Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

The UDP reuseport conflict was a little bit tricky.

The net-next code, via bpf-next, extracted the reuseport handling
into a helper so that the BPF sk lookup code could invoke it.

At the same time, the logic for reuseport handling of unconnected
sockets changed via commit efc6b6f6c3113e8b203b9debfb72d81e0f3dcace
which changed the logic to carry on the reuseport result into the
rest of the lookup loop if we do not return immediately.

This requires moving the reuseport_has_conns() logic into the callers.

While we are here, get rid of inline directives as they do not belong
in foo.c files.

The other changes were cases of more straightforward overlapping
modifications.

Signed-off-by: David S. Miller <davem@davemloft.net>

8 files changed, 193 insertions, 62 deletions

diff --git a/kernel/debug/gdbstub.c b/kernel/debug/gdbstub.c
index 61774aec46b4..a790026e42d0 100644
--- a/kernel/debug/gdbstub.c
+++ b/kernel/debug/gdbstub.c
@@ -792,6 +792,19 @@ static void gdb_cmd_query(struct kgdb_state *ks)
 		}
 		break;
 #endif
+#ifdef CONFIG_HAVE_ARCH_KGDB_QXFER_PKT
+	case 'S':
+		if (!strncmp(remcom_in_buffer, "qSupported:", 11))
+			strcpy(remcom_out_buffer, kgdb_arch_gdb_stub_feature);
+		break;
+	case 'X':
+		if (!strncmp(remcom_in_buffer, "qXfer:", 6))
+			kgdb_arch_handle_qxfer_pkt(remcom_in_buffer,
+						   remcom_out_buffer);
+		break;
+#endif
+	default:
+		break;
 	}
 }
 
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 95866b647581..67f060b86a73 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -70,7 +70,7 @@ gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask,
 	return 0;
 }
 
-static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size)
+bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size)
 {
 	return phys_to_dma_direct(dev, phys) + size - 1 <=
 			min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit);
diff --git a/kernel/dma/pool.c b/kernel/dma/pool.c
index 39ca26fa41b5..6bc74a2d5127 100644
--- a/kernel/dma/pool.c
+++ b/kernel/dma/pool.c
@@ -6,7 +6,6 @@
 #include <linux/debugfs.h>
 #include <linux/dma-direct.h>
 #include <linux/dma-noncoherent.h>
-#include <linux/dma-contiguous.h>
 #include <linux/init.h>
 #include <linux/genalloc.h>
 #include <linux/set_memory.h>
@@ -69,12 +68,7 @@ static int atomic_pool_expand(struct gen_pool *pool, size_t pool_size,
 
 	do {
 		pool_size = 1 << (PAGE_SHIFT + order);
-
-		if (dev_get_cma_area(NULL))
-			page = dma_alloc_from_contiguous(NULL, 1 << order,
-							 order, false);
-		else
-			page = alloc_pages(gfp, order);
+		page = alloc_pages(gfp, order);
 	} while (!page && order-- > 0);
 	if (!page)
 		goto out;
@@ -118,8 +112,7 @@ remove_mapping:
 	dma_common_free_remap(addr, pool_size);
 #endif
 free_page: __maybe_unused
-	if (!dma_release_from_contiguous(NULL, page, 1 << order))
-		__free_pages(page, order);
+	__free_pages(page, order);
 out:
 	return ret;
 }
@@ -203,7 +196,7 @@ static int __init dma_atomic_pool_init(void)
 }
 postcore_initcall(dma_atomic_pool_init);
 
-static inline struct gen_pool *dev_to_pool(struct device *dev)
+static inline struct gen_pool *dma_guess_pool_from_device(struct device *dev)
 {
 	u64 phys_mask;
 	gfp_t gfp;
@@ -217,51 +210,79 @@ static inline struct gen_pool *dev_to_pool(struct device *dev)
 	return atomic_pool_kernel;
 }
 
-static bool dma_in_atomic_pool(struct device *dev, void *start, size_t size)
+static inline struct gen_pool *dma_get_safer_pool(struct gen_pool *bad_pool)
+{
+	if (bad_pool == atomic_pool_kernel)
+		return atomic_pool_dma32 ? : atomic_pool_dma;
+
+	if (bad_pool == atomic_pool_dma32)
+		return atomic_pool_dma;
+
+	return NULL;
+}
+
+static inline struct gen_pool *dma_guess_pool(struct device *dev,
+					      struct gen_pool *bad_pool)
 {
-	struct gen_pool *pool = dev_to_pool(dev);
+	if (bad_pool)
+		return dma_get_safer_pool(bad_pool);
 
-	if (unlikely(!pool))
-		return false;
-	return gen_pool_has_addr(pool, (unsigned long)start, size);
+	return dma_guess_pool_from_device(dev);
 }
 
 void *dma_alloc_from_pool(struct device *dev, size_t size,
 			  struct page **ret_page, gfp_t flags)
 {
-	struct gen_pool *pool = dev_to_pool(dev);
-	unsigned long val;
+	struct gen_pool *pool = NULL;
+	unsigned long val = 0;
 	void *ptr = NULL;
-
-	if (!pool) {
-		WARN(1, "%pGg atomic pool not initialised!\n", &flags);
-		return NULL;
+	phys_addr_t phys;
+
+	while (1) {
+		pool = dma_guess_pool(dev, pool);
+		if (!pool) {
+			WARN(1, "Failed to get suitable pool for %s\n",
+			     dev_name(dev));
+			break;
+		}
+
+		val = gen_pool_alloc(pool, size);
+		if (!val)
+			continue;
+
+		phys = gen_pool_virt_to_phys(pool, val);
+		if (dma_coherent_ok(dev, phys, size))
+			break;
+
+		gen_pool_free(pool, val, size);
+		val = 0;
 	}
 
-	val = gen_pool_alloc(pool, size);
-	if (likely(val)) {
-		phys_addr_t phys = gen_pool_virt_to_phys(pool, val);
 
+	if (val) {
 		*ret_page = pfn_to_page(__phys_to_pfn(phys));
 		ptr = (void *)val;
 		memset(ptr, 0, size);
-	} else {
-		WARN_ONCE(1, "DMA coherent pool depleted, increase size "
-			     "(recommended min coherent_pool=%zuK)\n",
-			  gen_pool_size(pool) >> 9);
+
+		if (gen_pool_avail(pool) < atomic_pool_size)
+			schedule_work(&atomic_pool_work);
 	}
-	if (gen_pool_avail(pool) < atomic_pool_size)
-		schedule_work(&atomic_pool_work);
 
 	return ptr;
 }
 
 bool dma_free_from_pool(struct device *dev, void *start, size_t size)
 {
-	struct gen_pool *pool = dev_to_pool(dev);
+	struct gen_pool *pool = NULL;
+
+	while (1) {
+		pool = dma_guess_pool(dev, pool);
+		if (!pool)
+			return false;
 
-	if (!dma_in_atomic_pool(dev, start, size))
-		return false;
-	gen_pool_free(pool, (unsigned long)start, size);
-	return true;
+		if (gen_pool_has_addr(pool, (unsigned long)start, size)) {
+			gen_pool_free(pool, (unsigned long)start, size);
+			return true;
+		}
+	}
 }
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index bb0862873dba..5f8b0c52fd2e 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -2199,7 +2199,7 @@ static void handle_swbp(struct pt_regs *regs)
 	if (!uprobe) {
 		if (is_swbp > 0) {
 			/* No matching uprobe; signal SIGTRAP. */
-			send_sig(SIGTRAP, current, 0);
+			force_sig(SIGTRAP);
 		} else {
 			/*
 			 * Either we raced with uprobe_unregister() or we can't
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 761911168438..2a9fec53e159 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -195,9 +195,9 @@ void irq_set_thread_affinity(struct irq_desc *desc)
 			set_bit(IRQTF_AFFINITY, &action->thread_flags);
 }
 
+#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK
 static void irq_validate_effective_affinity(struct irq_data *data)
 {
-#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK
 	const struct cpumask *m = irq_data_get_effective_affinity_mask(data);
 	struct irq_chip *chip = irq_data_get_irq_chip(data);
 
@@ -205,9 +205,19 @@ static void irq_validate_effective_affinity(struct irq_data *data)
 		return;
 	pr_warn_once("irq_chip %s did not update eff. affinity mask of irq %u\n",
 		     chip->name, data->irq);
-#endif
 }
 
+static inline void irq_init_effective_affinity(struct irq_data *data,
+					       const struct cpumask *mask)
+{
+	cpumask_copy(irq_data_get_effective_affinity_mask(data), mask);
+}
+#else
+static inline void irq_validate_effective_affinity(struct irq_data *data) { }
+static inline void irq_init_effective_affinity(struct irq_data *data,
+					       const struct cpumask *mask) { }
+#endif
+
 int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask,
 			bool force)
 {
@@ -304,6 +314,26 @@ static int irq_try_set_affinity(struct irq_data *data,
 	return ret;
 }
 
+static bool irq_set_affinity_deactivated(struct irq_data *data,
+					 const struct cpumask *mask, bool force)
+{
+	struct irq_desc *desc = irq_data_to_desc(data);
+
+	/*
+	 * If the interrupt is not yet activated, just store the affinity
+	 * mask and do not call the chip driver at all. On activation the
+	 * driver has to make sure anyway that the interrupt is in a
+	 * useable state so startup works.
+	 */
+	if (!IS_ENABLED(CONFIG_IRQ_DOMAIN_HIERARCHY) || irqd_is_activated(data))
+		return false;
+
+	cpumask_copy(desc->irq_common_data.affinity, mask);
+	irq_init_effective_affinity(data, mask);
+	irqd_set(data, IRQD_AFFINITY_SET);
+	return true;
+}
+
 int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask,
 			    bool force)
 {
@@ -314,6 +344,9 @@ int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask,
 	if (!chip || !chip->irq_set_affinity)
 		return -EINVAL;
 
+	if (irq_set_affinity_deactivated(data, mask, force))
+		return 0;
+
 	if (irq_can_move_pcntxt(data) && !irqd_is_setaffinity_pending(data)) {
 		ret = irq_try_set_affinity(data, mask, force);
 	} else {
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index ca5db40392d4..2142c6767682 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1311,9 +1311,6 @@ static inline void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
 
 void activate_task(struct rq *rq, struct task_struct *p, int flags)
 {
-	if (task_contributes_to_load(p))
-		rq->nr_uninterruptible--;
-
 	enqueue_task(rq, p, flags);
 
 	p->on_rq = TASK_ON_RQ_QUEUED;
@@ -1323,9 +1320,6 @@ void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
 {
 	p->on_rq = (flags & DEQUEUE_SLEEP) ? 0 : TASK_ON_RQ_MIGRATING;
 
-	if (task_contributes_to_load(p))
-		rq->nr_uninterruptible++;
-
 	dequeue_task(rq, p, flags);
 }
 
@@ -2236,10 +2230,10 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
 
 	lockdep_assert_held(&rq->lock);
 
-#ifdef CONFIG_SMP
 	if (p->sched_contributes_to_load)
 		rq->nr_uninterruptible--;
 
+#ifdef CONFIG_SMP
 	if (wake_flags & WF_MIGRATED)
 		en_flags |= ENQUEUE_MIGRATED;
 #endif
@@ -2583,7 +2577,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	 * A similar smb_rmb() lives in try_invoke_on_locked_down_task().
 	 */
 	smp_rmb();
-	if (p->on_rq && ttwu_remote(p, wake_flags))
+	if (READ_ONCE(p->on_rq) && ttwu_remote(p, wake_flags))
 		goto unlock;
 
 	if (p->in_iowait) {
@@ -2592,9 +2586,6 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	}
 
 #ifdef CONFIG_SMP
-	p->sched_contributes_to_load = !!task_contributes_to_load(p);
-	p->state = TASK_WAKING;
-
 	/*
 	 * Ensure we load p->on_cpu _after_ p->on_rq, otherwise it would be
 	 * possible to, falsely, observe p->on_cpu == 0.
@@ -2613,8 +2604,20 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	 *
 	 * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in
 	 * __schedule().  See the comment for smp_mb__after_spinlock().
+	 *
+	 * Form a control-dep-acquire with p->on_rq == 0 above, to ensure
+	 * schedule()'s deactivate_task() has 'happened' and p will no longer
+	 * care about it's own p->state. See the comment in __schedule().
 	 */
-	smp_rmb();
+	smp_acquire__after_ctrl_dep();
+
+	/*
+	 * We're doing the wakeup (@success == 1), they did a dequeue (p->on_rq
+	 * == 0), which means we need to do an enqueue, change p->state to
+	 * TASK_WAKING such that we can unlock p->pi_lock before doing the
+	 * enqueue, such as ttwu_queue_wakelist().
+	 */
+	p->state = TASK_WAKING;
 
 	/*
 	 * If the owning (remote) CPU is still in the middle of schedule() with
@@ -2962,6 +2965,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 	 * Silence PROVE_RCU.
 	 */
 	raw_spin_lock_irqsave(&p->pi_lock, flags);
+	rseq_migrate(p);
 	/*
 	 * We're setting the CPU for the first time, we don't migrate,
 	 * so use __set_task_cpu().
@@ -3026,6 +3030,7 @@ void wake_up_new_task(struct task_struct *p)
 	 * as we're not fully set-up yet.
 	 */
 	p->recent_used_cpu = task_cpu(p);
+	rseq_migrate(p);
 	__set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0));
 #endif
 	rq = __task_rq_lock(p, &rf);
@@ -4097,6 +4102,7 @@ static void __sched notrace __schedule(bool preempt)
 {
 	struct task_struct *prev, *next;
 	unsigned long *switch_count;
+	unsigned long prev_state;
 	struct rq_flags rf;
 	struct rq *rq;
 	int cpu;
@@ -4116,9 +4122,16 @@ static void __sched notrace __schedule(bool preempt)
 	/*
 	 * Make sure that signal_pending_state()->signal_pending() below
 	 * can't be reordered with __set_current_state(TASK_INTERRUPTIBLE)
-	 * done by the caller to avoid the race with signal_wake_up().
+	 * done by the caller to avoid the race with signal_wake_up():
+	 *
+	 * __set_current_state(@state)		signal_wake_up()
+	 * schedule()				  set_tsk_thread_flag(p, TIF_SIGPENDING)
+	 *					  wake_up_state(p, state)
+	 *   LOCK rq->lock			    LOCK p->pi_state
+	 *   smp_mb__after_spinlock()		    smp_mb__after_spinlock()
+	 *     if (signal_pending_state())	    if (p->state & @state)
 	 *
-	 * The membarrier system call requires a full memory barrier
+	 * Also, the membarrier system call requires a full memory barrier
 	 * after coming from user-space, before storing to rq->curr.
 	 */
 	rq_lock(rq, &rf);
@@ -4129,10 +4142,38 @@ static void __sched notrace __schedule(bool preempt)
 	update_rq_clock(rq);
 
 	switch_count = &prev->nivcsw;
-	if (!preempt && prev->state) {
-		if (signal_pending_state(prev->state, prev)) {
+
+	/*
+	 * We must load prev->state once (task_struct::state is volatile), such
+	 * that:
+	 *
+	 *  - we form a control dependency vs deactivate_task() below.
+	 *  - ptrace_{,un}freeze_traced() can change ->state underneath us.
+	 */
+	prev_state = prev->state;
+	if (!preempt && prev_state) {
+		if (signal_pending_state(prev_state, prev)) {
 			prev->state = TASK_RUNNING;
 		} else {
+			prev->sched_contributes_to_load =
+				(prev_state & TASK_UNINTERRUPTIBLE) &&
+				!(prev_state & TASK_NOLOAD) &&
+				!(prev->flags & PF_FROZEN);
+
+			if (prev->sched_contributes_to_load)
+				rq->nr_uninterruptible++;
+
+			/*
+			 * __schedule()			ttwu()
+			 *   prev_state = prev->state;    if (p->on_rq && ...)
+			 *   if (prev_state)		    goto out;
+			 *     p->on_rq = 0;		  smp_acquire__after_ctrl_dep();
+			 *				  p->state = TASK_WAKING
+			 *
+			 * Where __schedule() and ttwu() have matching control dependencies.
+			 *
+			 * After this, schedule() must not care about p->state any more.
+			 */
 			deactivate_task(rq, prev, DEQUEUE_SLEEP | DEQUEUE_NOCLOCK);
 
 			if (prev->in_iowait) {
@@ -4444,6 +4485,7 @@ asmlinkage __visible void __sched preempt_schedule_irq(void)
 int default_wake_function(wait_queue_entry_t *curr, unsigned mode, int wake_flags,
 			  void *key)
 {
+	WARN_ON_ONCE(IS_ENABLED(CONFIG_SCHED_DEBUG) && wake_flags & ~WF_SYNC);
 	return try_to_wake_up(curr->private, mode, wake_flags);
 }
 EXPORT_SYMBOL(default_wake_function);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 658aa7a2ae6f..04fa8dbcfa4d 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4039,7 +4039,11 @@ static inline void update_misfit_status(struct task_struct *p, struct rq *rq)
 		return;
 	}
 
-	rq->misfit_task_load = task_h_load(p);
+	/*
+	 * Make sure that misfit_task_load will not be null even if
+	 * task_h_load() returns 0.
+	 */
+	rq->misfit_task_load = max_t(unsigned long, task_h_load(p), 1);
 }
 
 #else /* CONFIG_SMP */
@@ -7638,7 +7642,14 @@ static int detach_tasks(struct lb_env *env)
 
 		switch (env->migration_type) {
 		case migrate_load:
-			load = task_h_load(p);
+			/*
+			 * Depending of the number of CPUs and tasks and the
+			 * cgroup hierarchy, task_h_load() can return a null
+			 * value. Make sure that env->imbalance decreases
+			 * otherwise detach_tasks() will stop only after
+			 * detaching up to loop_max tasks.
+			 */
+			load = max_t(unsigned long, task_h_load(p), 1);
 
 			if (sched_feat(LB_MIN) &&
 			    load < 16 && !env->sd->nr_balance_failed)
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 398e6eadb861..df1ff803acc4 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -521,8 +521,8 @@ static int calc_wheel_index(unsigned long expires, unsigned long clk)
 		 * Force expire obscene large timeouts to expire at the
 		 * capacity limit of the wheel.
 		 */
-		if (expires >= WHEEL_TIMEOUT_CUTOFF)
-			expires = WHEEL_TIMEOUT_MAX;
+		if (delta >= WHEEL_TIMEOUT_CUTOFF)
+			expires = clk + WHEEL_TIMEOUT_MAX;
 
 		idx = calc_index(expires, LVL_DEPTH - 1);
 	}
@@ -584,7 +584,15 @@ trigger_dyntick_cpu(struct timer_base *base, struct timer_list *timer)
 	 * Set the next expiry time and kick the CPU so it can reevaluate the
 	 * wheel:
 	 */
-	base->next_expiry = timer->expires;
+	if (time_before(timer->expires, base->clk)) {
+		/*
+		 * Prevent from forward_timer_base() moving the base->clk
+		 * backward
+		 */
+		base->next_expiry = base->clk;
+	} else {
+		base->next_expiry = timer->expires;
+	}
 	wake_up_nohz_cpu(base->cpu);
 }
 
@@ -896,10 +904,13 @@ static inline void forward_timer_base(struct timer_base *base)
 	 * If the next expiry value is > jiffies, then we fast forward to
 	 * jiffies otherwise we forward to the next expiry value.
 	 */
-	if (time_after(base->next_expiry, jnow))
+	if (time_after(base->next_expiry, jnow)) {
 		base->clk = jnow;
-	else
+	} else {
+		if (WARN_ON_ONCE(time_before(base->next_expiry, base->clk)))
+			return;
 		base->clk = base->next_expiry;
+	}
 #endif
 }