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

Documentation/bpf/bpf_devel_QA.rst
  b7abcd9c656b ("bpf, doc: Link to submitting-patches.rst for general patch submission info")
  d56b0c461d19 ("bpf, docs: Fix link to netdev-FAQ target")
https://lore.kernel.org/all/20230307095812.236eb1be@canb.auug.org.au/

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

11 files changed, 129 insertions, 129 deletions

diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 93d0b87f3283..addeed3df15d 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -1295,15 +1295,11 @@ out:
 static void audit_log_cap(struct audit_buffer *ab, char *prefix,
 			  kernel_cap_t *cap)
 {
-	int i;
-
 	if (cap_isclear(*cap)) {
 		audit_log_format(ab, " %s=0", prefix);
 		return;
 	}
-	audit_log_format(ab, " %s=", prefix);
-	CAP_FOR_EACH_U32(i)
-		audit_log_format(ab, "%08x", cap->cap[CAP_LAST_U32 - i]);
+	audit_log_format(ab, " %s=%016llx", prefix, cap->val);
 }
 
 static void audit_log_fcaps(struct audit_buffer *ab, struct audit_names *name)
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index a8cb09e5973b..1853beaed4be 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -4574,6 +4574,7 @@ static int btf_datasec_resolve(struct btf_verifier_env *env,
 	struct btf *btf = env->btf;
 	u16 i;
 
+	env->resolve_mode = RESOLVE_TBD;
 	for_each_vsi_from(i, v->next_member, v->t, vsi) {
 		u32 var_type_id = vsi->type, type_id, type_size = 0;
 		const struct btf_type *var_type = btf_type_by_id(env->btf,
diff --git a/kernel/capability.c b/kernel/capability.c
index 339a44dfe2f4..3e058f41df32 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -20,13 +20,6 @@
 #include <linux/user_namespace.h>
 #include <linux/uaccess.h>
 
-/*
- * Leveraged for setting/resetting capabilities
- */
-
-const kernel_cap_t __cap_empty_set = CAP_EMPTY_SET;
-EXPORT_SYMBOL(__cap_empty_set);
-
 int file_caps_enabled = 1;
 
 static int __init file_caps_disable(char *str)
@@ -151,6 +144,7 @@ SYSCALL_DEFINE2(capget, cap_user_header_t, header, cap_user_data_t, dataptr)
 	pid_t pid;
 	unsigned tocopy;
 	kernel_cap_t pE, pI, pP;
+	struct __user_cap_data_struct kdata[2];
 
 	ret = cap_validate_magic(header, &tocopy);
 	if ((dataptr == NULL) || (ret != 0))
@@ -163,42 +157,46 @@ SYSCALL_DEFINE2(capget, cap_user_header_t, header, cap_user_data_t, dataptr)
 		return -EINVAL;
 
 	ret = cap_get_target_pid(pid, &pE, &pI, &pP);
-	if (!ret) {
-		struct __user_cap_data_struct kdata[_KERNEL_CAPABILITY_U32S];
-		unsigned i;
-
-		for (i = 0; i < tocopy; i++) {
-			kdata[i].effective = pE.cap[i];
-			kdata[i].permitted = pP.cap[i];
-			kdata[i].inheritable = pI.cap[i];
-		}
-
-		/*
-		 * Note, in the case, tocopy < _KERNEL_CAPABILITY_U32S,
-		 * we silently drop the upper capabilities here. This
-		 * has the effect of making older libcap
-		 * implementations implicitly drop upper capability
-		 * bits when they perform a: capget/modify/capset
-		 * sequence.
-		 *
-		 * This behavior is considered fail-safe
-		 * behavior. Upgrading the application to a newer
-		 * version of libcap will enable access to the newer
-		 * capabilities.
-		 *
-		 * An alternative would be to return an error here
-		 * (-ERANGE), but that causes legacy applications to
-		 * unexpectedly fail; the capget/modify/capset aborts
-		 * before modification is attempted and the application
-		 * fails.
-		 */
-		if (copy_to_user(dataptr, kdata, tocopy
-				 * sizeof(struct __user_cap_data_struct))) {
-			return -EFAULT;
-		}
-	}
+	if (ret)
+		return ret;
 
-	return ret;
+	/*
+	 * Annoying legacy format with 64-bit capabilities exposed
+	 * as two sets of 32-bit fields, so we need to split the
+	 * capability values up.
+	 */
+	kdata[0].effective   = pE.val; kdata[1].effective   = pE.val >> 32;
+	kdata[0].permitted   = pP.val; kdata[1].permitted   = pP.val >> 32;
+	kdata[0].inheritable = pI.val; kdata[1].inheritable = pI.val >> 32;
+
+	/*
+	 * Note, in the case, tocopy < _KERNEL_CAPABILITY_U32S,
+	 * we silently drop the upper capabilities here. This
+	 * has the effect of making older libcap
+	 * implementations implicitly drop upper capability
+	 * bits when they perform a: capget/modify/capset
+	 * sequence.
+	 *
+	 * This behavior is considered fail-safe
+	 * behavior. Upgrading the application to a newer
+	 * version of libcap will enable access to the newer
+	 * capabilities.
+	 *
+	 * An alternative would be to return an error here
+	 * (-ERANGE), but that causes legacy applications to
+	 * unexpectedly fail; the capget/modify/capset aborts
+	 * before modification is attempted and the application
+	 * fails.
+	 */
+	if (copy_to_user(dataptr, kdata, tocopy * sizeof(kdata[0])))
+		return -EFAULT;
+
+	return 0;
+}
+
+static kernel_cap_t mk_kernel_cap(u32 low, u32 high)
+{
+	return (kernel_cap_t) { (low | ((u64)high << 32)) & CAP_VALID_MASK };
 }
 
 /**
@@ -221,8 +219,8 @@ SYSCALL_DEFINE2(capget, cap_user_header_t, header, cap_user_data_t, dataptr)
  */
 SYSCALL_DEFINE2(capset, cap_user_header_t, header, const cap_user_data_t, data)
 {
-	struct __user_cap_data_struct kdata[_KERNEL_CAPABILITY_U32S];
-	unsigned i, tocopy, copybytes;
+	struct __user_cap_data_struct kdata[2] = { { 0, }, };
+	unsigned tocopy, copybytes;
 	kernel_cap_t inheritable, permitted, effective;
 	struct cred *new;
 	int ret;
@@ -246,21 +244,9 @@ SYSCALL_DEFINE2(capset, cap_user_header_t, header, const cap_user_data_t, data)
 	if (copy_from_user(&kdata, data, copybytes))
 		return -EFAULT;
 
-	for (i = 0; i < tocopy; i++) {
-		effective.cap[i] = kdata[i].effective;
-		permitted.cap[i] = kdata[i].permitted;
-		inheritable.cap[i] = kdata[i].inheritable;
-	}
-	while (i < _KERNEL_CAPABILITY_U32S) {
-		effective.cap[i] = 0;
-		permitted.cap[i] = 0;
-		inheritable.cap[i] = 0;
-		i++;
-	}
-
-	effective.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK;
-	permitted.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK;
-	inheritable.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK;
+	effective   = mk_kernel_cap(kdata[0].effective,   kdata[1].effective);
+	permitted   = mk_kernel_cap(kdata[0].permitted,   kdata[1].permitted);
+	inheritable = mk_kernel_cap(kdata[0].inheritable, kdata[1].inheritable);
 
 	new = prepare_creds();
 	if (!new)
diff --git a/kernel/irq/ipi.c b/kernel/irq/ipi.c
index bbd945bacef0..961d4af76af3 100644
--- a/kernel/irq/ipi.c
+++ b/kernel/irq/ipi.c
@@ -188,9 +188,9 @@ EXPORT_SYMBOL_GPL(ipi_get_hwirq);
 static int ipi_send_verify(struct irq_chip *chip, struct irq_data *data,
 			   const struct cpumask *dest, unsigned int cpu)
 {
-	const struct cpumask *ipimask = irq_data_get_affinity_mask(data);
+	const struct cpumask *ipimask;
 
-	if (!chip || !ipimask)
+	if (!chip || !data)
 		return -EINVAL;
 
 	if (!chip->ipi_send_single && !chip->ipi_send_mask)
@@ -199,6 +199,10 @@ static int ipi_send_verify(struct irq_chip *chip, struct irq_data *data,
 	if (cpu >= nr_cpu_ids)
 		return -EINVAL;
 
+	ipimask = irq_data_get_affinity_mask(data);
+	if (!ipimask)
+		return -EINVAL;
+
 	if (dest) {
 		if (!cpumask_subset(dest, ipimask))
 			return -EINVAL;
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index fd0996274401..240e145e969f 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -277,7 +277,7 @@ static struct attribute *irq_attrs[] = {
 };
 ATTRIBUTE_GROUPS(irq);
 
-static struct kobj_type irq_kobj_type = {
+static const struct kobj_type irq_kobj_type = {
 	.release	= irq_kobj_release,
 	.sysfs_ops	= &kobj_sysfs_ops,
 	.default_groups = irq_groups,
@@ -335,7 +335,7 @@ postcore_initcall(irq_sysfs_init);
 
 #else /* !CONFIG_SYSFS */
 
-static struct kobj_type irq_kobj_type = {
+static const struct kobj_type irq_kobj_type = {
 	.release	= irq_kobj_release,
 };
 
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 7d4fc6479062..f34760a1e222 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -1147,7 +1147,8 @@ struct irq_domain *irq_domain_create_hierarchy(struct irq_domain *parent,
 		domain = __irq_domain_create(fwnode, 0, ~0, 0, ops, host_data);
 
 	if (domain) {
-		domain->root = parent->root;
+		if (parent)
+			domain->root = parent->root;
 		domain->parent = parent;
 		domain->flags |= flags;
 
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index d0f0389920c1..7a97bcb086bf 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -830,11 +830,8 @@ static struct irq_domain *__msi_create_irq_domain(struct fwnode_handle *fwnode,
 	domain = irq_domain_create_hierarchy(parent, flags | IRQ_DOMAIN_FLAG_MSI, 0,
 					     fwnode, &msi_domain_ops, info);
 
-	if (domain) {
-		if (!domain->name && info->chip)
-			domain->name = info->chip->name;
+	if (domain)
 		irq_domain_update_bus_token(domain, info->bus_token);
-	}
 
 	return domain;
 }
@@ -1084,10 +1081,13 @@ int msi_domain_populate_irqs(struct irq_domain *domain, struct device *dev,
 	struct xarray *xa;
 	int ret, virq;
 
-	if (!msi_ctrl_valid(dev, &ctrl))
-		return -EINVAL;
-
 	msi_lock_descs(dev);
+
+	if (!msi_ctrl_valid(dev, &ctrl)) {
+		ret = -EINVAL;
+		goto unlock;
+	}
+
 	ret = msi_domain_add_simple_msi_descs(dev, &ctrl);
 	if (ret)
 		goto unlock;
@@ -1109,14 +1109,35 @@ int msi_domain_populate_irqs(struct irq_domain *domain, struct device *dev,
 	return 0;
 
 fail:
-	for (--virq; virq >= virq_base; virq--)
+	for (--virq; virq >= virq_base; virq--) {
+		msi_domain_depopulate_descs(dev, virq, 1);
 		irq_domain_free_irqs_common(domain, virq, 1);
+	}
 	msi_domain_free_descs(dev, &ctrl);
 unlock:
 	msi_unlock_descs(dev);
 	return ret;
 }
 
+void msi_domain_depopulate_descs(struct device *dev, int virq_base, int nvec)
+{
+	struct msi_ctrl ctrl = {
+		.domid	= MSI_DEFAULT_DOMAIN,
+		.first  = virq_base,
+		.last	= virq_base + nvec - 1,
+	};
+	struct msi_desc *desc;
+	struct xarray *xa;
+	unsigned long idx;
+
+	if (!msi_ctrl_valid(dev, &ctrl))
+		return;
+
+	xa = &dev->msi.data->__domains[ctrl.domid].store;
+	xa_for_each_range(xa, idx, desc, ctrl.first, ctrl.last)
+		desc->irq = 0;
+}
+
 /*
  * Carefully check whether the device can use reservation mode. If
  * reservation mode is enabled then the early activation will assign a
diff --git a/kernel/panic.c b/kernel/panic.c
index 487f5b03bf83..5cfea8302d23 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -212,9 +212,6 @@ static void panic_print_sys_info(bool console_flush)
 		return;
 	}
 
-	if (panic_print & PANIC_PRINT_ALL_CPU_BT)
-		trigger_all_cpu_backtrace();
-
 	if (panic_print & PANIC_PRINT_TASK_INFO)
 		show_state();
 
@@ -244,6 +241,30 @@ void check_panic_on_warn(const char *origin)
 		      origin, limit);
 }
 
+/*
+ * Helper that triggers the NMI backtrace (if set in panic_print)
+ * and then performs the secondary CPUs shutdown - we cannot have
+ * the NMI backtrace after the CPUs are off!
+ */
+static void panic_other_cpus_shutdown(bool crash_kexec)
+{
+	if (panic_print & PANIC_PRINT_ALL_CPU_BT)
+		trigger_all_cpu_backtrace();
+
+	/*
+	 * Note that smp_send_stop() is the usual SMP shutdown function,
+	 * which unfortunately may not be hardened to work in a panic
+	 * situation. If we want to do crash dump after notifier calls
+	 * and kmsg_dump, we will need architecture dependent extra
+	 * bits in addition to stopping other CPUs, hence we rely on
+	 * crash_smp_send_stop() for that.
+	 */
+	if (!crash_kexec)
+		smp_send_stop();
+	else
+		crash_smp_send_stop();
+}
+
 /**
  *	panic - halt the system
  *	@fmt: The text string to print
@@ -334,23 +355,10 @@ void panic(const char *fmt, ...)
 	 *
 	 * Bypass the panic_cpu check and call __crash_kexec directly.
 	 */
-	if (!_crash_kexec_post_notifiers) {
+	if (!_crash_kexec_post_notifiers)
 		__crash_kexec(NULL);
 
-		/*
-		 * Note smp_send_stop is the usual smp shutdown function, which
-		 * unfortunately means it may not be hardened to work in a
-		 * panic situation.
-		 */
-		smp_send_stop();
-	} else {
-		/*
-		 * If we want to do crash dump after notifier calls and
-		 * kmsg_dump, we will need architecture dependent extra
-		 * works in addition to stopping other CPUs.
-		 */
-		crash_smp_send_stop();
-	}
+	panic_other_cpus_shutdown(_crash_kexec_post_notifiers);
 
 	/*
 	 * Run any panic handlers, including those that might need to
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 5c840151f3bb..e3211455b203 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -546,7 +546,7 @@ static void sugov_tunables_free(struct kobject *kobj)
 	kfree(to_sugov_tunables(attr_set));
 }
 
-static struct kobj_type sugov_tunables_ktype = {
+static const struct kobj_type sugov_tunables_ktype = {
 	.default_groups = sugov_groups,
 	.sysfs_ops = &governor_sysfs_ops,
 	.release = &sugov_tunables_free,
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 5743be559415..d5d94510afd3 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -729,14 +729,10 @@ EXPORT_SYMBOL_GPL(blk_trace_startstop);
  **/
 int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
 {
-	struct request_queue *q;
+	struct request_queue *q = bdev_get_queue(bdev);
 	int ret, start = 0;
 	char b[BDEVNAME_SIZE];
 
-	q = bdev_get_queue(bdev);
-	if (!q)
-		return -ENXIO;
-
 	mutex_lock(&q->debugfs_mutex);
 
 	switch (cmd) {
diff --git a/kernel/umh.c b/kernel/umh.c
index fbf872c624cb..60aa9e764a38 100644
--- a/kernel/umh.c
+++ b/kernel/umh.c
@@ -32,9 +32,6 @@
 
 #include <trace/events/module.h>
 
-#define CAP_BSET	(void *)1
-#define CAP_PI		(void *)2
-
 static kernel_cap_t usermodehelper_bset = CAP_FULL_SET;
 static kernel_cap_t usermodehelper_inheritable = CAP_FULL_SET;
 static DEFINE_SPINLOCK(umh_sysctl_lock);
@@ -501,9 +498,9 @@ static int proc_cap_handler(struct ctl_table *table, int write,
 			 void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct ctl_table t;
-	unsigned long cap_array[_KERNEL_CAPABILITY_U32S];
-	kernel_cap_t new_cap;
-	int err, i;
+	unsigned long cap_array[2];
+	kernel_cap_t new_cap, *cap;
+	int err;
 
 	if (write && (!capable(CAP_SETPCAP) ||
 		      !capable(CAP_SYS_MODULE)))
@@ -512,16 +509,13 @@ static int proc_cap_handler(struct ctl_table *table, int write,
 	/*
 	 * convert from the global kernel_cap_t to the ulong array to print to
 	 * userspace if this is a read.
+	 *
+	 * Legacy format: capabilities are exposed as two 32-bit values
 	 */
+	cap = table->data;
 	spin_lock(&umh_sysctl_lock);
-	for (i = 0; i < _KERNEL_CAPABILITY_U32S; i++)  {
-		if (table->data == CAP_BSET)
-			cap_array[i] = usermodehelper_bset.cap[i];
-		else if (table->data == CAP_PI)
-			cap_array[i] = usermodehelper_inheritable.cap[i];
-		else
-			BUG();
-	}
+	cap_array[0] = (u32) cap->val;
+	cap_array[1] = cap->val >> 32;
 	spin_unlock(&umh_sysctl_lock);
 
 	t = *table;
@@ -535,22 +529,15 @@ static int proc_cap_handler(struct ctl_table *table, int write,
 	if (err < 0)
 		return err;
 
-	/*
-	 * convert from the sysctl array of ulongs to the kernel_cap_t
-	 * internal representation
-	 */
-	for (i = 0; i < _KERNEL_CAPABILITY_U32S; i++)
-		new_cap.cap[i] = cap_array[i];
+	new_cap.val = (u32)cap_array[0];
+	new_cap.val += (u64)cap_array[1] << 32;
 
 	/*
 	 * Drop everything not in the new_cap (but don't add things)
 	 */
 	if (write) {
 		spin_lock(&umh_sysctl_lock);
-		if (table->data == CAP_BSET)
-			usermodehelper_bset = cap_intersect(usermodehelper_bset, new_cap);
-		if (table->data == CAP_PI)
-			usermodehelper_inheritable = cap_intersect(usermodehelper_inheritable, new_cap);
+		*cap = cap_intersect(*cap, new_cap);
 		spin_unlock(&umh_sysctl_lock);
 	}
 
@@ -560,15 +547,15 @@ static int proc_cap_handler(struct ctl_table *table, int write,
 struct ctl_table usermodehelper_table[] = {
 	{
 		.procname	= "bset",
-		.data		= CAP_BSET,
-		.maxlen		= _KERNEL_CAPABILITY_U32S * sizeof(unsigned long),
+		.data		= &usermodehelper_bset,
+		.maxlen		= 2 * sizeof(unsigned long),
 		.mode		= 0600,
 		.proc_handler	= proc_cap_handler,
 	},
 	{
 		.procname	= "inheritable",
-		.data		= CAP_PI,
-		.maxlen		= _KERNEL_CAPABILITY_U32S * sizeof(unsigned long),
+		.data		= &usermodehelper_inheritable,
+		.maxlen		= 2 * sizeof(unsigned long),
 		.mode		= 0600,
 		.proc_handler	= proc_cap_handler,
 	},