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

Cross-merge networking fixes after downstream PR.

Conflicts:

include/linux/mlx5/driver.h
  617f5db1a626 ("RDMA/mlx5: Fix affinity assignment")
  dc13180824b7 ("net/mlx5: Enable devlink port for embedded cpu VF vports")
https://lore.kernel.org/all/20230613125939.595e50b8@canb.auug.org.au/

tools/testing/selftests/net/mptcp/mptcp_join.sh
  47867f0a7e83 ("selftests: mptcp: join: skip check if MIB counter not supported")
  425ba803124b ("selftests: mptcp: join: support RM_ADDR for used endpoints or not")
  45b1a1227a7a ("mptcp: introduces more address related mibs")
  0639fa230a21 ("selftests: mptcp: add explicit check for new mibs")
https://lore.kernel.org/netdev/20230609-upstream-net-20230610-mptcp-selftests-support-old-kernels-part-3-v1-0-2896fe2ee8a3@tessares.net/

No adjacent changes.

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

4 files changed, 32 insertions, 19 deletions

diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index aeef06c465ef..5407241dbb45 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -108,7 +108,7 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from)
 
 	cgroup_lock();
 
-	percpu_down_write(&cgroup_threadgroup_rwsem);
+	cgroup_attach_lock(true);
 
 	/* all tasks in @from are being moved, all csets are source */
 	spin_lock_irq(&css_set_lock);
@@ -144,7 +144,7 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from)
 	} while (task && !ret);
 out_err:
 	cgroup_migrate_finish(&mgctx);
-	percpu_up_write(&cgroup_threadgroup_rwsem);
+	cgroup_attach_unlock(true);
 	cgroup_unlock();
 	return ret;
 }
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 625d7483951c..245cf62ce85a 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -6486,19 +6486,18 @@ err:
 static void cgroup_css_set_put_fork(struct kernel_clone_args *kargs)
 	__releases(&cgroup_threadgroup_rwsem) __releases(&cgroup_mutex)
 {
+	struct cgroup *cgrp = kargs->cgrp;
+	struct css_set *cset = kargs->cset;
+
 	cgroup_threadgroup_change_end(current);
 
-	if (kargs->flags & CLONE_INTO_CGROUP) {
-		struct cgroup *cgrp = kargs->cgrp;
-		struct css_set *cset = kargs->cset;
+	if (cset) {
+		put_css_set(cset);
+		kargs->cset = NULL;
+	}
 
+	if (kargs->flags & CLONE_INTO_CGROUP) {
 		cgroup_unlock();
-
-		if (cset) {
-			put_css_set(cset);
-			kargs->cset = NULL;
-		}
-
 		if (cgrp) {
 			cgroup_put(cgrp);
 			kargs->cgrp = NULL;
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index f989f5f1933b..69ee4a29136f 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -901,10 +901,22 @@ static int kexec_purgatory_setup_sechdrs(struct purgatory_info *pi,
 		}
 
 		offset = ALIGN(offset, align);
+
+		/*
+		 * Check if the segment contains the entry point, if so,
+		 * calculate the value of image->start based on it.
+		 * If the compiler has produced more than one .text section
+		 * (Eg: .text.hot), they are generally after the main .text
+		 * section, and they shall not be used to calculate
+		 * image->start. So do not re-calculate image->start if it
+		 * is not set to the initial value, and warn the user so they
+		 * have a chance to fix their purgatory's linker script.
+		 */
 		if (sechdrs[i].sh_flags & SHF_EXECINSTR &&
 		    pi->ehdr->e_entry >= sechdrs[i].sh_addr &&
 		    pi->ehdr->e_entry < (sechdrs[i].sh_addr
-					 + sechdrs[i].sh_size)) {
+					 + sechdrs[i].sh_size) &&
+		    !WARN_ON(kbuf->image->start != pi->ehdr->e_entry)) {
 			kbuf->image->start -= sechdrs[i].sh_addr;
 			kbuf->image->start += kbuf->mem + offset;
 		}
diff --git a/kernel/vhost_task.c b/kernel/vhost_task.c
index f80d5c51ae67..da35e5b7f047 100644
--- a/kernel/vhost_task.c
+++ b/kernel/vhost_task.c
@@ -28,10 +28,6 @@ static int vhost_task_fn(void *data)
 	for (;;) {
 		bool did_work;
 
-		/* mb paired w/ vhost_task_stop */
-		if (test_bit(VHOST_TASK_FLAGS_STOP, &vtsk->flags))
-			break;
-
 		if (!dead && signal_pending(current)) {
 			struct ksignal ksig;
 			/*
@@ -48,11 +44,17 @@ static int vhost_task_fn(void *data)
 				clear_thread_flag(TIF_SIGPENDING);
 		}
 
+		/* mb paired w/ vhost_task_stop */
+		set_current_state(TASK_INTERRUPTIBLE);
+
+		if (test_bit(VHOST_TASK_FLAGS_STOP, &vtsk->flags)) {
+			__set_current_state(TASK_RUNNING);
+			break;
+		}
+
 		did_work = vtsk->fn(vtsk->data);
-		if (!did_work) {
-			set_current_state(TASK_INTERRUPTIBLE);
+		if (!did_work)
 			schedule();
-		}
 	}
 
 	complete(&vtsk->exited);