This is the 5.4.142 stable release

-----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCAAdFiEEZH8oZUiU471FcZm+ONu9yGCSaT4FAmEcr3MACgkQONu9yGCS
 aT6eag//f6COc7PQMKCJU7hcw0Xe4pIPmUUj+EpkwztzfX45dCzWxbhHxRiOqtKa
 ReSUXZ8mJLzYJgyHRr6FfsUqENWzKGqHby15yZ2h0rEyJns/V054NiBjz1aWoQZ4
 axpF1SYaLfLglfobslLc/3+JbyTfxBK/+m6XnZRJXqMMFnJ+hljJJxXuCryEQnU6
 KtAlrS2ITpbEyAECAE02oErxGDGCnTDzGpQvlSeJWqJVlisrsGIvGowjFliy6ONf
 YDjsejKlNUlQwnplXErefuXf7uhT/36sN0DnxCy5yXJ8SJwnzja3eYDz1yG9apG0
 ZR7KM3dN3L8viuRx2GEOubh8EMbirErD9DrhaPyaNhEPKHI2cHxHdG2prj5WkBzZ
 OjXcW32FDWzw6/kfnHEOBl0OrmhsEIY1/pP8jegape8lDrj/szN0ViJe0rzElba1
 6pb0D/ASFPYtYwR1O2/qZiPqqzHQEAFfDyDMKEKzogbNAHUbfvaE6g3qYafwQgS6
 o+g/BBxtrGNaIWtMtQ75aeoqFA4mkE9MrLJ1SzEFpw/PvHCHtFItCyEcUwaNvEz8
 OdwceDSIkT4Bn0GzEwuxKxcFyZ1R3rIABPIUGbid8Q3w6ZgM/vr2BPR3vkUY0zl+
 g9DPae9S4K8A+kYGwyeYzZ0dPC6otb8h01RtiGJyQgyiPAeTutk=
 =QJcB
 -----END PGP SIGNATURE-----

Merge 5.4.142 into android11-5.4-lts

Changes in 5.4.142
	iio: adc: ti-ads7950: Ensure CS is deasserted after reading channels
	iio: humidity: hdc100x: Add margin to the conversion time
	iio: adc: Fix incorrect exit of for-loop
	ASoC: xilinx: Fix reference to PCM buffer address
	ASoC: intel: atom: Fix reference to PCM buffer address
	i2c: dev: zero out array used for i2c reads from userspace
	ceph: reduce contention in ceph_check_delayed_caps()
	ACPI: NFIT: Fix support for virtual SPA ranges
	libnvdimm/region: Fix label activation vs errors
	ieee802154: hwsim: fix GPF in hwsim_set_edge_lqi
	ieee802154: hwsim: fix GPF in hwsim_new_edge_nl
	ASoC: cs42l42: Correct definition of ADC Volume control
	ASoC: cs42l42: Don't allow SND_SOC_DAIFMT_LEFT_J
	ASoC: cs42l42: Fix inversion of ADC Notch Switch control
	ASoC: cs42l42: Remove duplicate control for WNF filter frequency
	netfilter: nf_conntrack_bridge: Fix memory leak when error
	ASoC: cs42l42: Fix LRCLK frame start edge
	net: dsa: mt7530: add the missing RxUnicast MIB counter
	platform/x86: pcengines-apuv2: revert wiring up simswitch GPIO as LED
	platform/x86: pcengines-apuv2: Add missing terminating entries to gpio-lookup tables
	net: phy: micrel: Fix link detection on ksz87xx switch"
	ppp: Fix generating ifname when empty IFLA_IFNAME is specified
	net: sched: act_mirred: Reset ct info when mirror/redirect skb
	iavf: Set RSS LUT and key in reset handle path
	psample: Add a fwd declaration for skbuff
	net/mlx5: Fix return value from tracer initialization
	drm/meson: fix colour distortion from HDR set during vendor u-boot
	net: dsa: microchip: Fix ksz_read64()
	net: Fix memory leak in ieee802154_raw_deliver
	net: igmp: fix data-race in igmp_ifc_timer_expire()
	net: dsa: lan9303: fix broken backpressure in .port_fdb_dump
	net: dsa: lantiq: fix broken backpressure in .port_fdb_dump
	net: dsa: sja1105: fix broken backpressure in .port_fdb_dump
	net: bridge: fix memleak in br_add_if()
	net: linkwatch: fix failure to restore device state across suspend/resume
	tcp_bbr: fix u32 wrap bug in round logic if bbr_init() called after 2B packets
	net: igmp: increase size of mr_ifc_count
	xen/events: Fix race in set_evtchn_to_irq
	vsock/virtio: avoid potential deadlock when vsock device remove
	nbd: Aovid double completion of a request
	powerpc/kprobes: Fix kprobe Oops happens in booke
	x86/tools: Fix objdump version check again
	genirq: Provide IRQCHIP_AFFINITY_PRE_STARTUP
	x86/msi: Force affinity setup before startup
	x86/ioapic: Force affinity setup before startup
	x86/resctrl: Fix default monitoring groups reporting
	genirq/msi: Ensure deactivation on teardown
	genirq/timings: Prevent potential array overflow in __irq_timings_store()
	PCI/MSI: Enable and mask MSI-X early
	PCI/MSI: Mask all unused MSI-X entries
	PCI/MSI: Enforce that MSI-X table entry is masked for update
	PCI/MSI: Enforce MSI[X] entry updates to be visible
	PCI/MSI: Do not set invalid bits in MSI mask
	PCI/MSI: Correct misleading comments
	PCI/MSI: Use msi_mask_irq() in pci_msi_shutdown()
	PCI/MSI: Protect msi_desc::masked for multi-MSI
	KVM: VMX: Use current VMCS to query WAITPKG support for MSR emulation
	ceph: add some lockdep assertions around snaprealm handling
	ceph: clean up locking annotation for ceph_get_snap_realm and __lookup_snap_realm
	ceph: take snap_empty_lock atomically with snaprealm refcount change
	vmlinux.lds.h: Handle clang's module.{c,d}tor sections
	iommu/vt-d: Fix agaw for a supported 48 bit guest address width
	KVM: nSVM: avoid picking up unsupported bits from L2 in int_ctl (CVE-2021-3653)
	KVM: nSVM: always intercept VMLOAD/VMSAVE when nested (CVE-2021-3656)
	Linux 5.4.142

Signed-off-by: Greg Kroah-Hartman <[email protected]>
Change-Id: I7df2f917694a7f6d1eefb220b57271612b026443

fs/ceph/caps.c

@@ -4053,12 +4053,20 @@ bad:
 
 /*
  * Delayed work handler to process end of delayed cap release LRU list.
+ *
+ * If new caps are added to the list while processing it, these won't get
+ * processed in this run.  In this case, the ci->i_hold_caps_max will be
+ * returned so that the work can be scheduled accordingly.
  */
-void ceph_check_delayed_caps(struct ceph_mds_client *mdsc)
+unsigned long ceph_check_delayed_caps(struct ceph_mds_client *mdsc)
 {
 	struct inode *inode;
 	struct ceph_inode_info *ci;
 	int flags = CHECK_CAPS_NODELAY;
+	struct ceph_mount_options *opt = mdsc->fsc->mount_options;
+	unsigned long delay_max = opt->caps_wanted_delay_max * HZ;
+	unsigned long loop_start = jiffies;
+	unsigned long delay = 0;
 
 	dout("check_delayed_caps\n");
 	while (1) {
@@ -4068,6 +4076,11 @@ void ceph_check_delayed_caps(struct ceph_mds_client *mdsc)
 		ci = list_first_entry(&mdsc->cap_delay_list,
 				      struct ceph_inode_info,
 				      i_cap_delay_list);
+		if (time_before(loop_start, ci->i_hold_caps_max - delay_max)) {
+			dout("%s caps added recently.  Exiting loop", __func__);
+			delay = ci->i_hold_caps_max;
+			break;
+		}
 		if ((ci->i_ceph_flags & CEPH_I_FLUSH) == 0 &&
 		    time_before(jiffies, ci->i_hold_caps_max))
 			break;
@@ -4084,6 +4097,8 @@ void ceph_check_delayed_caps(struct ceph_mds_client *mdsc)
 		}
 	}
 	spin_unlock(&mdsc->cap_delay_lock);
+
+	return delay;
 }
 
 /*

fs/ceph/mds_client.c

@@ -4049,22 +4049,29 @@ static void maybe_recover_session(struct ceph_mds_client *mdsc)
 }
 
 /*
- * delayed work -- periodically trim expired leases, renew caps with mds
+ * delayed work -- periodically trim expired leases, renew caps with mds.  If
+ * the @delay parameter is set to 0 or if it's more than 5 secs, the default
+ * workqueue delay value of 5 secs will be used.
  */
-static void schedule_delayed(struct ceph_mds_client *mdsc)
+static void schedule_delayed(struct ceph_mds_client *mdsc, unsigned long delay)
 {
-	int delay = 5;
-	unsigned hz = round_jiffies_relative(HZ * delay);
-	schedule_delayed_work(&mdsc->delayed_work, hz);
+	unsigned long max_delay = HZ * 5;
+
+	/* 5 secs default delay */
+	if (!delay || (delay > max_delay))
+		delay = max_delay;
+	schedule_delayed_work(&mdsc->delayed_work,
+			      round_jiffies_relative(delay));
 }
 
 static void delayed_work(struct work_struct *work)
 {
-	int i;
 	struct ceph_mds_client *mdsc =
 		container_of(work, struct ceph_mds_client, delayed_work.work);
+	unsigned long delay;
 	int renew_interval;
 	int renew_caps;
+	int i;
 
 	dout("mdsc delayed_work\n");
 
@@ -4119,7 +4126,7 @@ static void delayed_work(struct work_struct *work)
 	}
 	mutex_unlock(&mdsc->mutex);
 
-	ceph_check_delayed_caps(mdsc);
+	delay = ceph_check_delayed_caps(mdsc);
 
 	ceph_queue_cap_reclaim_work(mdsc);
 
@@ -4127,7 +4134,7 @@ static void delayed_work(struct work_struct *work)
 
 	maybe_recover_session(mdsc);
 
-	schedule_delayed(mdsc);
+	schedule_delayed(mdsc, delay);
 }
 
 int ceph_mdsc_init(struct ceph_fs_client *fsc)
@@ -4600,7 +4607,7 @@ void ceph_mdsc_handle_mdsmap(struct ceph_mds_client *mdsc, struct ceph_msg *msg)
 			  mdsc->mdsmap->m_epoch);
 
 	mutex_unlock(&mdsc->mutex);
-	schedule_delayed(mdsc);
+	schedule_delayed(mdsc, 0);
 	return;
 
 bad_unlock:

fs/ceph/snap.c

@@ -60,24 +60,26 @@
 /*
  * increase ref count for the realm
  *
- * caller must hold snap_rwsem for write.
+ * caller must hold snap_rwsem.
  */
 void ceph_get_snap_realm(struct ceph_mds_client *mdsc,
 			 struct ceph_snap_realm *realm)
 {
-	dout("get_realm %p %d -> %d\n", realm,
-	     atomic_read(&realm->nref), atomic_read(&realm->nref)+1);
+	lockdep_assert_held(&mdsc->snap_rwsem);
+
 	/*
-	 * since we _only_ increment realm refs or empty the empty
-	 * list with snap_rwsem held, adjusting the empty list here is
-	 * safe.  we do need to protect against concurrent empty list
-	 * additions, however.
+	 * The 0->1 and 1->0 transitions must take the snap_empty_lock
+	 * atomically with the refcount change. Go ahead and bump the
+	 * nref here, unless it's 0, in which case we take the spinlock
+	 * and then do the increment and remove it from the list.
 	 */
-	if (atomic_inc_return(&realm->nref) == 1) {
-		spin_lock(&mdsc->snap_empty_lock);
+	if (atomic_inc_not_zero(&realm->nref))
+		return;
+
+	spin_lock(&mdsc->snap_empty_lock);
+	if (atomic_inc_return(&realm->nref) == 1)
 		list_del_init(&realm->empty_item);
-		spin_unlock(&mdsc->snap_empty_lock);
-	}
+	spin_unlock(&mdsc->snap_empty_lock);
 }
 
 static void __insert_snap_realm(struct rb_root *root,
@@ -113,6 +115,8 @@ static struct ceph_snap_realm *ceph_create_snap_realm(
 {
 	struct ceph_snap_realm *realm;
 
+	lockdep_assert_held_write(&mdsc->snap_rwsem);
+
 	realm = kzalloc(sizeof(*realm), GFP_NOFS);
 	if (!realm)
 		return ERR_PTR(-ENOMEM);
@@ -135,7 +139,7 @@ static struct ceph_snap_realm *ceph_create_snap_realm(
 /*
  * lookup the realm rooted at @ino.
  *
- * caller must hold snap_rwsem for write.
+ * caller must hold snap_rwsem.
  */
 static struct ceph_snap_realm *__lookup_snap_realm(struct ceph_mds_client *mdsc,
 						   u64 ino)
@@ -143,6 +147,8 @@ static struct ceph_snap_realm *__lookup_snap_realm(struct ceph_mds_client *mdsc,
 	struct rb_node *n = mdsc->snap_realms.rb_node;
 	struct ceph_snap_realm *r;
 
+	lockdep_assert_held(&mdsc->snap_rwsem);
+
 	while (n) {
 		r = rb_entry(n, struct ceph_snap_realm, node);
 		if (ino < r->ino)
@@ -176,6 +182,8 @@ static void __put_snap_realm(struct ceph_mds_client *mdsc,
 static void __destroy_snap_realm(struct ceph_mds_client *mdsc,
 				 struct ceph_snap_realm *realm)
 {
+	lockdep_assert_held_write(&mdsc->snap_rwsem);
+
 	dout("__destroy_snap_realm %p %llx\n", realm, realm->ino);
 
 	rb_erase(&realm->node, &mdsc->snap_realms);
@@ -198,28 +206,30 @@ static void __destroy_snap_realm(struct ceph_mds_client *mdsc,
 static void __put_snap_realm(struct ceph_mds_client *mdsc,
 			     struct ceph_snap_realm *realm)
 {
-	dout("__put_snap_realm %llx %p %d -> %d\n", realm->ino, realm,
-	     atomic_read(&realm->nref), atomic_read(&realm->nref)-1);
+	lockdep_assert_held_write(&mdsc->snap_rwsem);
+
+	/*
+	 * We do not require the snap_empty_lock here, as any caller that
+	 * increments the value must hold the snap_rwsem.
+	 */
 	if (atomic_dec_and_test(&realm->nref))
 		__destroy_snap_realm(mdsc, realm);
 }
 
 /*
- * caller needn't hold any locks
+ * See comments in ceph_get_snap_realm. Caller needn't hold any locks.
  */
 void ceph_put_snap_realm(struct ceph_mds_client *mdsc,
 			 struct ceph_snap_realm *realm)
 {
-	dout("put_snap_realm %llx %p %d -> %d\n", realm->ino, realm,
-	     atomic_read(&realm->nref), atomic_read(&realm->nref)-1);
-	if (!atomic_dec_and_test(&realm->nref))
+	if (!atomic_dec_and_lock(&realm->nref, &mdsc->snap_empty_lock))
 		return;
 
 	if (down_write_trylock(&mdsc->snap_rwsem)) {
+		spin_unlock(&mdsc->snap_empty_lock);
 		__destroy_snap_realm(mdsc, realm);
 		up_write(&mdsc->snap_rwsem);
 	} else {
-		spin_lock(&mdsc->snap_empty_lock);
 		list_add(&realm->empty_item, &mdsc->snap_empty);
 		spin_unlock(&mdsc->snap_empty_lock);
 	}
@@ -236,6 +246,8 @@ static void __cleanup_empty_realms(struct ceph_mds_client *mdsc)
 {
 	struct ceph_snap_realm *realm;
 
+	lockdep_assert_held_write(&mdsc->snap_rwsem);
+
 	spin_lock(&mdsc->snap_empty_lock);
 	while (!list_empty(&mdsc->snap_empty)) {
 		realm = list_first_entry(&mdsc->snap_empty,
@@ -269,6 +281,8 @@ static int adjust_snap_realm_parent(struct ceph_mds_client *mdsc,
 {
 	struct ceph_snap_realm *parent;
 
+	lockdep_assert_held_write(&mdsc->snap_rwsem);
+
 	if (realm->parent_ino == parentino)
 		return 0;
 
@@ -686,6 +700,8 @@ int ceph_update_snap_trace(struct ceph_mds_client *mdsc,
 	int err = -ENOMEM;
 	LIST_HEAD(dirty_realms);
 
+	lockdep_assert_held_write(&mdsc->snap_rwsem);
+
 	dout("update_snap_trace deletion=%d\n", deletion);
 more:
 	ceph_decode_need(&p, e, sizeof(*ri), bad);

fs/ceph/super.h

@@ -1064,7 +1064,7 @@ extern void ceph_flush_snaps(struct ceph_inode_info *ci,
 extern bool __ceph_should_report_size(struct ceph_inode_info *ci);
 extern void ceph_check_caps(struct ceph_inode_info *ci, int flags,
 			    struct ceph_mds_session *session);
-extern void ceph_check_delayed_caps(struct ceph_mds_client *mdsc);
+extern unsigned long ceph_check_delayed_caps(struct ceph_mds_client *mdsc);
 extern void ceph_flush_dirty_caps(struct ceph_mds_client *mdsc);
 extern int  ceph_drop_caps_for_unlink(struct inode *inode);
 extern int ceph_encode_inode_release(void **p, struct inode *inode,