Import of kernel-6.12.0-55.28.1.el10_0

Makefile.rhelver

@@ -12,7 +12,7 @@ RHEL_MINOR = 0
 #
 # Use this spot to avoid future merge conflicts.
 # Do not trim this comment.
-RHEL_RELEASE = 55.27.1
+RHEL_RELEASE = 55.28.1
 
 #
 # RHEL_REBASE_NUM

arch/powerpc/platforms/book3s/vas-api.c

@@ -464,7 +464,43 @@ static vm_fault_t vas_mmap_fault(struct vm_fault *vmf)
 	return VM_FAULT_SIGBUS;
 }
 
+/*
+ * During mmap() paste address, mapping VMA is saved in VAS window
+ * struct which is used to unmap during migration if the window is
+ * still open. But the user space can remove this mapping with
+ * munmap() before closing the window and the VMA address will
+ * be invalid. Set VAS window VMA to NULL in this function which
+ * is called before VMA free.
+ */
+static void vas_mmap_close(struct vm_area_struct *vma)
+{
+	struct file *fp = vma->vm_file;
+	struct coproc_instance *cp_inst = fp->private_data;
+	struct vas_window *txwin;
+
+	/* Should not happen */
+	if (!cp_inst || !cp_inst->txwin) {
+		pr_err("No attached VAS window for the paste address mmap\n");
+		return;
+	}
+
+	txwin = cp_inst->txwin;
+	/*
+	 * task_ref.vma is set in coproc_mmap() during mmap paste
+	 * address. So it has to be the same VMA that is getting freed.
+	 */
+	if (WARN_ON(txwin->task_ref.vma != vma)) {
+		pr_err("Invalid paste address mmaping\n");
+		return;
+	}
+
+	mutex_lock(&txwin->task_ref.mmap_mutex);
+	txwin->task_ref.vma = NULL;
+	mutex_unlock(&txwin->task_ref.mmap_mutex);
+}
+
 static const struct vm_operations_struct vas_vm_ops = {
+	.close = vas_mmap_close,
 	.fault = vas_mmap_fault,
 };
 

arch/s390/kernel/topology.c

@@ -555,6 +555,16 @@ static void __init alloc_masks(struct sysinfo_15_1_x *info,
 	}
 }
 
+static int __init detect_polarization(union topology_entry *tle)
+{
+	struct topology_core *tl_core;
+
+	while (tle->nl)
+		tle = next_tle(tle);
+	tl_core = (struct topology_core *)tle;
+	return tl_core->pp != POLARIZATION_HRZ;
+}
+
 void __init topology_init_early(void)
 {
 	struct sysinfo_15_1_x *info;
@@ -574,6 +584,7 @@ void __init topology_init_early(void)
 		      __func__, PAGE_SIZE, PAGE_SIZE);
 	info = tl_info;
 	store_topology(info);
+	cpu_management = detect_polarization(info->tle);
 	pr_info("The CPU configuration topology of the machine is: %d %d %d %d %d %d / %d\n",
 		info->mag[0], info->mag[1], info->mag[2], info->mag[3],
 		info->mag[4], info->mag[5], info->mnest);

arch/s390/pci/pci.c

@@ -44,6 +44,7 @@
 /* list of all detected zpci devices */
 static LIST_HEAD(zpci_list);
 static DEFINE_SPINLOCK(zpci_list_lock);
+static DEFINE_MUTEX(zpci_add_remove_lock);
 
 static DECLARE_BITMAP(zpci_domain, ZPCI_DOMAIN_BITMAP_SIZE);
 static DEFINE_SPINLOCK(zpci_domain_lock);
@@ -69,6 +70,15 @@ EXPORT_SYMBOL_GPL(zpci_aipb);
 struct airq_iv *zpci_aif_sbv;
 EXPORT_SYMBOL_GPL(zpci_aif_sbv);
 
+void zpci_zdev_put(struct zpci_dev *zdev)
+{
+	if (!zdev)
+		return;
+	mutex_lock(&zpci_add_remove_lock);
+	kref_put_lock(&zdev->kref, zpci_release_device, &zpci_list_lock);
+	mutex_unlock(&zpci_add_remove_lock);
+}
+
 struct zpci_dev *get_zdev_by_fid(u32 fid)
 {
 	struct zpci_dev *tmp, *zdev = NULL;
@@ -831,6 +841,7 @@ int zpci_add_device(struct zpci_dev *zdev)
 {
 	int rc;
 
+	mutex_lock(&zpci_add_remove_lock);
 	zpci_dbg(1, "add fid:%x, fh:%x, c:%d\n", zdev->fid, zdev->fh, zdev->state);
 	rc = zpci_init_iommu(zdev);
 	if (rc)
@@ -844,12 +855,14 @@ int zpci_add_device(struct zpci_dev *zdev)
 	spin_lock(&zpci_list_lock);
 	list_add_tail(&zdev->entry, &zpci_list);
 	spin_unlock(&zpci_list_lock);
+	mutex_unlock(&zpci_add_remove_lock);
 	return 0;
 
 error_destroy_iommu:
 	zpci_destroy_iommu(zdev);
 error:
 	zpci_dbg(0, "add fid:%x, rc:%d\n", zdev->fid, rc);
+	mutex_unlock(&zpci_add_remove_lock);
 	return rc;
 }
 
@@ -919,60 +932,44 @@ int zpci_deconfigure_device(struct zpci_dev *zdev)
  * @zdev: the zpci_dev that was reserved
  *
  * Handle the case that a given zPCI function was reserved by another system.
- * After a call to this function the zpci_dev can not be found via
- * get_zdev_by_fid() anymore but may still be accessible via existing
- * references though it will not be functional anymore.
  */
 void zpci_device_reserved(struct zpci_dev *zdev)
 {
-	/*
-	 * Remove device from zpci_list as it is going away. This also
-	 * makes sure we ignore subsequent zPCI events for this device.
-	 */
-	spin_lock(&zpci_list_lock);
-	list_del(&zdev->entry);
-	spin_unlock(&zpci_list_lock);
+	lockdep_assert_held(&zdev->state_lock);
+	/* We may declare the device reserved multiple times */
+	if (zdev->state == ZPCI_FN_STATE_RESERVED)
+		return;
 	zdev->state = ZPCI_FN_STATE_RESERVED;
 	zpci_dbg(3, "rsv fid:%x\n", zdev->fid);
+	/*
+	 * The underlying device is gone. Allow the zdev to be freed
+	 * as soon as all other references are gone by accounting for
+	 * the removal as a dropped reference.
+	 */
 	zpci_zdev_put(zdev);
 }
 
 void zpci_release_device(struct kref *kref)
 {
 	struct zpci_dev *zdev = container_of(kref, struct zpci_dev, kref);
-	int ret;
+
+	lockdep_assert_held(&zpci_add_remove_lock);
+	WARN_ON(zdev->state != ZPCI_FN_STATE_RESERVED);
+	/*
+	 * We already hold zpci_list_lock thanks to kref_put_lock().
+	 * This makes sure no new reference can be taken from the list.
+	 */
+	list_del(&zdev->entry);
+	spin_unlock(&zpci_list_lock);
 
 	if (zdev->has_hp_slot)
 		zpci_exit_slot(zdev);
 
-	if (zdev->zbus->bus)
-		zpci_bus_remove_device(zdev, false);
+	if (zdev->has_resources)
+		zpci_cleanup_bus_resources(zdev);
 
-	if (zdev_enabled(zdev))
-		zpci_disable_device(zdev);
-
-	switch (zdev->state) {
-	case ZPCI_FN_STATE_CONFIGURED:
-		ret = sclp_pci_deconfigure(zdev->fid);
-		zpci_dbg(3, "deconf fid:%x, rc:%d\n", zdev->fid, ret);
-		fallthrough;
-	case ZPCI_FN_STATE_STANDBY:
-		if (zdev->has_hp_slot)
-			zpci_exit_slot(zdev);
-		spin_lock(&zpci_list_lock);
-		list_del(&zdev->entry);
-		spin_unlock(&zpci_list_lock);
-		zpci_dbg(3, "rsv fid:%x\n", zdev->fid);
-		fallthrough;
-	case ZPCI_FN_STATE_RESERVED:
-		if (zdev->has_resources)
-			zpci_cleanup_bus_resources(zdev);
-		zpci_bus_device_unregister(zdev);
-		zpci_destroy_iommu(zdev);
-		fallthrough;
-	default:
-		break;
-	}
+	zpci_bus_device_unregister(zdev);
+	zpci_destroy_iommu(zdev);
 	zpci_dbg(3, "rem fid:%x\n", zdev->fid);
 	kfree_rcu(zdev, rcu);
 }

arch/s390/pci/pci_bus.h

@@ -17,11 +17,8 @@ int zpci_bus_scan_device(struct zpci_dev *zdev);
 void zpci_bus_remove_device(struct zpci_dev *zdev, bool set_error);
 
 void zpci_release_device(struct kref *kref);
-static inline void zpci_zdev_put(struct zpci_dev *zdev)
-{
-	if (zdev)
-		kref_put(&zdev->kref, zpci_release_device);
-}
+
+void zpci_zdev_put(struct zpci_dev *zdev);
 
 static inline void zpci_zdev_get(struct zpci_dev *zdev)
 {

arch/s390/pci/pci_clp.c

@@ -423,6 +423,8 @@ static void __clp_add(struct clp_fh_list_entry *entry, void *data)
 		return;
 	}
 	zdev = zpci_create_device(entry->fid, entry->fh, entry->config_state);
+	if (IS_ERR(zdev))
+		return;
 	list_add_tail(&zdev->entry, scan_list);
 }
 

arch/s390/pci/pci_event.c

@@ -335,6 +335,22 @@ static void zpci_event_hard_deconfigured(struct zpci_dev *zdev, u32 fh)
 	zdev->state = ZPCI_FN_STATE_STANDBY;
 }
 
+static void zpci_event_reappear(struct zpci_dev *zdev)
+{
+	lockdep_assert_held(&zdev->state_lock);
+	/*
+	 * The zdev is in the reserved state. This means that it was presumed to
+	 * go away but there are still undropped references. Now, the platform
+	 * announced its availability again. Bring back the lingering zdev
+	 * to standby. This is safe because we hold a temporary reference
+	 * now so that it won't go away. Account for the re-appearance of the
+	 * underlying device by incrementing the reference count.
+	 */
+	zdev->state = ZPCI_FN_STATE_STANDBY;
+	zpci_zdev_get(zdev);
+	zpci_dbg(1, "rea fid:%x, fh:%x\n", zdev->fid, zdev->fh);
+}
+
 static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
 {
 	struct zpci_dev *zdev = get_zdev_by_fid(ccdf->fid);
@@ -358,8 +374,10 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
 				break;
 			}
 		} else {
+			if (zdev->state == ZPCI_FN_STATE_RESERVED)
+				zpci_event_reappear(zdev);
 			/* the configuration request may be stale */
-			if (zdev->state != ZPCI_FN_STATE_STANDBY)
+			else if (zdev->state != ZPCI_FN_STATE_STANDBY)
 				break;
 			zdev->state = ZPCI_FN_STATE_CONFIGURED;
 		}
@@ -375,6 +393,8 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
 				break;
 			}
 		} else {
+			if (zdev->state == ZPCI_FN_STATE_RESERVED)
+				zpci_event_reappear(zdev);
 			zpci_update_fh(zdev, ccdf->fh);
 		}
 		break;

drivers/i2c/busses/i2c-designware-master.c

@@ -345,6 +345,7 @@ static int amd_i2c_dw_xfer_quirk(struct i2c_adapter *adap, struct i2c_msg *msgs,
 
 	dev->msgs = msgs;
 	dev->msgs_num = num_msgs;
+	dev->msg_write_idx = 0;
 	i2c_dw_xfer_init(dev);
 
 	/* Initiate messages read/write transaction */

drivers/pci/hotplug/s390_pci_hpc.c

@@ -59,16 +59,15 @@ static int disable_slot(struct hotplug_slot *hotplug_slot)
 
 	pdev = pci_get_slot(zdev->zbus->bus, zdev->devfn);
 	if (pdev && pci_num_vf(pdev)) {
-		pci_dev_put(pdev);
 		rc = -EBUSY;
 		goto out;
 	}
 
 	rc = zpci_deconfigure_device(zdev);
 out:
-	mutex_unlock(&zdev->state_lock);
 	if (pdev)
 		pci_dev_put(pdev);
+	mutex_unlock(&zdev->state_lock);
 	return rc;
 }
 

include/net/bluetooth/hci_core.h

@@ -29,6 +29,7 @@
 #include <linux/idr.h>
 #include <linux/leds.h>
 #include <linux/rculist.h>
+#include <linux/srcu.h>
 
 #include <net/bluetooth/hci.h>
 #include <net/bluetooth/hci_sync.h>
@@ -338,6 +339,7 @@ struct adv_monitor {
 
 struct hci_dev {
 	struct list_head list;
+	struct srcu_struct srcu;
 	struct mutex	lock;
 
 	struct ida	unset_handle_ida;

net/bluetooth/hci_core.c

@@ -63,7 +63,7 @@ static DEFINE_IDA(hci_index_ida);
 
 /* Get HCI device by index.
  * Device is held on return. */
-struct hci_dev *hci_dev_get(int index)
+static struct hci_dev *__hci_dev_get(int index, int *srcu_index)
 {
 	struct hci_dev *hdev = NULL, *d;
 
@@ -76,6 +76,8 @@ struct hci_dev *hci_dev_get(int index)
 	list_for_each_entry(d, &hci_dev_list, list) {
 		if (d->id == index) {
 			hdev = hci_dev_hold(d);
+			if (srcu_index)
+				*srcu_index = srcu_read_lock(&d->srcu);
 			break;
 		}
 	}
@@ -83,6 +85,22 @@ struct hci_dev *hci_dev_get(int index)
 	return hdev;
 }
 
+struct hci_dev *hci_dev_get(int index)
+{
+	return __hci_dev_get(index, NULL);
+}
+
+static struct hci_dev *hci_dev_get_srcu(int index, int *srcu_index)
+{
+	return __hci_dev_get(index, srcu_index);
+}
+
+static void hci_dev_put_srcu(struct hci_dev *hdev, int srcu_index)
+{
+	srcu_read_unlock(&hdev->srcu, srcu_index);
+	hci_dev_put(hdev);
+}
+
 /* ---- Inquiry support ---- */
 
 bool hci_discovery_active(struct hci_dev *hdev)
@@ -567,9 +585,9 @@ static int hci_dev_do_reset(struct hci_dev *hdev)
 int hci_dev_reset(__u16 dev)
 {
 	struct hci_dev *hdev;
-	int err;
+	int err, srcu_index;
 
-	hdev = hci_dev_get(dev);
+	hdev = hci_dev_get_srcu(dev, &srcu_index);
 	if (!hdev)
 		return -ENODEV;
 
@@ -591,7 +609,7 @@ int hci_dev_reset(__u16 dev)
 	err = hci_dev_do_reset(hdev);
 
 done:
-	hci_dev_put(hdev);
+	hci_dev_put_srcu(hdev, srcu_index);
 	return err;
 }
 
@@ -2440,6 +2458,11 @@ struct hci_dev *hci_alloc_dev_priv(int sizeof_priv)
 	if (!hdev)
 		return NULL;
 
+	if (init_srcu_struct(&hdev->srcu)) {
+		kfree(hdev);
+		return NULL;
+	}
+
 	hdev->pkt_type  = (HCI_DM1 | HCI_DH1 | HCI_HV1);
 	hdev->esco_type = (ESCO_HV1);
 	hdev->link_mode = (HCI_LM_ACCEPT);
@@ -2684,6 +2707,9 @@ void hci_unregister_dev(struct hci_dev *hdev)
 	list_del(&hdev->list);
 	write_unlock(&hci_dev_list_lock);
 
+	synchronize_srcu(&hdev->srcu);
+	cleanup_srcu_struct(&hdev->srcu);
+
 	disable_work_sync(&hdev->rx_work);
 	disable_work_sync(&hdev->cmd_work);
 	disable_work_sync(&hdev->tx_work);

net/bpf/test_run.c

@@ -660,12 +660,9 @@ static void *bpf_test_init(const union bpf_attr *kattr, u32 user_size,
 	void __user *data_in = u64_to_user_ptr(kattr->test.data_in);
 	void *data;
 
-	if (size < ETH_HLEN || size > PAGE_SIZE - headroom - tailroom)
+	if (user_size < ETH_HLEN || user_size > PAGE_SIZE - headroom - tailroom)
 		return ERR_PTR(-EINVAL);
 
-	if (user_size > size)
-		return ERR_PTR(-EMSGSIZE);
-
 	size = SKB_DATA_ALIGN(size);
 	data = kzalloc(size + headroom + tailroom, GFP_USER);
 	if (!data)

net/ipv4/udp_offload.c

@@ -273,6 +273,7 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb,
 	bool copy_dtor;
 	__sum16 check;
 	__be16 newlen;
+	int ret = 0;
 
 	mss = skb_shinfo(gso_skb)->gso_size;
 	if (gso_skb->len <= sizeof(*uh) + mss)
@@ -301,6 +302,10 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb,
 		if (skb_pagelen(gso_skb) - sizeof(*uh) == skb_shinfo(gso_skb)->gso_size)
 			return __udp_gso_segment_list(gso_skb, features, is_ipv6);
 
+		ret = __skb_linearize(gso_skb);
+		if (ret)
+			return ERR_PTR(ret);
+
 		 /* Setup csum, as fraglist skips this in udp4_gro_receive. */
 		gso_skb->csum_start = skb_transport_header(gso_skb) - gso_skb->head;
 		gso_skb->csum_offset = offsetof(struct udphdr, check);

net/tls/tls_strp.c

@@ -511,9 +511,8 @@ static int tls_strp_read_sock(struct tls_strparser *strp)
 	if (inq < strp->stm.full_len)
 		return tls_strp_read_copy(strp, true);
 
+	tls_strp_load_anchor_with_queue(strp, inq);
 	if (!strp->stm.full_len) {
-		tls_strp_load_anchor_with_queue(strp, inq);
-
 		sz = tls_rx_msg_size(strp, strp->anchor);
 		if (sz < 0) {
 			tls_strp_abort_strp(strp, sz);

tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c

@@ -23,7 +23,7 @@ static void test_xdp_with_devmap_helpers(void)
 	__u32 len = sizeof(info);
 	int err, dm_fd, dm_fd_redir, map_fd;
 	struct nstoken *nstoken = NULL;
-	char data[10] = {};
+	char data[ETH_HLEN] = {};
 	__u32 idx = 0;
 
 	SYS(out_close, "ip netns add %s", TEST_NS);
@@ -58,7 +58,7 @@ static void test_xdp_with_devmap_helpers(void)
 	/* send a packet to trigger any potential bugs in there */
 	DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts,
 			    .data_in = &data,
-			    .data_size_in = 10,
+			    .data_size_in = sizeof(data),
 			    .flags = BPF_F_TEST_XDP_LIVE_FRAMES,
 			    .repeat = 1,
 		);
@@ -158,7 +158,7 @@ static void test_xdp_with_devmap_helpers_veth(void)
 	struct nstoken *nstoken = NULL;
 	__u32 len = sizeof(info);
 	int err, dm_fd, dm_fd_redir, map_fd, ifindex_dst;
-	char data[10] = {};
+	char data[ETH_HLEN] = {};
 	__u32 idx = 0;
 
 	SYS(out_close, "ip netns add %s", TEST_NS);
@@ -208,7 +208,7 @@ static void test_xdp_with_devmap_helpers_veth(void)
 	/* send a packet to trigger any potential bugs in there */
 	DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts,
 			    .data_in = &data,
-			    .data_size_in = 10,
+			    .data_size_in = sizeof(data),
 			    .flags = BPF_F_TEST_XDP_LIVE_FRAMES,
 			    .repeat = 1,
 		);

tools/testing/selftests/net/bpf_offload.py

@@ -207,9 +207,11 @@ def bpftool_prog_list_wait(expected=0, n_retry=20):
     raise Exception("Time out waiting for program counts to stabilize want %d, have %d" % (expected, nprogs))
 
 def bpftool_map_list_wait(expected=0, n_retry=20, ns=""):
+    nmaps = None
     for i in range(n_retry):
         maps = bpftool_map_list(ns=ns)
-        if len(maps) == expected:
+        nmaps = len(maps)
+        if nmaps == expected:
             return maps
         time.sleep(0.05)
     raise Exception("Time out waiting for map counts to stabilize want %d, have %d" % (expected, nmaps))
@@ -594,8 +596,9 @@ def check_extack_nsim(output, reference, args):
     check_extack(output, "netdevsim: " + reference, args)
 
 def check_no_extack(res, needle):
-    fail((res[1] + res[2]).count(needle) or (res[1] + res[2]).count("Warning:"),
-         "Found '%s' in command output, leaky extack?" % (needle))
+    haystack = (res[1] + res[2]).strip()
+    fail(haystack.count(needle) or haystack.count("Warning:"),
+         "Unexpected command output, leaky extack? ('%s', '%s')" % (needle, haystack))
 
 def check_verifier_log(output, reference):
     lines = output.split("\n")
@@ -707,6 +710,7 @@ _, base_maps = bpftool("map")
 base_map_names = [
     'pid_iter.rodata', # created on each bpftool invocation
     'libbpf_det_bind', # created on each bpftool invocation
+    'libbpf_global',
 ]
 
 # Check netdevsim