diff --git a/Makefile b/Makefile
index b3ac049..364ddbd 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 5
 PATCHLEVEL = 4
-SUBLEVEL = 95
+SUBLEVEL = 96
 EXTRAVERSION =
 NAME = Kleptomaniac Octopus
 
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 51d867c..6c295a2 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -247,11 +247,11 @@
 
 
 /*
- * The linear kernel range starts at the bottom of the virtual address
- * space. Testing the top bit for the start of the region is a
- * sufficient check and avoids having to worry about the tag.
+ * Check whether an arbitrary address is within the linear map, which
+ * lives in the [PAGE_OFFSET, PAGE_END) interval at the bottom of the
+ * kernel's TTBR1 address range.
  */
-#define __is_lm_address(addr)	(!(((u64)addr) & BIT(vabits_actual - 1)))
+#define __is_lm_address(addr)	(((u64)(addr) ^ PAGE_OFFSET) < (PAGE_END - PAGE_OFFSET))
 
 #define __lm_to_phys(addr)	(((addr) & ~PAGE_OFFSET) + PHYS_OFFSET)
 #define __kimg_to_phys(addr)	((addr) - kimage_voffset)
@@ -332,7 +332,7 @@
 #endif /* !CONFIG_SPARSEMEM_VMEMMAP || CONFIG_DEBUG_VIRTUAL */
 
 #define virt_addr_valid(addr)	({					\
-	__typeof__(addr) __addr = addr;					\
+	__typeof__(addr) __addr = __tag_reset(addr);			\
 	__is_lm_address(__addr) && pfn_valid(virt_to_pfn(__addr));	\
 })
 
diff --git a/arch/arm64/mm/physaddr.c b/arch/arm64/mm/physaddr.c
index 67a9ba9..cde44c1 100644
--- a/arch/arm64/mm/physaddr.c
+++ b/arch/arm64/mm/physaddr.c
@@ -9,7 +9,7 @@
 
 phys_addr_t __virt_to_phys(unsigned long x)
 {
-	WARN(!__is_lm_address(x),
+	WARN(!__is_lm_address(__tag_reset(x)),
 	     "virt_to_phys used for non-linear address: %pK (%pS)\n",
 	      (void *)x,
 	      (void *)x);
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index 86f20d5..b40d029 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -88,7 +88,7 @@
  * think of extending them - you will be slapped with a stinking trout or a frozen
  * shark will reach you, wherever you are! You've been warned.
  */
-static inline unsigned long long notrace __rdmsr(unsigned int msr)
+static __always_inline unsigned long long __rdmsr(unsigned int msr)
 {
 	DECLARE_ARGS(val, low, high);
 
@@ -100,7 +100,7 @@
 	return EAX_EDX_VAL(val, low, high);
 }
 
-static inline void notrace __wrmsr(unsigned int msr, u32 low, u32 high)
+static __always_inline void __wrmsr(unsigned int msr, u32 low, u32 high)
 {
 	asm volatile("1: wrmsr\n"
 		     "2:\n"
diff --git a/block/blk-core.c b/block/blk-core.c
index d221322..5808baa 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -886,11 +886,14 @@
 	}
 
 	/*
-	 * For a REQ_NOWAIT based request, return -EOPNOTSUPP
-	 * if queue is not a request based queue.
+	 * Non-mq queues do not honor REQ_NOWAIT, so complete a bio
+	 * with BLK_STS_AGAIN status in order to catch -EAGAIN and
+	 * to give a chance to the caller to repeat request gracefully.
 	 */
-	if ((bio->bi_opf & REQ_NOWAIT) && !queue_is_mq(q))
-		goto not_supported;
+	if ((bio->bi_opf & REQ_NOWAIT) && !queue_is_mq(q)) {
+		status = BLK_STS_AGAIN;
+		goto end_io;
+	}
 
 	if (should_fail_bio(bio))
 		goto end_io;
diff --git a/drivers/acpi/thermal.c b/drivers/acpi/thermal.c
index d831a61..383c702 100644
--- a/drivers/acpi/thermal.c
+++ b/drivers/acpi/thermal.c
@@ -174,6 +174,8 @@
 	int tz_enabled;
 	int kelvin_offset;
 	struct work_struct thermal_check_work;
+	struct mutex thermal_check_lock;
+	refcount_t thermal_check_count;
 };
 
 /* --------------------------------------------------------------------------
@@ -494,17 +496,6 @@
 	return 0;
 }
 
-static void acpi_thermal_check(void *data)
-{
-	struct acpi_thermal *tz = data;
-
-	if (!tz->tz_enabled)
-		return;
-
-	thermal_zone_device_update(tz->thermal_zone,
-				   THERMAL_EVENT_UNSPECIFIED);
-}
-
 /* sys I/F for generic thermal sysfs support */
 
 static int thermal_get_temp(struct thermal_zone_device *thermal, int *temp)
@@ -538,6 +529,8 @@
 	return 0;
 }
 
+static void acpi_thermal_check_fn(struct work_struct *work);
+
 static int thermal_set_mode(struct thermal_zone_device *thermal,
 				enum thermal_device_mode mode)
 {
@@ -563,7 +556,7 @@
 		ACPI_DEBUG_PRINT((ACPI_DB_INFO,
 			"%s kernel ACPI thermal control\n",
 			tz->tz_enabled ? "Enable" : "Disable"));
-		acpi_thermal_check(tz);
+		acpi_thermal_check_fn(&tz->thermal_check_work);
 	}
 	return 0;
 }
@@ -932,6 +925,12 @@
                                  Driver Interface
    -------------------------------------------------------------------------- */
 
+static void acpi_queue_thermal_check(struct acpi_thermal *tz)
+{
+	if (!work_pending(&tz->thermal_check_work))
+		queue_work(acpi_thermal_pm_queue, &tz->thermal_check_work);
+}
+
 static void acpi_thermal_notify(struct acpi_device *device, u32 event)
 {
 	struct acpi_thermal *tz = acpi_driver_data(device);
@@ -942,17 +941,17 @@
 
 	switch (event) {
 	case ACPI_THERMAL_NOTIFY_TEMPERATURE:
-		acpi_thermal_check(tz);
+		acpi_queue_thermal_check(tz);
 		break;
 	case ACPI_THERMAL_NOTIFY_THRESHOLDS:
 		acpi_thermal_trips_update(tz, ACPI_TRIPS_REFRESH_THRESHOLDS);
-		acpi_thermal_check(tz);
+		acpi_queue_thermal_check(tz);
 		acpi_bus_generate_netlink_event(device->pnp.device_class,
 						  dev_name(&device->dev), event, 0);
 		break;
 	case ACPI_THERMAL_NOTIFY_DEVICES:
 		acpi_thermal_trips_update(tz, ACPI_TRIPS_REFRESH_DEVICES);
-		acpi_thermal_check(tz);
+		acpi_queue_thermal_check(tz);
 		acpi_bus_generate_netlink_event(device->pnp.device_class,
 						  dev_name(&device->dev), event, 0);
 		break;
@@ -1052,7 +1051,27 @@
 {
 	struct acpi_thermal *tz = container_of(work, struct acpi_thermal,
 					       thermal_check_work);
-	acpi_thermal_check(tz);
+
+	if (!tz->tz_enabled)
+		return;
+	/*
+	 * In general, it is not sufficient to check the pending bit, because
+	 * subsequent instances of this function may be queued after one of them
+	 * has started running (e.g. if _TMP sleeps).  Avoid bailing out if just
+	 * one of them is running, though, because it may have done the actual
+	 * check some time ago, so allow at least one of them to block on the
+	 * mutex while another one is running the update.
+	 */
+	if (!refcount_dec_not_one(&tz->thermal_check_count))
+		return;
+
+	mutex_lock(&tz->thermal_check_lock);
+
+	thermal_zone_device_update(tz->thermal_zone, THERMAL_EVENT_UNSPECIFIED);
+
+	refcount_inc(&tz->thermal_check_count);
+
+	mutex_unlock(&tz->thermal_check_lock);
 }
 
 static int acpi_thermal_add(struct acpi_device *device)
@@ -1084,6 +1103,8 @@
 	if (result)
 		goto free_memory;
 
+	refcount_set(&tz->thermal_check_count, 3);
+	mutex_init(&tz->thermal_check_lock);
 	INIT_WORK(&tz->thermal_check_work, acpi_thermal_check_fn);
 
 	pr_info(PREFIX "%s [%s] (%ld C)\n", acpi_device_name(device),
@@ -1149,7 +1170,7 @@
 		tz->state.active |= tz->trips.active[i].flags.enabled;
 	}
 
-	queue_work(acpi_thermal_pm_queue, &tz->thermal_check_work);
+	acpi_queue_thermal_check(tz);
 
 	return AE_OK;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
index 959eb07..c18f392 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
@@ -1914,6 +1914,9 @@
 			initial_link_setting;
 	uint32_t link_bw;
 
+	if (req_bw > dc_link_bandwidth_kbps(link, &link->verified_link_cap))
+		return false;
+
 	/* search for the minimum link setting that:
 	 * 1. is supported according to the link training result
 	 * 2. could support the b/w requested by the timing
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
index bb7add5e..a6d5bea 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
@@ -257,7 +257,7 @@
 	.num_banks = 8,
 	.num_chans = 4,
 	.vmm_page_size_bytes = 4096,
-	.dram_clock_change_latency_us = 23.84,
+	.dram_clock_change_latency_us = 11.72,
 	.return_bus_width_bytes = 64,
 	.dispclk_dppclk_vco_speed_mhz = 3600,
 	.xfc_bus_transport_time_us = 4,
diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index b16aea0..6dd29ba 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -421,15 +421,19 @@
 	/* Find our integrated MDIO bus node */
 	dn = of_find_compatible_node(NULL, NULL, "brcm,unimac-mdio");
 	priv->master_mii_bus = of_mdio_find_bus(dn);
-	if (!priv->master_mii_bus)
+	if (!priv->master_mii_bus) {
+		of_node_put(dn);
 		return -EPROBE_DEFER;
+	}
 
 	get_device(&priv->master_mii_bus->dev);
 	priv->master_mii_dn = dn;
 
 	priv->slave_mii_bus = devm_mdiobus_alloc(ds->dev);
-	if (!priv->slave_mii_bus)
+	if (!priv->slave_mii_bus) {
+		of_node_put(dn);
 		return -ENOMEM;
+	}
 
 	priv->slave_mii_bus->priv = priv;
 	priv->slave_mii_bus->name = "sf2 slave mii";
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 9040340..c3079f4 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -4752,6 +4752,12 @@
 	while (!done) {
 		/* Pull all the valid messages off the CRQ */
 		while ((crq = ibmvnic_next_crq(adapter)) != NULL) {
+			/* This barrier makes sure ibmvnic_next_crq()'s
+			 * crq->generic.first & IBMVNIC_CRQ_CMD_RSP is loaded
+			 * before ibmvnic_handle_crq()'s
+			 * switch(gen_crq->first) and switch(gen_crq->cmd).
+			 */
+			dma_rmb();
 			ibmvnic_handle_crq(crq, adapter);
 			crq->generic.first = 0;
 		}
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 7a96427..c2cabd7 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1295,8 +1295,21 @@
 	}
 
 	length = (io.nblocks + 1) << ns->lba_shift;
-	meta_len = (io.nblocks + 1) * ns->ms;
-	metadata = nvme_to_user_ptr(io.metadata);
+
+	if ((io.control & NVME_RW_PRINFO_PRACT) &&
+	    ns->ms == sizeof(struct t10_pi_tuple)) {
+		/*
+		 * Protection information is stripped/inserted by the
+		 * controller.
+		 */
+		if (nvme_to_user_ptr(io.metadata))
+			return -EINVAL;
+		meta_len = 0;
+		metadata = NULL;
+	} else {
+		meta_len = (io.nblocks + 1) * ns->ms;
+		metadata = nvme_to_user_ptr(io.metadata);
+	}
 
 	if (ns->ext) {
 		length += meta_len;
diff --git a/drivers/phy/motorola/phy-cpcap-usb.c b/drivers/phy/motorola/phy-cpcap-usb.c
index 5baf64d..1bebad3 100644
--- a/drivers/phy/motorola/phy-cpcap-usb.c
+++ b/drivers/phy/motorola/phy-cpcap-usb.c
@@ -625,35 +625,42 @@
 	generic_phy = devm_phy_create(ddata->dev, NULL, &ops);
 	if (IS_ERR(generic_phy)) {
 		error = PTR_ERR(generic_phy);
-		return PTR_ERR(generic_phy);
+		goto out_reg_disable;
 	}
 
 	phy_set_drvdata(generic_phy, ddata);
 
 	phy_provider = devm_of_phy_provider_register(ddata->dev,
 						     of_phy_simple_xlate);
-	if (IS_ERR(phy_provider))
-		return PTR_ERR(phy_provider);
+	if (IS_ERR(phy_provider)) {
+		error = PTR_ERR(phy_provider);
+		goto out_reg_disable;
+	}
 
 	error = cpcap_usb_init_optional_pins(ddata);
 	if (error)
-		return error;
+		goto out_reg_disable;
 
 	cpcap_usb_init_optional_gpios(ddata);
 
 	error = cpcap_usb_init_iio(ddata);
 	if (error)
-		return error;
+		goto out_reg_disable;
 
 	error = cpcap_usb_init_interrupts(pdev, ddata);
 	if (error)
-		return error;
+		goto out_reg_disable;
 
 	usb_add_phy_dev(&ddata->phy);
 	atomic_set(&ddata->active, 1);
 	schedule_delayed_work(&ddata->detect_work, msecs_to_jiffies(1));
 
 	return 0;
+
+out_reg_disable:
+	regulator_disable(ddata->vusb);
+
+	return error;
 }
 
 static int cpcap_usb_phy_remove(struct platform_device *pdev)
diff --git a/drivers/platform/x86/intel-vbtn.c b/drivers/platform/x86/intel-vbtn.c
index 37035dc..d4fc2cb 100644
--- a/drivers/platform/x86/intel-vbtn.c
+++ b/drivers/platform/x86/intel-vbtn.c
@@ -203,6 +203,12 @@
 			DMI_MATCH(DMI_PRODUCT_NAME, "Switch SA5-271"),
 		},
 	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 7352"),
+		},
+	},
 	{} /* Array terminator */
 };
 
diff --git a/drivers/platform/x86/touchscreen_dmi.c b/drivers/platform/x86/touchscreen_dmi.c
index 1e072db..7ed1189 100644
--- a/drivers/platform/x86/touchscreen_dmi.c
+++ b/drivers/platform/x86/touchscreen_dmi.c
@@ -231,6 +231,16 @@
 	.properties	= digma_citi_e200_props,
 };
 
+static const struct property_entry estar_beauty_hd_props[] = {
+	PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"),
+	{ }
+};
+
+static const struct ts_dmi_data estar_beauty_hd_data = {
+	.acpi_name	= "GDIX1001:00",
+	.properties	= estar_beauty_hd_props,
+};
+
 static const struct property_entry gp_electronic_t701_props[] = {
 	PROPERTY_ENTRY_U32("touchscreen-size-x", 960),
 	PROPERTY_ENTRY_U32("touchscreen-size-y", 640),
@@ -748,6 +758,14 @@
 		},
 	},
 	{
+		/* Estar Beauty HD (MID 7316R) */
+		.driver_data = (void *)&estar_beauty_hd_data,
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Estar"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "eSTAR BEAUTY HD Intel Quad core"),
+		},
+	},
+	{
 		/* GP-electronic T701 */
 		.driver_data = (void *)&gp_electronic_t701_data,
 		.matches = {
diff --git a/drivers/scsi/fnic/vnic_dev.c b/drivers/scsi/fnic/vnic_dev.c
index 522636e..c8bf8c7 100644
--- a/drivers/scsi/fnic/vnic_dev.c
+++ b/drivers/scsi/fnic/vnic_dev.c
@@ -444,7 +444,8 @@
 	fetch_index = ioread32(&vdev->devcmd2->wq.ctrl->fetch_index);
 	if (fetch_index == 0xFFFFFFFF) { /* check for hardware gone  */
 		pr_err("error in devcmd2 init");
-		return -ENODEV;
+		err = -ENODEV;
+		goto err_free_wq;
 	}
 
 	/*
@@ -460,7 +461,7 @@
 	err = vnic_dev_alloc_desc_ring(vdev, &vdev->devcmd2->results_ring,
 			DEVCMD2_RING_SIZE, DEVCMD2_DESC_SIZE);
 	if (err)
-		goto err_free_wq;
+		goto err_disable_wq;
 
 	vdev->devcmd2->result =
 		(struct devcmd2_result *) vdev->devcmd2->results_ring.descs;
@@ -481,8 +482,9 @@
 
 err_free_desc_ring:
 	vnic_dev_free_desc_ring(vdev, &vdev->devcmd2->results_ring);
-err_free_wq:
+err_disable_wq:
 	vnic_wq_disable(&vdev->devcmd2->wq);
+err_free_wq:
 	vnic_wq_free(&vdev->devcmd2->wq);
 err_free_devcmd2:
 	kfree(vdev->devcmd2);
diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c
index 8a76284..523809a 100644
--- a/drivers/scsi/ibmvscsi/ibmvfc.c
+++ b/drivers/scsi/ibmvscsi/ibmvfc.c
@@ -2881,8 +2881,10 @@
 	unsigned long flags = 0;
 
 	spin_lock_irqsave(shost->host_lock, flags);
-	if (sdev->type == TYPE_DISK)
+	if (sdev->type == TYPE_DISK) {
 		sdev->allow_restart = 1;
+		blk_queue_rq_timeout(sdev->request_queue, 120 * HZ);
+	}
 	spin_unlock_irqrestore(shost->host_lock, flags);
 	return 0;
 }
diff --git a/drivers/scsi/libfc/fc_exch.c b/drivers/scsi/libfc/fc_exch.c
index 52e8666..e5b18e5 100644
--- a/drivers/scsi/libfc/fc_exch.c
+++ b/drivers/scsi/libfc/fc_exch.c
@@ -1619,8 +1619,13 @@
 		rc = fc_exch_done_locked(ep);
 		WARN_ON(fc_seq_exch(sp) != ep);
 		spin_unlock_bh(&ep->ex_lock);
-		if (!rc)
+		if (!rc) {
 			fc_exch_delete(ep);
+		} else {
+			FC_EXCH_DBG(ep, "ep is completed already,"
+					"hence skip calling the resp\n");
+			goto skip_resp;
+		}
 	}
 
 	/*
@@ -1639,6 +1644,7 @@
 	if (!fc_invoke_resp(ep, sp, fp))
 		fc_frame_free(fp);
 
+skip_resp:
 	fc_exch_release(ep);
 	return;
 rel:
@@ -1895,10 +1901,16 @@
 
 	fc_exch_hold(ep);
 
-	if (!rc)
+	if (!rc) {
 		fc_exch_delete(ep);
+	} else {
+		FC_EXCH_DBG(ep, "ep is completed already,"
+				"hence skip calling the resp\n");
+		goto skip_resp;
+	}
 
 	fc_invoke_resp(ep, sp, ERR_PTR(-FC_EX_CLOSED));
+skip_resp:
 	fc_seq_set_resp(sp, NULL, ep->arg);
 	fc_exch_release(ep);
 }
diff --git a/drivers/scsi/scsi_transport_srp.c b/drivers/scsi/scsi_transport_srp.c
index d4d1104..8cd0a87 100644
--- a/drivers/scsi/scsi_transport_srp.c
+++ b/drivers/scsi/scsi_transport_srp.c
@@ -541,7 +541,14 @@
 	res = mutex_lock_interruptible(&rport->mutex);
 	if (res)
 		goto out;
-	scsi_target_block(&shost->shost_gendev);
+	if (rport->state != SRP_RPORT_FAIL_FAST)
+		/*
+		 * sdev state must be SDEV_TRANSPORT_OFFLINE, transition
+		 * to SDEV_BLOCK is illegal. Calling scsi_target_unblock()
+		 * later is ok though, scsi_internal_device_unblock_nowait()
+		 * treats SDEV_TRANSPORT_OFFLINE like SDEV_BLOCK.
+		 */
+		scsi_target_block(&shost->shost_gendev);
 	res = rport->state != SRP_RPORT_LOST ? i->f->reconnect(rport) : -ENODEV;
 	pr_debug("%s (state %d): transport.reconnect() returned %d\n",
 		 dev_name(&shost->shost_gendev), rport->state, res);
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 86e280e..7f644a5 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -347,33 +347,10 @@
 		return -ENOMEM;
 
 	ref->root_id = root_id;
-	if (key) {
+	if (key)
 		ref->key_for_search = *key;
-		/*
-		 * We can often find data backrefs with an offset that is too
-		 * large (>= LLONG_MAX, maximum allowed file offset) due to
-		 * underflows when subtracting a file's offset with the data
-		 * offset of its corresponding extent data item. This can
-		 * happen for example in the clone ioctl.
-		 * So if we detect such case we set the search key's offset to
-		 * zero to make sure we will find the matching file extent item
-		 * at add_all_parents(), otherwise we will miss it because the
-		 * offset taken form the backref is much larger then the offset
-		 * of the file extent item. This can make us scan a very large
-		 * number of file extent items, but at least it will not make
-		 * us miss any.
-		 * This is an ugly workaround for a behaviour that should have
-		 * never existed, but it does and a fix for the clone ioctl
-		 * would touch a lot of places, cause backwards incompatibility
-		 * and would not fix the problem for extents cloned with older
-		 * kernels.
-		 */
-		if (ref->key_for_search.type == BTRFS_EXTENT_DATA_KEY &&
-		    ref->key_for_search.offset >= LLONG_MAX)
-			ref->key_for_search.offset = 0;
-	} else {
+	else
 		memset(&ref->key_for_search, 0, sizeof(ref->key_for_search));
-	}
 
 	ref->inode_list = NULL;
 	ref->level = level;
@@ -409,10 +386,36 @@
 			      wanted_disk_byte, count, sc, gfp_mask);
 }
 
+static int is_shared_data_backref(struct preftrees *preftrees, u64 bytenr)
+{
+	struct rb_node **p = &preftrees->direct.root.rb_root.rb_node;
+	struct rb_node *parent = NULL;
+	struct prelim_ref *ref = NULL;
+	struct prelim_ref target = {0};
+	int result;
+
+	target.parent = bytenr;
+
+	while (*p) {
+		parent = *p;
+		ref = rb_entry(parent, struct prelim_ref, rbnode);
+		result = prelim_ref_compare(ref, &target);
+
+		if (result < 0)
+			p = &(*p)->rb_left;
+		else if (result > 0)
+			p = &(*p)->rb_right;
+		else
+			return 1;
+	}
+	return 0;
+}
+
 static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path,
-			   struct ulist *parents, struct prelim_ref *ref,
+			   struct ulist *parents,
+			   struct preftrees *preftrees, struct prelim_ref *ref,
 			   int level, u64 time_seq, const u64 *extent_item_pos,
-			   u64 total_refs, bool ignore_offset)
+			   bool ignore_offset)
 {
 	int ret = 0;
 	int slot;
@@ -424,6 +427,7 @@
 	u64 disk_byte;
 	u64 wanted_disk_byte = ref->wanted_disk_byte;
 	u64 count = 0;
+	u64 data_offset;
 
 	if (level != 0) {
 		eb = path->nodes[level];
@@ -434,18 +438,26 @@
 	}
 
 	/*
-	 * We normally enter this function with the path already pointing to
-	 * the first item to check. But sometimes, we may enter it with
-	 * slot==nritems. In that case, go to the next leaf before we continue.
+	 * 1. We normally enter this function with the path already pointing to
+	 *    the first item to check. But sometimes, we may enter it with
+	 *    slot == nritems.
+	 * 2. We are searching for normal backref but bytenr of this leaf
+	 *    matches shared data backref
+	 * 3. The leaf owner is not equal to the root we are searching
+	 *
+	 * For these cases, go to the next leaf before we continue.
 	 */
-	if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) {
+	eb = path->nodes[0];
+	if (path->slots[0] >= btrfs_header_nritems(eb) ||
+	    is_shared_data_backref(preftrees, eb->start) ||
+	    ref->root_id != btrfs_header_owner(eb)) {
 		if (time_seq == SEQ_LAST)
 			ret = btrfs_next_leaf(root, path);
 		else
 			ret = btrfs_next_old_leaf(root, path, time_seq);
 	}
 
-	while (!ret && count < total_refs) {
+	while (!ret && count < ref->count) {
 		eb = path->nodes[0];
 		slot = path->slots[0];
 
@@ -455,13 +467,31 @@
 		    key.type != BTRFS_EXTENT_DATA_KEY)
 			break;
 
+		/*
+		 * We are searching for normal backref but bytenr of this leaf
+		 * matches shared data backref, OR
+		 * the leaf owner is not equal to the root we are searching for
+		 */
+		if (slot == 0 &&
+		    (is_shared_data_backref(preftrees, eb->start) ||
+		     ref->root_id != btrfs_header_owner(eb))) {
+			if (time_seq == SEQ_LAST)
+				ret = btrfs_next_leaf(root, path);
+			else
+				ret = btrfs_next_old_leaf(root, path, time_seq);
+			continue;
+		}
 		fi = btrfs_item_ptr(eb, slot, struct btrfs_file_extent_item);
 		disk_byte = btrfs_file_extent_disk_bytenr(eb, fi);
+		data_offset = btrfs_file_extent_offset(eb, fi);
 
 		if (disk_byte == wanted_disk_byte) {
 			eie = NULL;
 			old = NULL;
-			count++;
+			if (ref->key_for_search.offset == key.offset - data_offset)
+				count++;
+			else
+				goto next;
 			if (extent_item_pos) {
 				ret = check_extent_in_eb(&key, eb, fi,
 						*extent_item_pos,
@@ -502,9 +532,9 @@
  */
 static int resolve_indirect_ref(struct btrfs_fs_info *fs_info,
 				struct btrfs_path *path, u64 time_seq,
+				struct preftrees *preftrees,
 				struct prelim_ref *ref, struct ulist *parents,
-				const u64 *extent_item_pos, u64 total_refs,
-				bool ignore_offset)
+				const u64 *extent_item_pos, bool ignore_offset)
 {
 	struct btrfs_root *root;
 	struct btrfs_key root_key;
@@ -513,6 +543,7 @@
 	int root_level;
 	int level = ref->level;
 	int index;
+	struct btrfs_key search_key = ref->key_for_search;
 
 	root_key.objectid = ref->root_id;
 	root_key.type = BTRFS_ROOT_ITEM_KEY;
@@ -545,13 +576,33 @@
 		goto out;
 	}
 
+	/*
+	 * We can often find data backrefs with an offset that is too large
+	 * (>= LLONG_MAX, maximum allowed file offset) due to underflows when
+	 * subtracting a file's offset with the data offset of its
+	 * corresponding extent data item. This can happen for example in the
+	 * clone ioctl.
+	 *
+	 * So if we detect such case we set the search key's offset to zero to
+	 * make sure we will find the matching file extent item at
+	 * add_all_parents(), otherwise we will miss it because the offset
+	 * taken form the backref is much larger then the offset of the file
+	 * extent item. This can make us scan a very large number of file
+	 * extent items, but at least it will not make us miss any.
+	 *
+	 * This is an ugly workaround for a behaviour that should have never
+	 * existed, but it does and a fix for the clone ioctl would touch a lot
+	 * of places, cause backwards incompatibility and would not fix the
+	 * problem for extents cloned with older kernels.
+	 */
+	if (search_key.type == BTRFS_EXTENT_DATA_KEY &&
+	    search_key.offset >= LLONG_MAX)
+		search_key.offset = 0;
 	path->lowest_level = level;
 	if (time_seq == SEQ_LAST)
-		ret = btrfs_search_slot(NULL, root, &ref->key_for_search, path,
-					0, 0);
+		ret = btrfs_search_slot(NULL, root, &search_key, path, 0, 0);
 	else
-		ret = btrfs_search_old_slot(root, &ref->key_for_search, path,
-					    time_seq);
+		ret = btrfs_search_old_slot(root, &search_key, path, time_seq);
 
 	/* root node has been locked, we can release @subvol_srcu safely here */
 	srcu_read_unlock(&fs_info->subvol_srcu, index);
@@ -574,8 +625,8 @@
 		eb = path->nodes[level];
 	}
 
-	ret = add_all_parents(root, path, parents, ref, level, time_seq,
-			      extent_item_pos, total_refs, ignore_offset);
+	ret = add_all_parents(root, path, parents, preftrees, ref, level,
+			      time_seq, extent_item_pos, ignore_offset);
 out:
 	path->lowest_level = 0;
 	btrfs_release_path(path);
@@ -609,7 +660,7 @@
 static int resolve_indirect_refs(struct btrfs_fs_info *fs_info,
 				 struct btrfs_path *path, u64 time_seq,
 				 struct preftrees *preftrees,
-				 const u64 *extent_item_pos, u64 total_refs,
+				 const u64 *extent_item_pos,
 				 struct share_check *sc, bool ignore_offset)
 {
 	int err;
@@ -653,9 +704,9 @@
 			ret = BACKREF_FOUND_SHARED;
 			goto out;
 		}
-		err = resolve_indirect_ref(fs_info, path, time_seq, ref,
-					   parents, extent_item_pos,
-					   total_refs, ignore_offset);
+		err = resolve_indirect_ref(fs_info, path, time_seq, preftrees,
+					   ref, parents, extent_item_pos,
+					   ignore_offset);
 		/*
 		 * we can only tolerate ENOENT,otherwise,we should catch error
 		 * and return directly.
@@ -758,8 +809,7 @@
  */
 static int add_delayed_refs(const struct btrfs_fs_info *fs_info,
 			    struct btrfs_delayed_ref_head *head, u64 seq,
-			    struct preftrees *preftrees, u64 *total_refs,
-			    struct share_check *sc)
+			    struct preftrees *preftrees, struct share_check *sc)
 {
 	struct btrfs_delayed_ref_node *node;
 	struct btrfs_delayed_extent_op *extent_op = head->extent_op;
@@ -793,7 +843,6 @@
 		default:
 			BUG();
 		}
-		*total_refs += count;
 		switch (node->type) {
 		case BTRFS_TREE_BLOCK_REF_KEY: {
 			/* NORMAL INDIRECT METADATA backref */
@@ -876,7 +925,7 @@
 static int add_inline_refs(const struct btrfs_fs_info *fs_info,
 			   struct btrfs_path *path, u64 bytenr,
 			   int *info_level, struct preftrees *preftrees,
-			   u64 *total_refs, struct share_check *sc)
+			   struct share_check *sc)
 {
 	int ret = 0;
 	int slot;
@@ -900,7 +949,6 @@
 
 	ei = btrfs_item_ptr(leaf, slot, struct btrfs_extent_item);
 	flags = btrfs_extent_flags(leaf, ei);
-	*total_refs += btrfs_extent_refs(leaf, ei);
 	btrfs_item_key_to_cpu(leaf, &found_key, slot);
 
 	ptr = (unsigned long)(ei + 1);
@@ -1125,8 +1173,6 @@
 	struct prelim_ref *ref;
 	struct rb_node *node;
 	struct extent_inode_elem *eie = NULL;
-	/* total of both direct AND indirect refs! */
-	u64 total_refs = 0;
 	struct preftrees preftrees = {
 		.direct = PREFTREE_INIT,
 		.indirect = PREFTREE_INIT,
@@ -1195,7 +1241,7 @@
 			}
 			spin_unlock(&delayed_refs->lock);
 			ret = add_delayed_refs(fs_info, head, time_seq,
-					       &preftrees, &total_refs, sc);
+					       &preftrees, sc);
 			mutex_unlock(&head->mutex);
 			if (ret)
 				goto out;
@@ -1216,8 +1262,7 @@
 		    (key.type == BTRFS_EXTENT_ITEM_KEY ||
 		     key.type == BTRFS_METADATA_ITEM_KEY)) {
 			ret = add_inline_refs(fs_info, path, bytenr,
-					      &info_level, &preftrees,
-					      &total_refs, sc);
+					      &info_level, &preftrees, sc);
 			if (ret)
 				goto out;
 			ret = add_keyed_refs(fs_info, path, bytenr, info_level,
@@ -1236,7 +1281,7 @@
 	WARN_ON(!RB_EMPTY_ROOT(&preftrees.indirect_missing_keys.root.rb_root));
 
 	ret = resolve_indirect_refs(fs_info, path, time_seq, &preftrees,
-				    extent_item_pos, total_refs, sc, ignore_offset);
+				    extent_item_pos, sc, ignore_offset);
 	if (ret)
 		goto out;
 
diff --git a/fs/udf/super.c b/fs/udf/super.c
index 4aba487..8bb001c 100644
--- a/fs/udf/super.c
+++ b/fs/udf/super.c
@@ -705,6 +705,7 @@
 	struct buffer_head *bh = NULL;
 	int nsr = 0;
 	struct udf_sb_info *sbi;
+	loff_t session_offset;
 
 	sbi = UDF_SB(sb);
 	if (sb->s_blocksize < sizeof(struct volStructDesc))
@@ -712,7 +713,8 @@
 	else
 		sectorsize = sb->s_blocksize;
 
-	sector += (((loff_t)sbi->s_session) << sb->s_blocksize_bits);
+	session_offset = (loff_t)sbi->s_session << sb->s_blocksize_bits;
+	sector += session_offset;
 
 	udf_debug("Starting at sector %u (%lu byte sectors)\n",
 		  (unsigned int)(sector >> sb->s_blocksize_bits),
@@ -757,8 +759,7 @@
 
 	if (nsr > 0)
 		return 1;
-	else if (!bh && sector - (sbi->s_session << sb->s_blocksize_bits) ==
-			VSD_FIRST_SECTOR_OFFSET)
+	else if (!bh && sector - session_offset == VSD_FIRST_SECTOR_OFFSET)
 		return -1;
 	else
 		return 0;
diff --git a/include/linux/kthread.h b/include/linux/kthread.h
index 0f9da96..c7108ce 100644
--- a/include/linux/kthread.h
+++ b/include/linux/kthread.h
@@ -31,6 +31,9 @@
 					  unsigned int cpu,
 					  const char *namefmt);
 
+void kthread_set_per_cpu(struct task_struct *k, int cpu);
+bool kthread_is_per_cpu(struct task_struct *k);
+
 /**
  * kthread_run - create and wake a thread.
  * @threadfn: the function to run until signal_pending(current).
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 4b38ba1..37b5145 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -619,6 +619,7 @@
 
 unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu);
 unsigned int tcp_current_mss(struct sock *sk);
+u32 tcp_clamp_probe0_to_user_timeout(const struct sock *sk, u32 when);
 
 /* Bound MSS / TSO packet size with the half of the window */
 static inline int tcp_bound_to_half_wnd(struct tcp_sock *tp, int pktsize)
diff --git a/kernel/kthread.c b/kernel/kthread.c
index e51f000..1d4c98a 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -469,11 +469,36 @@
 		return p;
 	kthread_bind(p, cpu);
 	/* CPU hotplug need to bind once again when unparking the thread. */
-	set_bit(KTHREAD_IS_PER_CPU, &to_kthread(p)->flags);
 	to_kthread(p)->cpu = cpu;
 	return p;
 }
 
+void kthread_set_per_cpu(struct task_struct *k, int cpu)
+{
+	struct kthread *kthread = to_kthread(k);
+	if (!kthread)
+		return;
+
+	WARN_ON_ONCE(!(k->flags & PF_NO_SETAFFINITY));
+
+	if (cpu < 0) {
+		clear_bit(KTHREAD_IS_PER_CPU, &kthread->flags);
+		return;
+	}
+
+	kthread->cpu = cpu;
+	set_bit(KTHREAD_IS_PER_CPU, &kthread->flags);
+}
+
+bool kthread_is_per_cpu(struct task_struct *k)
+{
+	struct kthread *kthread = to_kthread(k);
+	if (!kthread)
+		return false;
+
+	return test_bit(KTHREAD_IS_PER_CPU, &kthread->flags);
+}
+
 /**
  * kthread_unpark - unpark a thread created by kthread_create().
  * @k:		thread created by kthread_create().
diff --git a/kernel/smpboot.c b/kernel/smpboot.c
index 2efe1e2..f25208e8 100644
--- a/kernel/smpboot.c
+++ b/kernel/smpboot.c
@@ -188,6 +188,7 @@
 		kfree(td);
 		return PTR_ERR(tsk);
 	}
+	kthread_set_per_cpu(tsk, cpu);
 	/*
 	 * Park the thread so that it could start right on the CPU
 	 * when it is available.
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 28e5265..29c36c0 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1848,12 +1848,6 @@
 	mutex_lock(&wq_pool_attach_mutex);
 
 	/*
-	 * set_cpus_allowed_ptr() will fail if the cpumask doesn't have any
-	 * online CPUs.  It'll be re-applied when any of the CPUs come up.
-	 */
-	set_cpus_allowed_ptr(worker->task, pool->attrs->cpumask);
-
-	/*
 	 * The wq_pool_attach_mutex ensures %POOL_DISASSOCIATED remains
 	 * stable across this function.  See the comments above the flag
 	 * definition for details.
@@ -1861,6 +1855,9 @@
 	if (pool->flags & POOL_DISASSOCIATED)
 		worker->flags |= WORKER_UNBOUND;
 
+	if (worker->rescue_wq)
+		set_cpus_allowed_ptr(worker->task, pool->attrs->cpumask);
+
 	list_add_tail(&worker->node, &pool->workers);
 	worker->pool = pool;
 
diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c
index bfe7bdd..98c3967 100644
--- a/net/core/gen_estimator.c
+++ b/net/core/gen_estimator.c
@@ -80,11 +80,11 @@
 	u64 rate, brate;
 
 	est_fetch_counters(est, &b);
-	brate = (b.bytes - est->last_bytes) << (10 - est->ewma_log - est->intvl_log);
-	brate -= (est->avbps >> est->ewma_log);
+	brate = (b.bytes - est->last_bytes) << (10 - est->intvl_log);
+	brate = (brate >> est->ewma_log) - (est->avbps >> est->ewma_log);
 
-	rate = (u64)(b.packets - est->last_packets) << (10 - est->ewma_log - est->intvl_log);
-	rate -= (est->avpps >> est->ewma_log);
+	rate = (u64)(b.packets - est->last_packets) << (10 - est->intvl_log);
+	rate = (rate >> est->ewma_log) - (est->avpps >> est->ewma_log);
 
 	write_seqcount_begin(&est->seq);
 	est->avbps += brate;
@@ -143,6 +143,9 @@
 	if (parm->interval < -2 || parm->interval > 3)
 		return -EINVAL;
 
+	if (parm->ewma_log == 0 || parm->ewma_log >= 31)
+		return -EINVAL;
+
 	est = kzalloc(sizeof(*est), GFP_KERNEL);
 	if (!est)
 		return -ENOBUFS;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 26305aa..a1768de 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3295,6 +3295,7 @@
 	} else {
 		unsigned long when = tcp_probe0_when(sk, TCP_RTO_MAX);
 
+		when = tcp_clamp_probe0_to_user_timeout(sk, when);
 		tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0,
 				     when, TCP_RTO_MAX, NULL);
 	}
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 5da6ffc..d0774b4 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3850,6 +3850,8 @@
 		 */
 		timeout = TCP_RESOURCE_PROBE_INTERVAL;
 	}
+
+	timeout = tcp_clamp_probe0_to_user_timeout(sk, timeout);
 	tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0, timeout, TCP_RTO_MAX, NULL);
 }
 
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 7fcd116..fa2ae96 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -40,6 +40,24 @@
 	return min_t(u32, icsk->icsk_rto, msecs_to_jiffies(remaining));
 }
 
+u32 tcp_clamp_probe0_to_user_timeout(const struct sock *sk, u32 when)
+{
+	struct inet_connection_sock *icsk = inet_csk(sk);
+	u32 remaining;
+	s32 elapsed;
+
+	if (!icsk->icsk_user_timeout || !icsk->icsk_probes_tstamp)
+		return when;
+
+	elapsed = tcp_jiffies32 - icsk->icsk_probes_tstamp;
+	if (unlikely(elapsed < 0))
+		elapsed = 0;
+	remaining = msecs_to_jiffies(icsk->icsk_user_timeout) - elapsed;
+	remaining = max_t(u32, remaining, TCP_TIMEOUT_MIN);
+
+	return min_t(u32, remaining, when);
+}
+
 /**
  *  tcp_write_err() - close socket and save error info
  *  @sk:  The socket the error has appeared on.
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 3ab85e1..1a15e7b 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -4080,6 +4080,8 @@
 
 	rcu_read_lock();
 	key = rcu_dereference(sta->ptk[sta->ptk_idx]);
+	if (!key)
+		key = rcu_dereference(sdata->default_unicast_key);
 	if (key) {
 		switch (key->conf.cipher) {
 		case WLAN_CIPHER_SUITE_TKIP:
diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c
index 3a1d428..ea9ddea 100644
--- a/net/switchdev/switchdev.c
+++ b/net/switchdev/switchdev.c
@@ -461,10 +461,11 @@
 	extack = switchdev_notifier_info_to_extack(&port_obj_info->info);
 
 	if (check_cb(dev)) {
-		/* This flag is only checked if the return value is success. */
-		port_obj_info->handled = true;
-		return add_cb(dev, port_obj_info->obj, port_obj_info->trans,
-			      extack);
+		err = add_cb(dev, port_obj_info->obj, port_obj_info->trans,
+			     extack);
+		if (err != -EOPNOTSUPP)
+			port_obj_info->handled = true;
+		return err;
 	}
 
 	/* Switch ports might be stacked under e.g. a LAG. Ignore the
@@ -513,9 +514,10 @@
 	int err = -EOPNOTSUPP;
 
 	if (check_cb(dev)) {
-		/* This flag is only checked if the return value is success. */
-		port_obj_info->handled = true;
-		return del_cb(dev, port_obj_info->obj);
+		err = del_cb(dev, port_obj_info->obj);
+		if (err != -EOPNOTSUPP)
+			port_obj_info->handled = true;
+		return err;
 	}
 
 	/* Switch ports might be stacked under e.g. a LAG. Ignore the
@@ -563,9 +565,10 @@
 	int err = -EOPNOTSUPP;
 
 	if (check_cb(dev)) {
-		port_attr_info->handled = true;
-		return set_cb(dev, port_attr_info->attr,
-			      port_attr_info->trans);
+		err = set_cb(dev, port_attr_info->attr, port_attr_info->trans);
+		if (err != -EOPNOTSUPP)
+			port_attr_info->handled = true;
+		return err;
 	}
 
 	/* Switch ports might be stacked under e.g. a LAG. Ignore the
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 5f515a2..b3667a5 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -2450,6 +2450,9 @@
 	/* CometLake-S */
 	{ PCI_DEVICE(0x8086, 0xa3f0),
 	  .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE},
+	/* CometLake-R */
+	{ PCI_DEVICE(0x8086, 0xf0c8),
+	  .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE},
 	/* Icelake */
 	{ PCI_DEVICE(0x8086, 0x34c8),
 	  .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE},
diff --git a/sound/soc/sof/intel/hda-codec.c b/sound/soc/sof/intel/hda-codec.c
index 9e8233c..df38616 100644
--- a/sound/soc/sof/intel/hda-codec.c
+++ b/sound/soc/sof/intel/hda-codec.c
@@ -68,8 +68,7 @@
 		 * has been recorded in STATESTS
 		 */
 		if (codec->jacktbl.used)
-			schedule_delayed_work(&codec->jackpoll_work,
-					      codec->jackpoll_interval);
+			pm_request_resume(&codec->core.dev);
 }
 #else
 void hda_codec_jack_wake_enable(struct snd_sof_dev *sdev) {}
diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c
index edba474..693d740 100644
--- a/tools/objtool/elf.c
+++ b/tools/objtool/elf.c
@@ -214,8 +214,11 @@
 
 	symtab = find_section_by_name(elf, ".symtab");
 	if (!symtab) {
-		WARN("missing symbol table");
-		return -1;
+		/*
+		 * A missing symbol table is actually possible if it's an empty
+		 * .o file.  This can happen for thunk_64.o.
+		 */
+		return 0;
 	}
 
 	symbols_nr = symtab->sh.sh_size / symtab->sh.sh_entsize;
diff --git a/tools/testing/selftests/powerpc/alignment/alignment_handler.c b/tools/testing/selftests/powerpc/alignment/alignment_handler.c
index 0453c50..0725239 100644
--- a/tools/testing/selftests/powerpc/alignment/alignment_handler.c
+++ b/tools/testing/selftests/powerpc/alignment/alignment_handler.c
@@ -380,7 +380,6 @@
 	LOAD_DFORM_TEST(ldu);
 	LOAD_XFORM_TEST(ldx);
 	LOAD_XFORM_TEST(ldux);
-	LOAD_DFORM_TEST(lmw);
 	STORE_DFORM_TEST(stb);
 	STORE_XFORM_TEST(stbx);
 	STORE_DFORM_TEST(stbu);
@@ -399,7 +398,11 @@
 	STORE_XFORM_TEST(stdx);
 	STORE_DFORM_TEST(stdu);
 	STORE_XFORM_TEST(stdux);
+
+#ifdef __BIG_ENDIAN__
+	LOAD_DFORM_TEST(lmw);
 	STORE_DFORM_TEST(stmw);
+#endif
 
 	return rc;
 }