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

Conflicts:

tools/testing/selftests/net/config
  62199e3f1658 ("selftests: net: Add VXLAN MDB test")
  3a0385be133e ("selftests: add the missing CONFIG_IP_SCTP in net config")

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

6 files changed, 43 insertions, 24 deletions

diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 5b919ef832b6..dac42a2ad588 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -623,7 +623,7 @@ static int swiotlb_do_find_slots(struct device *dev, int area_index,
 		phys_to_dma_unencrypted(dev, mem->start) & boundary_mask;
 	unsigned long max_slots = get_max_slots(boundary_mask);
 	unsigned int iotlb_align_mask =
-		dma_get_min_align_mask(dev) & ~(IO_TLB_SIZE - 1);
+		dma_get_min_align_mask(dev) | alloc_align_mask;
 	unsigned int nslots = nr_slots(alloc_size), stride;
 	unsigned int offset = swiotlb_align_offset(dev, orig_addr);
 	unsigned int index, slots_checked, count = 0, i;
@@ -639,8 +639,8 @@ static int swiotlb_do_find_slots(struct device *dev, int area_index,
 	 * allocations.
 	 */
 	if (alloc_size >= PAGE_SIZE)
-		iotlb_align_mask &= PAGE_MASK;
-	iotlb_align_mask &= alloc_align_mask;
+		iotlb_align_mask |= ~PAGE_MASK;
+	iotlb_align_mask &= ~(IO_TLB_SIZE - 1);
 
 	/*
 	 * For mappings with an alignment requirement don't bother looping to
diff --git a/kernel/events/core.c b/kernel/events/core.c
index fb3e436bcd4a..435815d3be3f 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -12173,7 +12173,7 @@ perf_event_set_output(struct perf_event *event, struct perf_event *output_event)
 	/*
 	 * If its not a per-cpu rb, it must be the same task.
 	 */
-	if (output_event->cpu == -1 && output_event->ctx != event->ctx)
+	if (output_event->cpu == -1 && output_event->hw.target != event->hw.target)
 		goto out;
 
 	/*
@@ -12893,12 +12893,14 @@ void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu)
 	__perf_pmu_remove(src_ctx, src_cpu, pmu, &src_ctx->pinned_groups, &events);
 	__perf_pmu_remove(src_ctx, src_cpu, pmu, &src_ctx->flexible_groups, &events);
 
-	/*
-	 * Wait for the events to quiesce before re-instating them.
-	 */
-	synchronize_rcu();
+	if (!list_empty(&events)) {
+		/*
+		 * Wait for the events to quiesce before re-instating them.
+		 */
+		synchronize_rcu();
 
-	__perf_pmu_install(dst_ctx, dst_cpu, pmu, &events);
+		__perf_pmu_install(dst_ctx, dst_cpu, pmu, &events);
+	}
 
 	mutex_unlock(&dst_ctx->mutex);
 	mutex_unlock(&src_ctx->mutex);
diff --git a/kernel/fork.c b/kernel/fork.c
index c0257cbee093..0c92f224c68c 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -617,6 +617,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 	if (retval)
 		goto out;
 
+	mt_clear_in_rcu(vmi.mas.tree);
 	for_each_vma(old_vmi, mpnt) {
 		struct file *file;
 
@@ -700,6 +701,8 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 	retval = arch_dup_mmap(oldmm, mm);
 loop_out:
 	vma_iter_free(&vmi);
+	if (!retval)
+		mt_set_in_rcu(vmi.mas.tree);
 out:
 	mmap_write_unlock(mm);
 	flush_tlb_mm(oldmm);
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 8e880c09ab59..7b95ee98a1a5 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -3024,6 +3024,18 @@ need_offload_krc(struct kfree_rcu_cpu *krcp)
 	return !!READ_ONCE(krcp->head);
 }
 
+static bool
+need_wait_for_krwp_work(struct kfree_rcu_cpu_work *krwp)
+{
+	int i;
+
+	for (i = 0; i < FREE_N_CHANNELS; i++)
+		if (!list_empty(&krwp->bulk_head_free[i]))
+			return true;
+
+	return !!krwp->head_free;
+}
+
 static int krc_count(struct kfree_rcu_cpu *krcp)
 {
 	int sum = atomic_read(&krcp->head_count);
@@ -3107,15 +3119,14 @@ static void kfree_rcu_monitor(struct work_struct *work)
 	for (i = 0; i < KFREE_N_BATCHES; i++) {
 		struct kfree_rcu_cpu_work *krwp = &(krcp->krw_arr[i]);
 
-		// Try to detach bulk_head or head and attach it over any
-		// available corresponding free channel. It can be that
-		// a previous RCU batch is in progress, it means that
-		// immediately to queue another one is not possible so
-		// in that case the monitor work is rearmed.
-		if ((!list_empty(&krcp->bulk_head[0]) && list_empty(&krwp->bulk_head_free[0])) ||
-			(!list_empty(&krcp->bulk_head[1]) && list_empty(&krwp->bulk_head_free[1])) ||
-				(READ_ONCE(krcp->head) && !krwp->head_free)) {
+		// Try to detach bulk_head or head and attach it, only when
+		// all channels are free.  Any channel is not free means at krwp
+		// there is on-going rcu work to handle krwp's free business.
+		if (need_wait_for_krwp_work(krwp))
+			continue;
 
+		// kvfree_rcu_drain_ready() might handle this krcp, if so give up.
+		if (need_offload_krc(krcp)) {
 			// Channel 1 corresponds to the SLAB-pointer bulk path.
 			// Channel 2 corresponds to vmalloc-pointer bulk path.
 			for (j = 0; j < FREE_N_CHANNELS; j++) {
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 0feea145bb29..c67bcc89a771 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -5667,12 +5667,15 @@ int modify_ftrace_direct(unsigned long ip,
 		ret = 0;
 	}
 
-	if (unlikely(ret && new_direct)) {
-		direct->count++;
-		list_del_rcu(&new_direct->next);
-		synchronize_rcu_tasks();
-		kfree(new_direct);
-		ftrace_direct_func_count--;
+	if (ret) {
+		direct->addr = old_addr;
+		if (unlikely(new_direct)) {
+			direct->count++;
+			list_del_rcu(&new_direct->next);
+			synchronize_rcu_tasks();
+			kfree(new_direct);
+			ftrace_direct_func_count--;
+		}
 	}
 
  out_unlock:
diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c
index f0ff730125bf..d6a70aff2410 100644
--- a/kernel/trace/trace_events_synth.c
+++ b/kernel/trace/trace_events_synth.c
@@ -44,7 +44,7 @@ enum { ERRORS };
 
 static const char *err_text[] = { ERRORS };
 
-DEFINE_MUTEX(lastcmd_mutex);
+static DEFINE_MUTEX(lastcmd_mutex);
 static char *last_cmd;
 
 static int errpos(const char *str)