Merge tag 'sched-core-2020-10-12' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:

 - reorganize & clean up the SD* flags definitions and add a bunch of
   sanity checks. These new checks caught quite a few bugs or at least
   inconsistencies, resulting in another set of patches.

 - rseq updates, add MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ

 - add a new tracepoint to improve CPU capacity tracking

 - improve overloaded SMP system load-balancing behavior

 - tweak SMT balancing

 - energy-aware scheduling updates

 - NUMA balancing improvements

 - deadline scheduler fixes and improvements

 - CPU isolation fixes

 - misc cleanups, simplifications and smaller optimizations

* tag 'sched-core-2020-10-12' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (42 commits)
  sched/deadline: Unthrottle PI boosted threads while enqueuing
  sched/debug: Add new tracepoint to track cpu_capacity
  sched/fair: Tweak pick_next_entity()
  rseq/selftests: Test MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ
  rseq/selftests,x86_64: Add rseq_offset_deref_addv()
  rseq/membarrier: Add MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ
  sched/fair: Use dst group while checking imbalance for NUMA balancer
  sched/fair: Reduce busy load balance interval
  sched/fair: Minimize concurrent LBs between domain level
  sched/fair: Reduce minimal imbalance threshold
  sched/fair: Relax constraint on task's load during load balance
  sched/fair: Remove the force parameter of update_tg_load_avg()
  sched/fair: Fix wrong cpu selecting from isolated domain
  sched: Remove unused inline function uclamp_bucket_base_value()
  sched/rt: Disable RT_RUNTIME_SHARE by default
  sched/deadline: Fix stale throttling on de-/boosted tasks
  sched/numa: Use runnable_avg to classify node
  sched/topology: Move sd_flag_debug out of #ifdef CONFIG_SYSCTL
  MAINTAINERS: Add myself as SCHED_DEADLINE reviewer
  sched/topology: Move SD_DEGENERATE_GROUPS_MASK out of linux/sched/topology.h
  ...

3 files changed, 281 insertions, 1 deletions

diff --git a/tools/testing/selftests/rseq/param_test.c b/tools/testing/selftests/rseq/param_test.c
index e8a657a5f48a..384589095864 100644
--- a/tools/testing/selftests/rseq/param_test.c
+++ b/tools/testing/selftests/rseq/param_test.c
@@ -1,8 +1,10 @@
 // SPDX-License-Identifier: LGPL-2.1
 #define _GNU_SOURCE
 #include <assert.h>
+#include <linux/membarrier.h>
 #include <pthread.h>
 #include <sched.h>
+#include <stdatomic.h>
 #include <stdint.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -1131,6 +1133,220 @@ static int set_signal_handler(void)
 	return ret;
 }
 
+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 = opt_reps;
+	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,
+				sizeof(struct percpu_list_entry) * 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);
+		if (sys_membarrier(MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ,
+					MEMBARRIER_CMD_FLAG_CPU, cpu_a) &&
+				errno != ENXIO /* missing CPU */) {
+			perror("sys_membarrier");
+			abort();
+		}
+		/*
+		 * Cpu A should now only modify list_b, so the 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);
+		if (sys_membarrier(MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ,
+					MEMBARRIER_CMD_FLAG_CPU, cpu_b) &&
+				errno != ENXIO /* missing CPU*/) {
+			perror("sys_membarrier");
+			abort();
+		}
+		/* 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. */
+#ifdef RSEQ_ARCH_HAS_OFFSET_DEREF_ADDV
+void test_membarrier(void)
+{
+	const int num_threads = opt_threads;
+	struct test_membarrier_thread_args thread_args;
+	pthread_t worker_threads[num_threads];
+	pthread_t manager_thread;
+	int i, ret;
+
+	if (sys_membarrier(MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ, 0, 0)) {
+		perror("sys_membarrier");
+		abort();
+	}
+
+	thread_args.stop = 0;
+	thread_args.percpu_list_ptr = 0;
+	ret = pthread_create(&manager_thread, NULL,
+			test_membarrier_manager_thread, &thread_args);
+	if (ret) {
+		errno = ret;
+		perror("pthread_create");
+		abort();
+	}
+
+	for (i = 0; i < num_threads; i++) {
+		ret = pthread_create(&worker_threads[i], NULL,
+				test_membarrier_worker_thread, &thread_args);
+		if (ret) {
+			errno = ret;
+			perror("pthread_create");
+			abort();
+		}
+	}
+
+
+	for (i = 0; i < num_threads; i++) {
+		ret = pthread_join(worker_threads[i], NULL);
+		if (ret) {
+			errno = ret;
+			perror("pthread_join");
+			abort();
+		}
+	}
+
+	atomic_store(&thread_args.stop, 1);
+	ret = pthread_join(manager_thread, NULL);
+	if (ret) {
+		errno = ret;
+		perror("pthread_join");
+		abort();
+	}
+}
+#else /* RSEQ_ARCH_HAS_OFFSET_DEREF_ADDV */
+void test_membarrier(void)
+{
+	fprintf(stderr, "rseq_offset_deref_addv is not implemented on this architecture. "
+			"Skipping membarrier test.\n");
+}
+#endif
+
 static void show_usage(int argc, char **argv)
 {
 	printf("Usage : %s <OPTIONS>\n",
@@ -1153,7 +1369,7 @@ static void show_usage(int argc, char **argv)
 	printf("	[-r N] Number of repetitions per thread (default 5000)\n");
 	printf("	[-d] Disable rseq system call (no initialization)\n");
 	printf("	[-D M] Disable rseq for each M threads\n");
-	printf("	[-T test] Choose test: (s)pinlock, (l)ist, (b)uffer, (m)emcpy, (i)ncrement\n");
+	printf("	[-T test] Choose test: (s)pinlock, (l)ist, (b)uffer, (m)emcpy, (i)ncrement, membarrie(r)\n");
 	printf("	[-M] Push into buffer and memcpy buffer with memory barriers.\n");
 	printf("	[-v] Verbose output.\n");
 	printf("	[-h] Show this help.\n");
@@ -1268,6 +1484,7 @@ int main(int argc, char **argv)
 			case 'i':
 			case 'b':
 			case 'm':
+			case 'r':
 				break;
 			default:
 				show_usage(argc, argv);
@@ -1320,6 +1537,10 @@ int main(int argc, char **argv)
 		printf_verbose("counter increment\n");
 		test_percpu_inc();
 		break;
+	case 'r':
+		printf_verbose("membarrier\n");
+		test_membarrier();
+		break;
 	}
 	if (!opt_disable_rseq && rseq_unregister_current_thread())
 		abort();
diff --git a/tools/testing/selftests/rseq/rseq-x86.h b/tools/testing/selftests/rseq/rseq-x86.h
index b2da6004fe30..640411518e46 100644
--- a/tools/testing/selftests/rseq/rseq-x86.h
+++ b/tools/testing/selftests/rseq/rseq-x86.h
@@ -279,6 +279,63 @@ error1:
 #endif
 }
 
+#define RSEQ_ARCH_HAS_OFFSET_DEREF_ADDV
+
+/*
+ *   pval = *(ptr+off)
+ *  *pval += inc;
+ */
+static inline __attribute__((always_inline))
+int rseq_offset_deref_addv(intptr_t *ptr, off_t off, intptr_t inc, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
+#endif
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+		RSEQ_INJECT_ASM(3)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1])
+#endif
+		/* get p+v */
+		"movq %[ptr], %%rbx\n\t"
+		"addq %[off], %%rbx\n\t"
+		/* get pv */
+		"movq (%%rbx), %%rcx\n\t"
+		/* *pv += inc */
+		"addq %[inc], (%%rcx)\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(4)
+		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [rseq_abi]		"r" (&__rseq_abi),
+		  /* final store input */
+		  [ptr]			"m" (*ptr),
+		  [off]			"er" (off),
+		  [inc]			"er" (inc)
+		: "memory", "cc", "rax", "rbx", "rcx"
+		  RSEQ_INJECT_CLOBBER
+		: abort
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1
+#endif
+	);
+	return 0;
+abort:
+	RSEQ_INJECT_FAILED
+	return -1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_bug("cpu_id comparison failed");
+#endif
+}
+
 static inline __attribute__((always_inline))
 int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
 				 intptr_t *v2, intptr_t newv2,
diff --git a/tools/testing/selftests/rseq/run_param_test.sh b/tools/testing/selftests/rseq/run_param_test.sh
index e426304fd4a0..f51bc83c9e41 100755
--- a/tools/testing/selftests/rseq/run_param_test.sh
+++ b/tools/testing/selftests/rseq/run_param_test.sh
@@ -15,6 +15,7 @@ TEST_LIST=(
 	"-T m"
 	"-T m -M"
 	"-T i"
+	"-T r"
 )
 
 TEST_NAME=(
@@ -25,6 +26,7 @@ TEST_NAME=(
 	"memcpy"
 	"memcpy with barrier"
 	"increment"
+	"membarrier"
 )
 IFS="$OLDIFS"