function_single(cpu_id, ipi_func, NULL, 1);
+       else
+               smp_call_function_many(tmpmask, ipi_func, NULL, 1);
        preempt_enable();
 
-       free_cpumask_var(tmpmask);
+out:
+       if (cpu_id < 0)
+               free_cpumask_var(tmpmask);
        cpus_read_unlock();
 
        /*
@@ -283,11 +332,18 @@ static int membarrier_register_private_expedited(int flags)
            set_state = MEMBARRIER_STATE_PRIVATE_EXPEDITED,
            ret;
 
-       if (flags & MEMBARRIER_FLAG_SYNC_CORE) {
+       if (flags == MEMBARRIER_FLAG_SYNC_CORE) {
                if (!IS_ENABLED(CONFIG_ARCH_HAS_MEMBARRIER_SYNC_CORE))
                        return -EINVAL;
                ready_state =
                        MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY;
+       } else if (flags == MEMBARRIER_FLAG_RSEQ) {
+               if (!IS_ENABLED(CONFIG_RSEQ))
+                       return -EINVAL;
+               ready_state =
+                       MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ_READY;
+       } else {
+               BUG_ON(flags != 0);
        }
 
        /*
@@ -299,6 +355,8 @@ static int membarrier_register_private_expedited(int flags)
                return 0;
        if (flags & MEMBARRIER_FLAG_SYNC_CORE)
                set_state |= MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE;
+       if (flags & MEMBARRIER_FLAG_RSEQ)
+               set_state |= MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ;
        atomic_or(set_state, &mm->membarrier_state);
        ret = sync_runqueues_membarrier_state(mm);
        if (ret)
@@ -310,8 +368,15 @@ static int membarrier_register_private_expedited(int flags)
 
 /**
  * sys_membarrier - issue memory barriers on a set of threads
- * @cmd:   Takes command values defined in enum membarrier_cmd.
- * @flags: Currently needs to be 0. For future extensions.
+ * @cmd:    Takes command values defined in enum membarrier_cmd.
+ * @flags:  Currently needs to be 0 for all commands other than
+ *          MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ: in the latter
+ *          case it can be MEMBARRIER_CMD_FLAG_CPU, indicating that @cpu_id
+ *          contains the CPU on which to interrupt (= restart)
+ *          the RSEQ critical section.
+ * @cpu_id: if @flags == MEMBARRIER_CMD_FLAG_CPU, indicates the cpu on which
+ *          RSEQ CS should be interrupted (@cmd must be
+ *          MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ).
  *
  * If this system call is not implemented, -ENOSYS is returned. If the
  * command specified does not exist, not available on the running
@@ -337,10 +402,21 @@ static int membarrier_register_private_expedited(int flags)
  *        smp_mb()           X           O            O
  *        sys_membarrier()   O           O            O
  */
-SYSCALL_DEFINE2(membarrier, int, cmd, int, flags)
+SYSCALL_DEFINE3(membarrier, int, cmd, int, flags, int, cpu_id)
 {
-       if (unlikely(flags))
-               return -EINVAL;
+       switch (cmd) {
+       case MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ:
+               if (unlikely(flags && flags != MEMBARRIER_CMD_FLAG_CPU))
+                       return -EINVAL;
+               break;
+       default:
+               if (unlikely(flags))
+                       return -EINVAL;
+       }
+
+       if (!(flags & MEMBARRIER_CMD_FLAG_CPU))
+               cpu_id = -1;
+
        switch (cmd) {
        case MEMBARRIER_CMD_QUERY:
        {
@@ -362,13 +438,17 @@ SYSCALL_DEFINE2(membarrier, int, cmd, int, flags)
        case MEMBARRIER_CMD_REGISTER_GLOBAL_EXPEDITED:
                return membarrier_register_global_expedited();
        case MEMBARRIER_CMD_PRIVATE_EXPEDITED:
-               return membarrier_private_expedited(0);
+               return membarrier_private_expedited(0, cpu_id);
        case MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED:
                return membarrier_register_private_expedited(0);
        case MEMBARRIER_CMD_PRIVATE_EXPEDITED_SYNC_CORE:
-               return membarrier_private_expedited(MEMBARRIER_FLAG_SYNC_CORE);
+               return membarrier_private_expedited(MEMBARRIER_FLAG_SYNC_CORE, cpu_id);
        case MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_SYNC_CORE:
                return membarrier_register_private_expedited(MEMBARRIER_FLAG_SYNC_CORE);
+       case MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ:
+               return membarrier_private_expedited(MEMBARRIER_FLAG_RSEQ, cpu_id);
+       case MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ:
+               return membarrier_register_private_expedited(MEMBARRIER_FLAG_RSEQ);
        default:
                return -EINVAL;
        }
--

2.28.0.402.g5ffc5be6b7-goog

#3 lore raw
Quoted 1 line · ----- On Sep 15, 2020, at 2:12 AM, Peter Oskolkov [email protected] wrote:

Any comments here? Should I change anything?

See below,

Quoted 4 lines
Quoted 4 lines
include/uapi/linux/membarrier.h +0 -0
index 5891d7614c8c..98c2b0e7c0d8 100644
Quoted 8 lines

include/uapi/linux/membarrier.h line 120

Quoted 8 lines
include/uapi/linux/membarrier.h +4 -0
@@ -114,6 +114,29 @@
  *                          If this command is not implemented by an
  *                          architecture, -EINVAL is returned.
  *                          Returns 0 on success.
+ * @MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ:
+ *                          In addition to provide memory ordering
+ *                          guarantees described in
+ *                          MEMBARRIER_CMD_PRIVATE_EXPEDITED_SYNC_CORE,

^ is the above still true ? I see from the code that the rseq membarrier only issues rseq_preempt, not any (documented) explicit core serialization nor memory barrier.

Quoted 83 lines
Quoted 83 lines
include/uapi/linux/membarrier.h +25 -0
+ *                          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 +154,15 @@ 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 */
kernel/sched/membarrier.c +17 -2
index 168479a7d61b..e32e9476ccf3 100644
@@ -18,6 +18,14 @@
 #define MEMBARRIER_PRIVATE_EXPEDITED_SYNC_CORE_BITMASK 0
 #endif
 
+#ifdef CONFIG_RSEQ
+#define MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ_BITMASK          \
+       (MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ                  \
+       | MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ_BITMASK)
+#else
+#define MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ_BITMASK  0
+#endif
+
 #define MEMBARRIER_CMD_BITMASK                                         \
        (MEMBARRIER_CMD_GLOBAL | MEMBARRIER_CMD_GLOBAL_EXPEDITED        \
        | MEMBARRIER_CMD_REGISTER_GLOBAL_EXPEDITED                      \
@@ -30,6 +38,13 @@ static void ipi_mb(void *info)
        smp_mb();       /* IPIs should be serializing but paranoid. */
 }
 
+#ifdef CONFIG_RSEQ
+static void ipi_rseq(void *info)
+{
+       rseq_preempt(current);
+}
+#endif
+
 static void ipi_sync_rq_state(void *info)
 {
        struct mm_struct *mm = (struct mm_struct *) info;
@@ -129,19 +144,29 @@ static int membarrier_global_expedited(void)
        return 0;
 }
 
-static int membarrier_private_expedited(int flags)
+static int membarrier_private_expedited(int flags, int cpu_id)
 {
-       int cpu;
        cpumask_var_t tmpmask;
        struct mm_struct *mm = current->mm;
+       smp_call_func_t ipi_func = ipi_mb;
 
Quoted 16 lines
Quoted 6 lines
kernel/sched/membarrier.c +1 -1
-       if (flags & MEMBARRIER_FLAG_SYNC_CORE) {
+       if (flags == MEMBARRIER_FLAG_SYNC_CORE) {
                if (!IS_ENABLED(CONFIG_ARCH_HAS_MEMBARRIER_SYNC_CORE))
                        return -EINVAL;
                if (!(atomic_read(&mm->membarrier_state) &
                      MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY))

kernel/sched/membarrier.c static int membarrier_global_expedited(void) · line 167

Quoted 10 lines
kernel/sched/membarrier.c +9 -0
                        return -EPERM;
+       } else if (flags == MEMBARRIER_FLAG_RSEQ) {
+#ifdef CONFIG_RSEQ
+               if (!(atomic_read(&mm->membarrier_state) &
+                     MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ_READY))
+                       return -EPERM;
+               ipi_func = ipi_rseq;
+#else
+               return -EINVAL;
+#endif

I'm allergic to mixing code logic and preprocessor logic. Anything against the following changes ?

(above)

static void ipi_rseq(void *info)

{
    rseq_preempt(current);
}

^ without the #ifdef CONFIG_RSEQ (rseq_preempt is already defined as a no-op when CONFIG_RSEQ=n)

and within membarrier_private_expedited:

if (!IS_ENABLED(CONFIG_RSEQ))
return -EINVAL;
if (!(atomic_read(&mm->membarrier_state) &
MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ_READY))
return -EPERM;
ipi_func = ipi_rseq;

[...]

Quoted 17 lines
Quoted 17 lines
kernel/sched/membarrier.c +9 -2
@@ -310,8 +368,15 @@ static int membarrier_register_private_expedited(int flags)
 
 /**
  * sys_membarrier - issue memory barriers on a set of threads
- * @cmd:   Takes command values defined in enum membarrier_cmd.
- * @flags: Currently needs to be 0. For future extensions.
+ * @cmd:    Takes command values defined in enum membarrier_cmd.
+ * @flags:  Currently needs to be 0 for all commands other than
+ *          MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ: in the latter
+ *          case it can be MEMBARRIER_CMD_FLAG_CPU, indicating that @cpu_id
+ *          contains the CPU on which to interrupt (= restart)
+ *          the RSEQ critical section.
+ * @cpu_id: if @flags == MEMBARRIER_CMD_FLAG_CPU, indicates the cpu on which
+ *          RSEQ CS should be interrupted (@cmd must be
+ *          MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ).
  *
  * If this system call is not implemented, -ENOSYS is returned. If the
Quoted 8 lines

kernel/sched/membarrier.c static int membarrier_register_private_expedited(int · line 406

Quoted 8 lines
kernel/sched/membarrier.c +1 -1
  * command specified does not exist, not available on the running
@@ -337,10 +402,21 @@ static int membarrier_register_private_expedited(int
 flags)
  *        smp_mb()           X           O            O
  *        sys_membarrier()   O           O            O
  */
-SYSCALL_DEFINE2(membarrier, int, cmd, int, flags)
+SYSCALL_DEFINE3(membarrier, int, cmd, int, flags, int, cpu_id)

Now that we have the first use of "flags", it would be a good time to change "int flags" to "unsigned int flags", which is a preferred way to express system call flags parameters.

Thanks,

Mathieu

Quoted 44 lines
Quoted 44 lines
kernel/sched/membarrier.c +13 -2
 {
-       if (unlikely(flags))
-               return -EINVAL;
+       switch (cmd) {
+       case MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ:
+               if (unlikely(flags && flags != MEMBARRIER_CMD_FLAG_CPU))
+                       return -EINVAL;
+               break;
+       default:
+               if (unlikely(flags))
+                       return -EINVAL;
+       }
+
+       if (!(flags & MEMBARRIER_CMD_FLAG_CPU))
+               cpu_id = -1;
+
        switch (cmd) {
        case MEMBARRIER_CMD_QUERY:
        {
kernel/sched/membarrier.c +6 -2
@@ -362,13 +438,17 @@ SYSCALL_DEFINE2(membarrier, int, cmd, int, flags)
        case MEMBARRIER_CMD_REGISTER_GLOBAL_EXPEDITED:
                return membarrier_register_global_expedited();
        case MEMBARRIER_CMD_PRIVATE_EXPEDITED:
-               return membarrier_private_expedited(0);
+               return membarrier_private_expedited(0, cpu_id);
        case MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED:
                return membarrier_register_private_expedited(0);
        case MEMBARRIER_CMD_PRIVATE_EXPEDITED_SYNC_CORE:
-               return membarrier_private_expedited(MEMBARRIER_FLAG_SYNC_CORE);
+               return membarrier_private_expedited(MEMBARRIER_FLAG_SYNC_CORE,
 cpu_id);
        case MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_SYNC_CORE:
                return membarrier_register_private_expedited(MEMBARRIER_FLAG_SYNC_CORE);
+       case MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ:
+               return membarrier_private_expedited(MEMBARRIER_FLAG_RSEQ,
 cpu_id);
+       case MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ:
+               return
 membarrier_register_private_expedited(MEMBARRIER_FLAG_RSEQ);
        default:
                return -EINVAL;
        }

--
2.28.0.402.g5ffc5be6b7-goog

Signature · 3 lines
Mathieu Desnoyers
EfficiOS Inc.
http://www.efficios.com
#4 lore raw
Quoted 6 lines · Mathieu Desnoyers
Quoted 1 line · ----- On Sep 15, 2020, at 2:12 AM, Peter Oskolkov [email protected] wrote:

Any comments here? Should I change anything?

See below,

Thanks for the review - all done in V7. Please have a look.

Thanks,
Peter

[...]