Merge Energy Model management code changes for 6.16

12 files changed, 118 insertions, 94 deletions

diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 5a5adc66b8e2..92b606d60020 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -2189,7 +2189,7 @@ static long bpf_for_each_hash_elem(struct bpf_map *map, bpf_callback_t callback_
 		b = &htab->buckets[i];
 		rcu_read_lock();
 		head = &b->head;
-		hlist_nulls_for_each_entry_rcu(elem, n, head, hash_node) {
+		hlist_nulls_for_each_entry_safe(elem, n, head, hash_node) {
 			key = elem->key;
 			if (is_percpu) {
 				/* current cpu value for percpu map */
diff --git a/kernel/bpf/preload/bpf_preload_kern.c b/kernel/bpf/preload/bpf_preload_kern.c
index 2fdf3c978db1..774e5a538811 100644
--- a/kernel/bpf/preload/bpf_preload_kern.c
+++ b/kernel/bpf/preload/bpf_preload_kern.c
@@ -89,5 +89,6 @@ static void __exit fini(void)
 }
 late_initcall(load);
 module_exit(fini);
+MODULE_IMPORT_NS("BPF_INTERNAL");
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Embedded BPF programs for introspection in bpffs");
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 9794446bc8c6..64c3393e8270 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1583,7 +1583,7 @@ struct bpf_map *bpf_map_get(u32 ufd)
 
 	return map;
 }
-EXPORT_SYMBOL(bpf_map_get);
+EXPORT_SYMBOL_NS(bpf_map_get, "BPF_INTERNAL");
 
 struct bpf_map *bpf_map_get_with_uref(u32 ufd)
 {
@@ -3364,7 +3364,7 @@ struct bpf_link *bpf_link_get_from_fd(u32 ufd)
 	bpf_link_inc(link);
 	return link;
 }
-EXPORT_SYMBOL(bpf_link_get_from_fd);
+EXPORT_SYMBOL_NS(bpf_link_get_from_fd, "BPF_INTERNAL");
 
 static void bpf_tracing_link_release(struct bpf_link *link)
 {
@@ -6020,7 +6020,7 @@ int kern_sys_bpf(int cmd, union bpf_attr *attr, unsigned int size)
 		return ____bpf_sys_bpf(cmd, attr, size);
 	}
 }
-EXPORT_SYMBOL(kern_sys_bpf);
+EXPORT_SYMBOL_NS(kern_sys_bpf, "BPF_INTERNAL");
 
 static const struct bpf_func_proto bpf_sys_bpf_proto = {
 	.func		= bpf_sys_bpf,
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 3caf2cd86e65..63e5b90da1f3 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -90,7 +90,7 @@
 DEFINE_MUTEX(cgroup_mutex);
 DEFINE_SPINLOCK(css_set_lock);
 
-#ifdef CONFIG_PROVE_RCU
+#if (defined CONFIG_PROVE_RCU || defined CONFIG_LOCKDEP)
 EXPORT_SYMBOL_GPL(cgroup_mutex);
 EXPORT_SYMBOL_GPL(css_set_lock);
 #endif
@@ -2353,9 +2353,37 @@ static struct file_system_type cgroup2_fs_type = {
 };
 
 #ifdef CONFIG_CPUSETS_V1
+enum cpuset_param {
+	Opt_cpuset_v2_mode,
+};
+
+static const struct fs_parameter_spec cpuset_fs_parameters[] = {
+	fsparam_flag  ("cpuset_v2_mode", Opt_cpuset_v2_mode),
+	{}
+};
+
+static int cpuset_parse_param(struct fs_context *fc, struct fs_parameter *param)
+{
+	struct cgroup_fs_context *ctx = cgroup_fc2context(fc);
+	struct fs_parse_result result;
+	int opt;
+
+	opt = fs_parse(fc, cpuset_fs_parameters, param, &result);
+	if (opt < 0)
+		return opt;
+
+	switch (opt) {
+	case Opt_cpuset_v2_mode:
+		ctx->flags |= CGRP_ROOT_CPUSET_V2_MODE;
+		return 0;
+	}
+	return -EINVAL;
+}
+
 static const struct fs_context_operations cpuset_fs_context_ops = {
 	.get_tree	= cgroup1_get_tree,
 	.free		= cgroup_fs_context_free,
+	.parse_param	= cpuset_parse_param,
 };
 
 /*
@@ -2392,6 +2420,7 @@ static int cpuset_init_fs_context(struct fs_context *fc)
 static struct file_system_type cpuset_fs_type = {
 	.name			= "cpuset",
 	.init_fs_context	= cpuset_init_fs_context,
+	.parameters		= cpuset_fs_parameters,
 	.fs_flags		= FS_USERNS_MOUNT,
 };
 #endif
diff --git a/kernel/dma/coherent.c b/kernel/dma/coherent.c
index 3b2bdca9f1d4..77c8d9487a9a 100644
--- a/kernel/dma/coherent.c
+++ b/kernel/dma/coherent.c
@@ -336,16 +336,22 @@ static phys_addr_t dma_reserved_default_memory_size __initdata;
 
 static int rmem_dma_device_init(struct reserved_mem *rmem, struct device *dev)
 {
-	if (!rmem->priv) {
-		struct dma_coherent_mem *mem;
+	struct dma_coherent_mem *mem = rmem->priv;
 
+	if (!mem) {
 		mem = dma_init_coherent_memory(rmem->base, rmem->base,
 					       rmem->size, true);
 		if (IS_ERR(mem))
 			return PTR_ERR(mem);
 		rmem->priv = mem;
 	}
-	dma_assign_coherent_memory(dev, rmem->priv);
+
+	/* Warn if the device potentially can't use the reserved memory */
+	if (mem->device_base + rmem->size - 1 >
+	    min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit))
+		dev_warn(dev, "reserved memory is beyond device's set DMA address range\n");
+
+	dma_assign_coherent_memory(dev, mem);
 	return 0;
 }
 
diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c
index 055da410ac71..8df0dfaaca18 100644
--- a/kernel/dma/contiguous.c
+++ b/kernel/dma/contiguous.c
@@ -64,8 +64,7 @@ struct cma *dma_contiguous_default_area;
  * Users, who want to set the size of global CMA area for their system
  * should use cma= kernel parameter.
  */
-static const phys_addr_t size_bytes __initconst =
-	(phys_addr_t)CMA_SIZE_MBYTES * SZ_1M;
+#define size_bytes ((phys_addr_t)CMA_SIZE_MBYTES * SZ_1M)
 static phys_addr_t  size_cmdline __initdata = -1;
 static phys_addr_t base_cmdline __initdata;
 static phys_addr_t limit_cmdline __initdata;
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index cda127027e48..051a32988040 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -910,6 +910,19 @@ int dma_set_coherent_mask(struct device *dev, u64 mask)
 }
 EXPORT_SYMBOL(dma_set_coherent_mask);
 
+static bool __dma_addressing_limited(struct device *dev)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	if (min_not_zero(dma_get_mask(dev), dev->bus_dma_limit) <
+			 dma_get_required_mask(dev))
+		return true;
+
+	if (unlikely(ops) || use_dma_iommu(dev))
+		return false;
+	return !dma_direct_all_ram_mapped(dev);
+}
+
 /**
  * dma_addressing_limited - return if the device is addressing limited
  * @dev:	device to check
@@ -920,15 +933,11 @@ EXPORT_SYMBOL(dma_set_coherent_mask);
  */
 bool dma_addressing_limited(struct device *dev)
 {
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-
-	if (min_not_zero(dma_get_mask(dev), dev->bus_dma_limit) <
-			 dma_get_required_mask(dev))
-		return true;
-
-	if (unlikely(ops) || use_dma_iommu(dev))
+	if (!__dma_addressing_limited(dev))
 		return false;
-	return !dma_direct_all_ram_mapped(dev);
+
+	dev_dbg(dev, "device is DMA addressing limited\n");
+	return true;
 }
 EXPORT_SYMBOL_GPL(dma_addressing_limited);
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index e93c19565914..95e703891b24 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3943,7 +3943,7 @@ static int merge_sched_in(struct perf_event *event, void *data)
 			perf_event_set_state(event, PERF_EVENT_STATE_ERROR);
 
 			if (*perf_event_fasync(event))
-				event->pending_kill = POLL_HUP;
+				event->pending_kill = POLL_ERR;
 
 			perf_event_wakeup(event);
 		} else {
@@ -6075,7 +6075,7 @@ static __poll_t perf_poll(struct file *file, poll_table *wait)
 
 	if (unlikely(READ_ONCE(event->state) == PERF_EVENT_STATE_ERROR &&
 		     event->attr.pinned))
-		return events;
+		return EPOLLERR;
 
 	/*
 	 * Pin the event->rb by taking event->mmap_mutex; otherwise
diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c
index d9b7e2b38c7a..ea7995a25780 100644
--- a/kernel/power/energy_model.c
+++ b/kernel/power/energy_model.c
@@ -233,6 +233,10 @@ static int em_compute_costs(struct device *dev, struct em_perf_state *table,
 	unsigned long prev_cost = ULONG_MAX;
 	int i, ret;
 
+	/* This is needed only for CPUs and EAS skip other devices */
+	if (!_is_cpu_device(dev))
+		return 0;
+
 	/* Compute the cost of each performance state. */
 	for (i = nr_states - 1; i >= 0; i--) {
 		unsigned long power_res, cost;
@@ -698,10 +702,12 @@ static int em_recalc_and_update(struct device *dev, struct em_perf_domain *pd,
 {
 	int ret;
 
-	ret = em_compute_costs(dev, em_table->state, NULL, pd->nr_perf_states,
-			       pd->flags);
-	if (ret)
-		goto free_em_table;
+	if (!em_is_artificial(pd)) {
+		ret = em_compute_costs(dev, em_table->state, NULL,
+				       pd->nr_perf_states, pd->flags);
+		if (ret)
+			goto free_em_table;
+	}
 
 	ret = em_dev_update_perf_domain(dev, em_table);
 	if (ret)
@@ -721,10 +727,24 @@ free_em_table:
  * Adjustment of CPU performance values after boot, when all CPUs capacites
  * are correctly calculated.
  */
-static void em_adjust_new_capacity(struct device *dev,
+static void em_adjust_new_capacity(unsigned int cpu, struct device *dev,
 				   struct em_perf_domain *pd)
 {
+	unsigned long cpu_capacity = arch_scale_cpu_capacity(cpu);
 	struct em_perf_table *em_table;
+	struct em_perf_state *table;
+	unsigned long em_max_perf;
+
+	rcu_read_lock();
+	table = em_perf_state_from_pd(pd);
+	em_max_perf = table[pd->nr_perf_states - 1].performance;
+	rcu_read_unlock();
+
+	if (em_max_perf == cpu_capacity)
+		return;
+
+	pr_debug("updating cpu%d cpu_cap=%lu old capacity=%lu\n", cpu,
+		 cpu_capacity, em_max_perf);
 
 	em_table = em_table_dup(pd);
 	if (!em_table) {
@@ -737,12 +757,27 @@ static void em_adjust_new_capacity(struct device *dev,
 	em_recalc_and_update(dev, pd, em_table);
 }
 
+/**
+ * em_adjust_cpu_capacity() - Adjust the EM for a CPU after a capacity update.
+ * @cpu: Target CPU.
+ *
+ * Adjust the existing EM for @cpu after a capacity update under the assumption
+ * that the capacity has been updated in the same way for all of the CPUs in
+ * the same perf domain.
+ */
+void em_adjust_cpu_capacity(unsigned int cpu)
+{
+	struct device *dev = get_cpu_device(cpu);
+	struct em_perf_domain *pd;
+
+	pd = em_pd_get(dev);
+	if (pd)
+		em_adjust_new_capacity(cpu, dev, pd);
+}
+
 static void em_check_capacity_update(void)
 {
 	cpumask_var_t cpu_done_mask;
-	struct em_perf_state *table;
-	struct em_perf_domain *pd;
-	unsigned long cpu_capacity;
 	int cpu;
 
 	if (!zalloc_cpumask_var(&cpu_done_mask, GFP_KERNEL)) {
@@ -753,7 +788,7 @@ static void em_check_capacity_update(void)
 	/* Check if CPUs capacity has changed than update EM */
 	for_each_possible_cpu(cpu) {
 		struct cpufreq_policy *policy;
-		unsigned long em_max_perf;
+		struct em_perf_domain *pd;
 		struct device *dev;
 
 		if (cpumask_test_cpu(cpu, cpu_done_mask))
@@ -776,24 +811,7 @@ static void em_check_capacity_update(void)
 		cpumask_or(cpu_done_mask, cpu_done_mask,
 			   em_span_cpus(pd));
 
-		cpu_capacity = arch_scale_cpu_capacity(cpu);
-
-		rcu_read_lock();
-		table = em_perf_state_from_pd(pd);
-		em_max_perf = table[pd->nr_perf_states - 1].performance;
-		rcu_read_unlock();
-
-		/*
-		 * Check if the CPU capacity has been adjusted during boot
-		 * and trigger the update for new performance values.
-		 */
-		if (em_max_perf == cpu_capacity)
-			continue;
-
-		pr_debug("updating cpu%d cpu_cap=%lu old capacity=%lu\n",
-			 cpu, cpu_capacity, em_max_perf);
-
-		em_adjust_new_capacity(dev, pd);
+		em_adjust_new_capacity(cpu, dev, pd);
 	}
 
 	free_cpumask_var(cpu_done_mask);
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 66bcd40a28ca..fdbf249d1c68 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -163,7 +163,7 @@ enum scx_ops_flags {
 	/*
 	 * CPU cgroup support flags
 	 */
-	SCX_OPS_HAS_CGROUP_WEIGHT = 1LLU << 16,	/* cpu.weight */
+	SCX_OPS_HAS_CGROUP_WEIGHT = 1LLU << 16,	/* DEPRECATED, will be removed on 6.18 */
 
 	SCX_OPS_ALL_FLAGS	= SCX_OPS_KEEP_BUILTIN_IDLE |
 				  SCX_OPS_ENQ_LAST |
@@ -3899,35 +3899,6 @@ bool scx_can_stop_tick(struct rq *rq)
 
 DEFINE_STATIC_PERCPU_RWSEM(scx_cgroup_rwsem);
 static bool scx_cgroup_enabled;
-static bool cgroup_warned_missing_weight;
-static bool cgroup_warned_missing_idle;
-
-static void scx_cgroup_warn_missing_weight(struct task_group *tg)
-{
-	if (scx_ops_enable_state() == SCX_OPS_DISABLED ||
-	    cgroup_warned_missing_weight)
-		return;
-
-	if ((scx_ops.flags & SCX_OPS_HAS_CGROUP_WEIGHT) || !tg->css.parent)
-		return;
-
-	pr_warn("sched_ext: \"%s\" does not implement cgroup cpu.weight\n",
-		scx_ops.name);
-	cgroup_warned_missing_weight = true;
-}
-
-static void scx_cgroup_warn_missing_idle(struct task_group *tg)
-{
-	if (!scx_cgroup_enabled || cgroup_warned_missing_idle)
-		return;
-
-	if (!tg->idle)
-		return;
-
-	pr_warn("sched_ext: \"%s\" does not implement cgroup cpu.idle\n",
-		scx_ops.name);
-	cgroup_warned_missing_idle = true;
-}
 
 int scx_tg_online(struct task_group *tg)
 {
@@ -3937,8 +3908,6 @@ int scx_tg_online(struct task_group *tg)
 
 	percpu_down_read(&scx_cgroup_rwsem);
 
-	scx_cgroup_warn_missing_weight(tg);
-
 	if (scx_cgroup_enabled) {
 		if (SCX_HAS_OP(cgroup_init)) {
 			struct scx_cgroup_init_args args =
@@ -4076,9 +4045,7 @@ void scx_group_set_weight(struct task_group *tg, unsigned long weight)
 
 void scx_group_set_idle(struct task_group *tg, bool idle)
 {
-	percpu_down_read(&scx_cgroup_rwsem);
-	scx_cgroup_warn_missing_idle(tg);
-	percpu_up_read(&scx_cgroup_rwsem);
+	/* TODO: Implement ops->cgroup_set_idle() */
 }
 
 static void scx_cgroup_lock(void)
@@ -4272,9 +4239,6 @@ static int scx_cgroup_init(void)
 
 	percpu_rwsem_assert_held(&scx_cgroup_rwsem);
 
-	cgroup_warned_missing_weight = false;
-	cgroup_warned_missing_idle = false;
-
 	/*
 	 * scx_tg_on/offline() are excluded through scx_cgroup_rwsem. If we walk
 	 * cgroups and init, all online cgroups are initialized.
@@ -4284,9 +4248,6 @@ static int scx_cgroup_init(void)
 		struct task_group *tg = css_tg(css);
 		struct scx_cgroup_init_args args = { .weight = tg->scx_weight };
 
-		scx_cgroup_warn_missing_weight(tg);
-		scx_cgroup_warn_missing_idle(tg);
-
 		if ((tg->scx_flags &
 		     (SCX_TG_ONLINE | SCX_TG_INITED)) != SCX_TG_ONLINE)
 			continue;
@@ -4623,7 +4584,7 @@ unlock:
 
 static void free_exit_info(struct scx_exit_info *ei)
 {
-	kfree(ei->dump);
+	kvfree(ei->dump);
 	kfree(ei->msg);
 	kfree(ei->bt);
 	kfree(ei);
@@ -4639,7 +4600,7 @@ static struct scx_exit_info *alloc_exit_info(size_t exit_dump_len)
 
 	ei->bt = kcalloc(SCX_EXIT_BT_LEN, sizeof(ei->bt[0]), GFP_KERNEL);
 	ei->msg = kzalloc(SCX_EXIT_MSG_LEN, GFP_KERNEL);
-	ei->dump = kzalloc(exit_dump_len, GFP_KERNEL);
+	ei->dump = kvzalloc(exit_dump_len, GFP_KERNEL);
 
 	if (!ei->bt || !ei->msg || !ei->dump) {
 		free_exit_info(ei);
@@ -5252,6 +5213,9 @@ static int validate_ops(const struct sched_ext_ops *ops)
 		return -EINVAL;
 	}
 
+	if (ops->flags & SCX_OPS_HAS_CGROUP_WEIGHT)
+		pr_warn("SCX_OPS_HAS_CGROUP_WEIGHT is deprecated and a noop\n");
+
 	return 0;
 }
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index e43993a4e580..0fb9bf995a47 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7081,9 +7081,6 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
 		h_nr_idle = task_has_idle_policy(p);
 		if (task_sleep || task_delayed || !se->sched_delayed)
 			h_nr_runnable = 1;
-	} else {
-		cfs_rq = group_cfs_rq(se);
-		slice = cfs_rq_min_slice(cfs_rq);
 	}
 
 	for_each_sched_entity(se) {
@@ -7093,6 +7090,7 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
 			if (p && &p->se == se)
 				return -1;
 
+			slice = cfs_rq_min_slice(cfs_rq);
 			break;
 		}
 
diff --git a/kernel/vhost_task.c b/kernel/vhost_task.c
index 2ef2e1b80091..2f844c279a3e 100644
--- a/kernel/vhost_task.c
+++ b/kernel/vhost_task.c
@@ -111,7 +111,7 @@ EXPORT_SYMBOL_GPL(vhost_task_stop);
  * @arg: data to be passed to fn and handled_kill
  * @name: the thread's name
  *
- * This returns a specialized task for use by the vhost layer or NULL on
+ * This returns a specialized task for use by the vhost layer or ERR_PTR() on
  * failure. The returned task is inactive, and the caller must fire it up
  * through vhost_task_start().
  */