4.14.257-rc1 review

cover

	https://www.kernel.org/pub/linux/kernel/v4.x/stable-review/patch-4.14.257-rc1.gz
    Linux 4.14.257-rc1
    net: tulip: de4x5: fix the problem that the array 'lp->phy[8]' may be out of bound
    net: ieee802154: handle iftypes as u32
    USB: serial: option: add Telit LE910S1 0x9200 composition
 .../pinctrl/marvell,armada-37xx-pinctrl.txt        |  26 +-
 Documentation/networking/ipvs-sysctl.txt           |   3 +-
 Makefile                                           |   4 +-
 arch/arm/boot/dts/bcm5301x.dtsi                    |   4 +-
 arch/arm/include/asm/tlb.h                         |   8 +
 arch/arm/mach-socfpga/core.h                       |   2 +-
 arch/arm/mach-socfpga/platsmp.c                    |   8 +-
 arch/arm64/boot/dts/marvell/armada-3720-db.dts     |   3 +
 .../boot/dts/marvell/armada-3720-espressobin.dts   |   3 +
 arch/arm64/boot/dts/marvell/armada-37xx.dtsi       |   9 +
 arch/ia64/include/asm/tlb.h                        |  10 +
 arch/mips/Kconfig                                  |   2 +-
 arch/parisc/Makefile                               |   5 +
 arch/parisc/install.sh                             |   1 +
 arch/parisc/kernel/time.c                          |  24 +-
 arch/s390/include/asm/tlb.h                        |  14 +
 arch/s390/kernel/setup.c                           |   3 -
 arch/s390/mm/pgtable.c                             |  13 +
 arch/sh/include/asm/tlb.h                          |  10 +
 arch/um/include/asm/tlb.h                          |  12 +
 arch/x86/realmode/init.c                           |  12 +-
 drivers/android/binder.c                           |   2 +-
 drivers/ata/sata_fsl.c                             |  20 +-
 drivers/block/xen-blkfront.c                       | 126 ++++--
 drivers/gpu/drm/vc4/vc4_bo.c                       |   2 +-
 drivers/hid/wacom_wac.c                            |   8 +-
 drivers/hid/wacom_wac.h                            |   1 +
 drivers/media/cec/cec-adap.c                       |   1 +
 drivers/net/ethernet/dec/tulip/de4x5.c             |  34 +-
 drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c |   4 +
 drivers/net/ethernet/mellanox/mlx4/en_netdev.c     |   9 +-
 drivers/net/ethernet/natsemi/xtsonic.c             |   2 +-
 .../net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c    |  10 +-
 drivers/net/usb/lan78xx.c                          |   2 +-
 drivers/net/vrf.c                                  |   2 +
 drivers/net/xen-netfront.c                         | 257 +++++++-----
 drivers/pci/host/pci-aardvark.c                    | 463 +++++++++++++++++----
 drivers/pinctrl/mvebu/pinctrl-armada-37xx.c        |  28 +-
 drivers/platform/x86/thinkpad_acpi.c               |  12 -
 drivers/scsi/mpt3sas/mpt3sas_scsih.c               |   2 +-
 drivers/scsi/scsi_transport_iscsi.c                |   6 +-
 drivers/staging/rtl8192e/rtl8192e/rtl_core.c       |   3 +-
 drivers/staging/typec/tcpm.c                       |   4 -
 drivers/thermal/thermal_core.c                     |   2 +
 drivers/tty/hvc/hvc_xen.c                          |  17 +-
 drivers/tty/serial/amba-pl011.c                    |   1 +
 drivers/tty/serial/msm_serial.c                    |   3 +
 drivers/tty/serial/serial_core.c                   |  13 +-
 drivers/usb/core/hub.c                             |  23 +-
 drivers/usb/host/xhci-ring.c                       |  21 +-
 drivers/usb/serial/option.c                        |   5 +
 drivers/vhost/vsock.c                              |   2 +-
 drivers/video/console/vgacon.c                     |  14 +-
 drivers/xen/xenbus/xenbus_probe.c                  |  27 +-
 fs/btrfs/disk-io.c                                 |  14 +-
 fs/file.c                                          |  19 +-
 fs/file_table.c                                    |   9 +-
 fs/fuse/dev.c                                      |  14 +-
 fs/nfs/nfs42proc.c                                 |   5 +-
 fs/nfs/nfs42xdr.c                                  |   3 +-
 fs/proc/vmcore.c                                   |  15 +-
 include/asm-generic/tlb.h                          |   2 +
 include/linux/file.h                               |   2 +
 include/linux/fs.h                                 |   4 +-
 include/linux/ipc_namespace.h                      |  15 +
 include/linux/kprobes.h                            |   2 +
 include/linux/sched/task.h                         |   2 +-
 include/linux/shm.h                                |  13 +-
 include/linux/siphash.h                            |  14 +-
 include/net/nfc/nci_core.h                         |   1 +
 include/net/nl802154.h                             |   7 +-
 include/uapi/linux/pci_regs.h                      |   5 +
 include/xen/interface/io/ring.h                    | 293 +++++++------
 ipc/shm.c                                          | 176 ++++++--
 ipc/util.c                                         |   6 +-
 kernel/kprobes.c                                   |   3 +
 kernel/power/hibernate.c                           |   6 +-
 kernel/trace/trace.h                               |  24 +-
 kernel/trace/trace_events.c                        |   7 +
 lib/siphash.c                                      |  12 +-
 mm/hugetlb.c                                       |  72 +++-
 mm/memory.c                                        |  10 +
 net/ipv4/devinet.c                                 |   2 +-
 net/ipv4/tcp_cubic.c                               |   5 +-
 net/ipv6/ip6_output.c                              |   2 +-
 net/mpls/af_mpls.c                                 |  68 ++-
 net/netfilter/ipvs/ip_vs_core.c                    |   8 +-
 net/nfc/nci/core.c                                 |  19 +-
 net/rds/tcp.c                                      |   2 +-
 net/smc/af_smc.c                                   |   8 +-
 net/smc/smc_close.c                                |  10 +
 sound/pci/ctxfi/ctamixer.c                         |  14 +-
 sound/pci/ctxfi/ctdaio.c                           |  16 +-
 sound/pci/ctxfi/ctresource.c                       |   7 +-
 sound/pci/ctxfi/ctresource.h                       |   4 +-
 sound/pci/ctxfi/ctsrc.c                            |   7 +-
 sound/soc/soc-topology.c                           |   3 +
 tools/perf/ui/hist.c                               |  28 +-
 tools/perf/util/hist.h                             |   1 -
 99 files changed, 1591 insertions(+), 670 deletions(-)
---
 drivers/usb/serial/option.c |    2 ++
 1 file changed, 2 insertions(+)
@@ -1270,6 +1270,8 @@ static const struct usb_device_id option
 	  .driver_info = NCTRL(2) },
 	{ USB_DEVICE(TELIT_VENDOR_ID, 0x9010),				/* Telit SBL FN980 flashing device */
 	  .driver_info = NCTRL(0) | ZLP },
+	{ USB_DEVICE(TELIT_VENDOR_ID, 0x9200),				/* Telit LE910S1 flashing device */
+	  .driver_info = NCTRL(0) | ZLP },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_MF622, 0xff, 0xff, 0xff) }, /* ZTE WCDMA products */
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0002, 0xff, 0xff, 0xff),
 	  .driver_info = RSVD(1) },

T:  Bus=02 Lev=01 Prnt=01 Port=03 Cnt=01 Dev#= 86 Spd=5000 MxCh= 0
D:  Ver= 3.20 Cls=00(>ifc ) Sub=00 Prot=00 MxPS= 9 #Cfgs=  1
P:  Vendor=2cb7 ProdID=01a2 Rev= 5.04
S:  Manufacturer=Fibocom Wireless Inc.
S:  Product=Fibocom FM101-GL Module
S:  SerialNumber=673326ce
  bDeviceClass            0
  bDeviceSubClass         0
  bDeviceProtocol         0
  bMaxPacketSize0         9
  idVendor           0x2cb7
  idProduct          0x01a2
  bcdDevice            5.04
  iManufacturer           1 Fibocom Wireless Inc.
  iProduct                2 Fibocom FM101-GL Module
  iSerial                 3 673326ce
  bNumConfigurations      1
T:  Bus=02 Lev=01 Prnt=01 Port=03 Cnt=01 Dev#= 85 Spd=5000 MxCh= 0
D:  Ver= 3.20 Cls=00(>ifc ) Sub=00 Prot=00 MxPS= 9 #Cfgs=  1
P:  Vendor=2cb7 ProdID=01a4 Rev= 5.04
S:  Manufacturer=Fibocom Wireless Inc.
S:  Product=Fibocom FM101-GL Module
S:  SerialNumber=673326ce
  bDeviceClass            0
  bDeviceSubClass         0
  bDeviceProtocol         0
  bMaxPacketSize0         9
  idVendor           0x2cb7
  idProduct          0x01a4
  bcdDevice            5.04
  iManufacturer           1 Fibocom Wireless Inc.
  iProduct                2 Fibocom FM101-GL Module
  iSerial                 3 673326ce
  bNumConfigurations      1
---
 drivers/usb/serial/option.c |    3 +++
 1 file changed, 3 insertions(+)
@@ -2098,6 +2098,9 @@ static const struct usb_device_id option
 	{ USB_DEVICE_AND_INTERFACE_INFO(0x2cb7, 0x010b, 0xff, 0xff, 0x30) },	/* Fibocom FG150 Diag */
 	{ USB_DEVICE_AND_INTERFACE_INFO(0x2cb7, 0x010b, 0xff, 0, 0) },		/* Fibocom FG150 AT */
 	{ USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a0, 0xff) },			/* Fibocom NL668-AM/NL652-EU (laptop MBIM) */
+	{ USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a2, 0xff) },			/* Fibocom FM101-GL (laptop MBIM) */
+	{ USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a4, 0xff),			/* Fibocom FM101-GL (laptop MBIM) */
+	  .driver_info = RSVD(4) },
 	{ USB_DEVICE_INTERFACE_CLASS(0x2df3, 0x9d03, 0xff) },			/* LongSung M5710 */
 	{ USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1404, 0xff) },			/* GosunCn GM500 RNDIS */
 	{ USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1405, 0xff) },			/* GosunCn GM500 MBIM */

---
 drivers/usb/core/hub.c |   14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)
@@ -4472,8 +4472,6 @@ hub_port_init(struct usb_hub *hub, struc
 	if (oldspeed == USB_SPEED_LOW)
 		delay = HUB_LONG_RESET_TIME;
 
-	mutex_lock(hcd->address0_mutex);
-
 	/* Reset the device; full speed may morph to high speed */
 	/* FIXME a USB 2.0 device may morph into SuperSpeed on reset. */
 	retval = hub_port_reset(hub, port1, udev, delay, false);

@@ -4772,7 +4770,6 @@ fail:
 		hub_port_disable(hub, port1, 0);
 		update_devnum(udev, devnum);	/* for disconnect processing */
 	}
-	mutex_unlock(hcd->address0_mutex);
 	return retval;
 }
 

@@ -4917,6 +4914,9 @@ static void hub_port_connect(struct usb_
 		unit_load = 100;
 
 	status = 0;
+
+	mutex_lock(hcd->address0_mutex);
+
 	for (i = 0; i < SET_CONFIG_TRIES; i++) {
 
 		/* reallocate for each attempt, since references

@@ -4953,6 +4953,8 @@ static void hub_port_connect(struct usb_
 		if (status < 0)
 			goto loop;
 
+		mutex_unlock(hcd->address0_mutex);
+
 		if (udev->quirks & USB_QUIRK_DELAY_INIT)
 			msleep(2000);
 

@@ -5041,6 +5043,7 @@ static void hub_port_connect(struct usb_
 
 loop_disable:
 		hub_port_disable(hub, port1, 1);
+		mutex_lock(hcd->address0_mutex);
 loop:
 		usb_ep0_reinit(udev);
 		release_devnum(udev);

@@ -5067,6 +5070,8 @@ loop:
 	}
 
 done:
+	mutex_unlock(hcd->address0_mutex);
+
 	hub_port_disable(hub, port1, 1);
 	if (hcd->driver->relinquish_port && !hub->hdev->parent) {
 		if (status != -ENOTCONN && status != -ENODEV)

@@ -5608,6 +5613,8 @@ static int usb_reset_and_verify_device(s
 	bos = udev->bos;
 	udev->bos = NULL;
 
+	mutex_lock(hcd->address0_mutex);
+
 	for (i = 0; i < SET_CONFIG_TRIES; ++i) {
 
 		/* ep0 maxpacket size may change; let the HCD know about it.

@@ -5617,6 +5624,7 @@ static int usb_reset_and_verify_device(s
 		if (ret >= 0 || ret == -ENOTCONN || ret == -ENODEV)
 			break;
 	}
+	mutex_unlock(hcd->address0_mutex);
 
 	if (ret < 0)
 		goto re_enumerate;

---
 drivers/usb/core/hub.c |   19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)
@@ -4859,6 +4859,7 @@ static void hub_port_connect(struct usb_
 	struct usb_port *port_dev = hub->ports[port1 - 1];
 	struct usb_device *udev = port_dev->child;
 	static int unreliable_port = -1;
+	bool retry_locked;
 
 	/* Disconnect any existing devices under this port */
 	if (udev) {

@@ -4915,9 +4916,10 @@ static void hub_port_connect(struct usb_
 
 	status = 0;
 
-	mutex_lock(hcd->address0_mutex);
-
 	for (i = 0; i < SET_CONFIG_TRIES; i++) {
+		usb_lock_port(port_dev);
+		mutex_lock(hcd->address0_mutex);
+		retry_locked = true;
 
 		/* reallocate for each attempt, since references
 		 * to the previous one can escape in various ways

@@ -4926,6 +4928,8 @@ static void hub_port_connect(struct usb_
 		if (!udev) {
 			dev_err(&port_dev->dev,
 					"couldn't allocate usb_device\n");
+			mutex_unlock(hcd->address0_mutex);
+			usb_unlock_port(port_dev);
 			goto done;
 		}
 

@@ -4947,13 +4951,13 @@ static void hub_port_connect(struct usb_
 		}
 
 		/* reset (non-USB 3.0 devices) and get descriptor */
-		usb_lock_port(port_dev);
 		status = hub_port_init(hub, udev, port1, i);
-		usb_unlock_port(port_dev);
 		if (status < 0)
 			goto loop;
 
 		mutex_unlock(hcd->address0_mutex);
+		usb_unlock_port(port_dev);
+		retry_locked = false;
 
 		if (udev->quirks & USB_QUIRK_DELAY_INIT)
 			msleep(2000);

@@ -5043,11 +5047,14 @@ static void hub_port_connect(struct usb_
 
 loop_disable:
 		hub_port_disable(hub, port1, 1);
-		mutex_lock(hcd->address0_mutex);
 loop:
 		usb_ep0_reinit(udev);
 		release_devnum(udev);
 		hub_free_dev(udev);
+		if (retry_locked) {
+			mutex_unlock(hcd->address0_mutex);
+			usb_unlock_port(port_dev);
+		}
 		usb_put_dev(udev);
 		if ((status == -ENOTCONN) || (status == -ENOTSUPP))
 			break;

@@ -5070,8 +5077,6 @@ loop:
 	}
 
 done:
-	mutex_unlock(hcd->address0_mutex);
-
 	hub_port_disable(hub, port1, 1);
 	if (hcd->driver->relinquish_port && !hub->hdev->parent) {
 		if (status != -ENOTCONN && status != -ENODEV)

---
 drivers/android/binder.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
@@ -2894,7 +2894,7 @@ static void binder_transaction(struct bi
 		t->from = thread;
 	else
 		t->from = NULL;
-	t->sender_euid = proc->cred->euid;
+	t->sender_euid = task_euid(proc->tsk);
 	t->to_proc = target_proc;
 	t->to_thread = target_thread;
 	t->code = tr->code;

---
 sound/pci/ctxfi/ctamixer.c   |   14 ++++++--------
 sound/pci/ctxfi/ctdaio.c     |   16 ++++++++--------
 sound/pci/ctxfi/ctresource.c |    7 +++----
 sound/pci/ctxfi/ctresource.h |    4 ++--
 sound/pci/ctxfi/ctsrc.c      |    7 +++----
 5 files changed, 22 insertions(+), 26 deletions(-)
@@ -27,16 +27,15 @@
 
 #define BLANK_SLOT		4094
 
-static int amixer_master(struct rsc *rsc)
+static void amixer_master(struct rsc *rsc)
 {
 	rsc->conj = 0;
-	return rsc->idx = container_of(rsc, struct amixer, rsc)->idx[0];
+	rsc->idx = container_of(rsc, struct amixer, rsc)->idx[0];
 }
 
-static int amixer_next_conj(struct rsc *rsc)
+static void amixer_next_conj(struct rsc *rsc)
 {
 	rsc->conj++;
-	return container_of(rsc, struct amixer, rsc)->idx[rsc->conj];
 }
 
 static int amixer_index(const struct rsc *rsc)

@@ -335,16 +334,15 @@ int amixer_mgr_destroy(struct amixer_mgr
 
 /* SUM resource management */
 
-static int sum_master(struct rsc *rsc)
+static void sum_master(struct rsc *rsc)
 {
 	rsc->conj = 0;
-	return rsc->idx = container_of(rsc, struct sum, rsc)->idx[0];
+	rsc->idx = container_of(rsc, struct sum, rsc)->idx[0];
 }
 
-static int sum_next_conj(struct rsc *rsc)
+static void sum_next_conj(struct rsc *rsc)
 {
 	rsc->conj++;
-	return container_of(rsc, struct sum, rsc)->idx[rsc->conj];
 }
 
 static int sum_index(const struct rsc *rsc)

@@ -55,12 +55,12 @@ static struct daio_rsc_idx idx_20k2[NUM_
 	[SPDIFIO] = {.left = 0x05, .right = 0x85},
 };
 
-static int daio_master(struct rsc *rsc)
+static void daio_master(struct rsc *rsc)
 {
 	/* Actually, this is not the resource index of DAIO.
 	 * For DAO, it is the input mapper index. And, for DAI,
 	 * it is the output time-slot index. */
-	return rsc->conj = rsc->idx;
+	rsc->conj = rsc->idx;
 }
 
 static int daio_index(const struct rsc *rsc)

@@ -68,19 +68,19 @@ static int daio_index(const struct rsc *
 	return rsc->conj;
 }
 
-static int daio_out_next_conj(struct rsc *rsc)
+static void daio_out_next_conj(struct rsc *rsc)
 {
-	return rsc->conj += 2;
+	rsc->conj += 2;
 }
 
-static int daio_in_next_conj_20k1(struct rsc *rsc)
+static void daio_in_next_conj_20k1(struct rsc *rsc)
 {
-	return rsc->conj += 0x200;
+	rsc->conj += 0x200;
 }
 
-static int daio_in_next_conj_20k2(struct rsc *rsc)
+static void daio_in_next_conj_20k2(struct rsc *rsc)
 {
-	return rsc->conj += 0x100;
+	rsc->conj += 0x100;
 }
 
 static const struct rsc_ops daio_out_rsc_ops = {

@@ -113,18 +113,17 @@ static int audio_ring_slot(const struct
     return (rsc->conj << 4) + offset_in_audio_slot_block[rsc->type];
 }
 
-static int rsc_next_conj(struct rsc *rsc)
+static void rsc_next_conj(struct rsc *rsc)
 {
 	unsigned int i;
 	for (i = 0; (i < 8) && (!(rsc->msr & (0x1 << i))); )
 		i++;
 	rsc->conj += (AUDIO_SLOT_BLOCK_NUM >> i);
-	return rsc->conj;
 }
 
-static int rsc_master(struct rsc *rsc)
+static void rsc_master(struct rsc *rsc)
 {
-	return rsc->conj = rsc->idx;
+	rsc->conj = rsc->idx;
 }
 
 static const struct rsc_ops rsc_generic_ops = {

@@ -43,8 +43,8 @@ struct rsc {
 };
 
 struct rsc_ops {
-	int (*master)(struct rsc *rsc);	/* Move to master resource */
-	int (*next_conj)(struct rsc *rsc); /* Move to next conjugate resource */
+	void (*master)(struct rsc *rsc); /* Move to master resource */
+	void (*next_conj)(struct rsc *rsc); /* Move to next conjugate resource */
 	int (*index)(const struct rsc *rsc); /* Return the index of resource */
 	/* Return the output slot number */
 	int (*output_slot)(const struct rsc *rsc);

@@ -594,16 +594,15 @@ int src_mgr_destroy(struct src_mgr *src_
 
 /* SRCIMP resource manager operations */
 
-static int srcimp_master(struct rsc *rsc)
+static void srcimp_master(struct rsc *rsc)
 {
 	rsc->conj = 0;
-	return rsc->idx = container_of(rsc, struct srcimp, rsc)->idx[0];
+	rsc->idx = container_of(rsc, struct srcimp, rsc)->idx[0];
 }
 
-static int srcimp_next_conj(struct rsc *rsc)
+static void srcimp_next_conj(struct rsc *rsc)
 {
 	rsc->conj++;
-	return container_of(rsc, struct srcimp, rsc)->idx[rsc->conj];
 }
 
 static int srcimp_index(const struct rsc *rsc)

---
 drivers/media/cec/cec-adap.c |    1 +
 1 file changed, 1 insertion(+)
@@ -1135,6 +1135,7 @@ void cec_received_msg_ts(struct cec_adap
 			if (abort)
 				dst->rx_status |= CEC_RX_STATUS_FEATURE_ABORT;
 			msg->flags = dst->flags;
+			msg->sequence = dst->sequence;
 			/* Remove it from the wait_queue */
 			list_del_init(&data->list);
 

---
 drivers/hid/wacom_wac.c |    8 +++++++-
 drivers/hid/wacom_wac.h |    1 +
 2 files changed, 8 insertions(+), 1 deletion(-)
@@ -2433,6 +2433,9 @@ static void wacom_wac_finger_event(struc
 	struct wacom_features *features = &wacom->wacom_wac.features;
 
 	switch (equivalent_usage) {
+	case HID_DG_CONFIDENCE:
+		wacom_wac->hid_data.confidence = value;
+		break;
 	case HID_GD_X:
 		wacom_wac->hid_data.x = value;
 		break;

@@ -2463,7 +2466,8 @@ static void wacom_wac_finger_event(struc
 
 
 	if (usage->usage_index + 1 == field->report_count) {
-		if (equivalent_usage == wacom_wac->hid_data.last_slot_field)
+		if (equivalent_usage == wacom_wac->hid_data.last_slot_field &&
+		    wacom_wac->hid_data.confidence)
 			wacom_wac_finger_slot(wacom_wac, wacom_wac->touch_input);
 	}
 }

@@ -2476,6 +2480,8 @@ static void wacom_wac_finger_pre_report(
 	struct hid_data* hid_data = &wacom_wac->hid_data;
 	int i;
 
+	hid_data->confidence = true;
+
 	for (i = 0; i < report->maxfield; i++) {
 		struct hid_field *field = report->field[i];
 		int j;

@@ -293,6 +293,7 @@ struct hid_data {
 	bool inrange_state;
 	bool invert_state;
 	bool tipswitch;
+	bool confidence;
 	int x;
 	int y;
 	int pressure;

---
 drivers/staging/rtl8192e/rtl8192e/rtl_core.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
@@ -2582,13 +2582,14 @@ static void _rtl92e_pci_disconnect(struc
 			free_irq(dev->irq, dev);
 			priv->irq = 0;
 		}
-		free_rtllib(dev);
 
 		if (dev->mem_start != 0) {
 			iounmap((void __iomem *)dev->mem_start);
 			release_mem_region(pci_resource_start(pdev, 1),
 					pci_resource_len(pdev, 1));
 		}
+
+		free_rtllib(dev);
 	} else {
 		priv = rtllib_priv(dev);
 	}

---
 fs/fuse/dev.c |   14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)
@@ -897,6 +897,12 @@ static int fuse_try_move_page(struct fus
 		goto out_put_old;
 	}
 
+	/*
+	 * Release while we have extra ref on stolen page.  Otherwise
+	 * anon_pipe_buf_release() might think the page can be reused.
+	 */
+	pipe_buf_release(cs->pipe, buf);
+
 	get_page(newpage);
 
 	if (!(buf->flags & PIPE_BUF_FLAG_LRU))

@@ -2046,8 +2052,12 @@ static ssize_t fuse_dev_splice_write(str
 
 	pipe_lock(pipe);
 out_free:
-	for (idx = 0; idx < nbuf; idx++)
-		pipe_buf_release(pipe, &bufs[idx]);
+	for (idx = 0; idx < nbuf; idx++) {
+		struct pipe_buffer *buf = &bufs[idx];
+
+		if (buf->ops)
+			pipe_buf_release(pipe, buf);
+	}
 	pipe_unlock(pipe);
 
 	kfree(bufs);

[    2.479830] Call trace:
[    2.482314]  xb_init_comms+0x18/0x150
[    2.486354]  xs_init+0x34/0x138
[    2.489786]  xenbus_probe+0x4c/0x70
[    2.498432]  xenbus_probe_initcall+0x2c/0x7c
[    2.503944]  do_one_initcall+0x54/0x1b8
[    2.507358]  kernel_init_freeable+0x1ac/0x210
[    2.511617]  kernel_init+0x28/0x130
[    2.516112]  ret_from_fork+0x10/0x20
---
 drivers/xen/xenbus/xenbus_probe.c |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)
@@ -838,7 +838,7 @@ static struct notifier_block xenbus_resu
 
 static int __init xenbus_init(void)
 {
-	int err = 0;
+	int err;
 	uint64_t v = 0;
 	xen_store_domain_type = XS_UNKNOWN;
 

@@ -912,8 +912,10 @@ static int __init xenbus_init(void)
 	 */
 	proc_create_mount_point("xen");
 #endif
+	return 0;
 
 out_error:
+	xen_store_domain_type = XS_UNKNOWN;
 	return err;
 }
 

---
 drivers/xen/xenbus/xenbus_probe.c |   23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)
@@ -878,6 +878,29 @@ static int __init xenbus_init(void)
 		err = hvm_get_parameter(HVM_PARAM_STORE_PFN, &v);
 		if (err)
 			goto out_error;
+		/*
+		 * Uninitialized hvm_params are zero and return no error.
+		 * Although it is theoretically possible to have
+		 * HVM_PARAM_STORE_PFN set to zero on purpose, in reality it is
+		 * not zero when valid. If zero, it means that Xenstore hasn't
+		 * been properly initialized. Instead of attempting to map a
+		 * wrong guest physical address return error.
+		 *
+		 * Also recognize all bits set as an invalid value.
+		 */
+		if (!v || !~v) {
+			err = -ENOENT;
+			goto out_error;
+		}
+		/* Avoid truncation on 32-bit. */
+#if BITS_PER_LONG == 32
+		if (v > ULONG_MAX) {
+			pr_err("%s: cannot handle HVM_PARAM_STORE_PFN=%llx > ULONG_MAX\n",
+			       __func__, v);
+			err = -EINVAL;
+			goto out_error;
+		}
+#endif
 		xen_store_gfn = (unsigned long)v;
 		xen_store_interface =
 			xen_remap(xen_store_gfn << XEN_PAGE_SHIFT,

---
 kernel/trace/trace.h |   24 ++++++++++++++++++------
 1 file changed, 18 insertions(+), 6 deletions(-)
@@ -1363,14 +1363,26 @@ __event_trigger_test_discard(struct trac
 	if (eflags & EVENT_FILE_FL_TRIGGER_COND)
 		*tt = event_triggers_call(file, entry);
 
-	if (test_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT, &file->flags) ||
-	    (unlikely(file->flags & EVENT_FILE_FL_FILTERED) &&
-	     !filter_match_preds(file->filter, entry))) {
-		__trace_event_discard_commit(buffer, event);
-		return true;
-	}
+	if (likely(!(file->flags & (EVENT_FILE_FL_SOFT_DISABLED |
+				    EVENT_FILE_FL_FILTERED |
+				    EVENT_FILE_FL_PID_FILTER))))
+		return false;
+
+	if (file->flags & EVENT_FILE_FL_SOFT_DISABLED)
+		goto discard;
+
+	if (file->flags & EVENT_FILE_FL_FILTERED &&
+	    !filter_match_preds(file->filter, entry))
+		goto discard;
+
+	if ((file->flags & EVENT_FILE_FL_PID_FILTER) &&
+	    trace_event_ignore_this_pid(file))
+		goto discard;
 
 	return false;
+ discard:
+	__trace_event_discard_commit(buffer, event);
+	return true;
 }
 
 /**

---
 Documentation/networking/ipvs-sysctl.txt | 3 +--
 net/netfilter/ipvs/ip_vs_core.c          | 8 ++++----
 2 files changed, 5 insertions(+), 6 deletions(-)
index 056898685d408..fc531c29a2e83 100644
@@ -30,8 +30,7 @@ conn_reuse_mode - INTEGER
 
 	0: disable any special handling on port reuse. The new
 	connection will be delivered to the same real server that was
-	servicing the previous connection. This will effectively
-	disable expire_nodest_conn.
+	servicing the previous connection.
 
 	bit 1: enable rescheduling of new connections when it is safe.
 	That is, whenever expire_nodest_conn and for TCP sockets, when

index a95fe5fe9f046..4b9cd1c1c9987 100644
@@ -1838,7 +1838,6 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int
 	struct ip_vs_proto_data *pd;
 	struct ip_vs_conn *cp;
 	int ret, pkts;
-	int conn_reuse_mode;
 	struct sock *sk;
 
 	/* Already marked as IPVS request or reply? */

@@ -1914,15 +1913,16 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int
 	 */
 	cp = pp->conn_in_get(ipvs, af, skb, &iph);
 
-	conn_reuse_mode = sysctl_conn_reuse_mode(ipvs);
-	if (conn_reuse_mode && !iph.fragoffs && is_new_conn(skb, &iph) && cp) {
+	if (!iph.fragoffs && is_new_conn(skb, &iph) && cp) {
+		int conn_reuse_mode = sysctl_conn_reuse_mode(ipvs);
 		bool old_ct = false, resched = false;
 
 		if (unlikely(sysctl_expire_nodest_conn(ipvs)) && cp->dest &&
 		    unlikely(!atomic_read(&cp->dest->weight))) {
 			resched = true;
 			old_ct = ip_vs_conn_uses_old_conntrack(cp, skb);
-		} else if (is_new_conn_expected(cp, conn_reuse_mode)) {
+		} else if (conn_reuse_mode &&
+			   is_new_conn_expected(cp, conn_reuse_mode)) {
 			old_ct = ip_vs_conn_uses_old_conntrack(cp, skb);
 			if (!atomic_read(&cp->n_control)) {
 				resched = true;

2.33.0
---
 arch/arm/boot/dts/bcm5301x.dtsi | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
index 165fd1c1461a0..01a4935598915 100644
@@ -365,7 +365,7 @@ mdio: mdio@18003000 {
 	i2c0: i2c@18009000 {
 		compatible = "brcm,iproc-i2c";
 		reg = <0x18009000 0x50>;
-		interrupts = <GIC_SPI 121 IRQ_TYPE_LEVEL_HIGH>;
+		interrupts = <GIC_SPI 89 IRQ_TYPE_LEVEL_HIGH>;
 		#address-cells = <1>;
 		#size-cells = <0>;
 		clock-frequency = <100000>;

2.33.0
---
 arch/arm/boot/dts/bcm5301x.dtsi | 2 ++
 1 file changed, 2 insertions(+)
index 01a4935598915..c3b6ba4db8e3d 100644
@@ -246,6 +246,8 @@ chipcommon: chipcommon@0 {
 
 			gpio-controller;
 			#gpio-cells = <2>;
+			interrupt-controller;
+			#interrupt-cells = <2>;
 		};
 
 		pcie0: pcie@12000 {

2.33.0
---
 sound/soc/soc-topology.c | 3 +++
 1 file changed, 3 insertions(+)
index 50aa45525be5a..0fbe505026997 100644
@@ -2585,6 +2585,7 @@ EXPORT_SYMBOL_GPL(snd_soc_tplg_widget_remove_all);
 /* remove dynamic controls from the component driver */
 int snd_soc_tplg_component_remove(struct snd_soc_component *comp, u32 index)
 {
+	struct snd_card *card = comp->card->snd_card;
 	struct snd_soc_dobj *dobj, *next_dobj;
 	int pass = SOC_TPLG_PASS_END;
 

@@ -2592,6 +2593,7 @@ int snd_soc_tplg_component_remove(struct snd_soc_component *comp, u32 index)
 	while (pass >= SOC_TPLG_PASS_START) {
 
 		/* remove mixer controls */
+		down_write(&card->controls_rwsem);
 		list_for_each_entry_safe(dobj, next_dobj, &comp->dobj_list,
 			list) {
 

@@ -2625,6 +2627,7 @@ int snd_soc_tplg_component_remove(struct snd_soc_component *comp, u32 index)
 				break;
 			}
 		}
+		up_write(&card->controls_rwsem);
 		pass--;
 	}
 

2.33.0
---
 include/net/nl802154.h | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)
index ddcee128f5d9a..145acb8f25095 100644
@@ -19,6 +19,8 @@
  *
  */
 
+#include <linux/types.h>
+
 #define NL802154_GENL_NAME "nl802154"
 
 enum nl802154_commands {

@@ -150,10 +152,9 @@ enum nl802154_attrs {
 };
 
 enum nl802154_iftype {
-	/* for backwards compatibility TODO */
-	NL802154_IFTYPE_UNSPEC = -1,
+	NL802154_IFTYPE_UNSPEC = (~(__u32)0),
 
-	NL802154_IFTYPE_NODE,
+	NL802154_IFTYPE_NODE = 0,
 	NL802154_IFTYPE_MONITOR,
 	NL802154_IFTYPE_COORD,
 

2.33.0
---
 fs/nfs/nfs42xdr.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)
index 5966e1e7b1f51..09c683402f950 100644
@@ -625,8 +625,7 @@ static int nfs4_xdr_dec_clone(struct rpc_rqst *rqstp,
 	status = decode_clone(xdr);
 	if (status)
 		goto out;
-	status = decode_getfattr(xdr, res->dst_fattr, res->server);
-
+	decode_getfattr(xdr, res->dst_fattr, res->server);
 out:
 	res->rpc_status = status;
 	return status;

2.33.0
---
 arch/arm/mach-socfpga/core.h    | 2 +-
 arch/arm/mach-socfpga/platsmp.c | 8 ++++----
 2 files changed, 5 insertions(+), 5 deletions(-)
index 65e1817d8afe6..692a287a8712d 100644
@@ -48,7 +48,7 @@ extern void __iomem *sdr_ctl_base_addr;
 u32 socfpga_sdram_self_refresh(u32 sdr_base);
 extern unsigned int socfpga_sdram_self_refresh_sz;
 
-extern char secondary_trampoline, secondary_trampoline_end;
+extern char secondary_trampoline[], secondary_trampoline_end[];
 
 extern unsigned long socfpga_cpu1start_addr;
 

index 0ee76772b5074..a272999ce04b9 100644
@@ -31,14 +31,14 @@
 
 static int socfpga_boot_secondary(unsigned int cpu, struct task_struct *idle)
 {
-	int trampoline_size = &secondary_trampoline_end - &secondary_trampoline;
+	int trampoline_size = secondary_trampoline_end - secondary_trampoline;
 
 	if (socfpga_cpu1start_addr) {
 		/* This will put CPU #1 into reset. */
 		writel(RSTMGR_MPUMODRST_CPU1,
 		       rst_manager_base_addr + SOCFPGA_RSTMGR_MODMPURST);
 
-		memcpy(phys_to_virt(0), &secondary_trampoline, trampoline_size);
+		memcpy(phys_to_virt(0), secondary_trampoline, trampoline_size);
 
 		writel(__pa_symbol(secondary_startup),
 		       sys_manager_base_addr + (socfpga_cpu1start_addr & 0x000000ff));

@@ -56,12 +56,12 @@ static int socfpga_boot_secondary(unsigned int cpu, struct task_struct *idle)
 
 static int socfpga_a10_boot_secondary(unsigned int cpu, struct task_struct *idle)
 {
-	int trampoline_size = &secondary_trampoline_end - &secondary_trampoline;
+	int trampoline_size = secondary_trampoline_end - secondary_trampoline;
 
 	if (socfpga_cpu1start_addr) {
 		writel(RSTMGR_MPUMODRST_CPU1, rst_manager_base_addr +
 		       SOCFPGA_A10_RSTMGR_MODMPURST);
-		memcpy(phys_to_virt(0), &secondary_trampoline, trampoline_size);
+		memcpy(phys_to_virt(0), secondary_trampoline, trampoline_size);
 
 		writel(__pa_symbol(secondary_startup),
 		       sys_manager_base_addr + (socfpga_cpu1start_addr & 0x00000fff));

2.33.0
---
 drivers/scsi/mpt3sas/mpt3sas_scsih.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
index 332ea3af69ec3..79c5a193308f4 100644
@@ -2955,7 +2955,7 @@ _scsih_ublock_io_device(struct MPT3SAS_ADAPTER *ioc, u64 sas_address)
 
 	shost_for_each_device(sdev, ioc->shost) {
 		sas_device_priv_data = sdev->hostdata;
-		if (!sas_device_priv_data)
+		if (!sas_device_priv_data || !sas_device_priv_data->sas_target)
 			continue;
 		if (sas_device_priv_data->sas_target->sas_address
 		    != sas_address)

2.33.0
---
 drivers/gpu/drm/vc4/vc4_bo.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
index eff0a8ece8bcf..85abba74ed981 100644
@@ -292,7 +292,7 @@ struct drm_gem_object *vc4_create_object(struct drm_device *dev, size_t size)
 
 	bo = kzalloc(sizeof(*bo), GFP_KERNEL);
 	if (!bo)
-		return ERR_PTR(-ENOMEM);
+		return NULL;
 
 	mutex_lock(&vc4->bo_lock);
 	bo->label = VC4_BO_TYPE_KERNEL;

2.33.0
---
 net/ipv6/ip6_output.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
index a903d0ce7e701..f906fe2acedd3 100644
@@ -175,7 +175,7 @@ static int ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *s
 #if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM)
 	/* Policy lookup after SNAT yielded a new policy */
 	if (skb_dst(skb)->xfrm) {
-		IPCB(skb)->flags |= IPSKB_REROUTED;
+		IP6CB(skb)->flags |= IP6SKB_REROUTED;
 		return dst_output(net, sk, skb);
 	}
 #endif

2.33.0
Client                                            |  Server
close() // client actively close                  |
  smc_release()                                   |
      smc_close_active() // PEERCLOSEWAIT1        |
          smc_close_final() // abort or closed = 1|
              smc_cdc_get_slot_and_msg_send()     |
          [A]                                     |
                                                  |smc_cdc_msg_recv_action() // ACTIVE
                                                  |  queue_work(smc_close_wq, &conn->close_work)
                                                  |    smc_close_passive_work() // PROCESSABORT or APPCLOSEWAIT1
                                                  |      smc_close_passive_abort_received() // only in abort
                                                  |
                                                  |close() // server recv zero, close
                                                  |  smc_release() // PROCESSABORT or APPCLOSEWAIT1
                                                  |    smc_close_active()
                                                  |      smc_close_abort() or smc_close_final() // CLOSED
                                                  |        smc_cdc_get_slot_and_msg_send() // abort or closed = 1
smc_cdc_msg_recv_action()                         |    smc_clcsock_release()
  queue_work(smc_close_wq, &conn->close_work)     |      sock_release(tcp) // actively close clc, enter TIME_WAIT
    smc_close_passive_work() // PEERCLOSEWAIT1    |    smc_conn_free()
      smc_close_passive_abort_received() // CLOSED|
      smc_conn_free()                             |
      smc_clcsock_release()                       |
        sock_release(tcp) // passive close clc    |
---
 net/smc/smc_close.c | 6 ++++++
 1 file changed, 6 insertions(+)
index 2427a1f3d0d12..d915907ac29ae 100644
@@ -215,6 +215,12 @@ int smc_close_active(struct smc_sock *smc)
 			/* send close request */
 			rc = smc_close_final(conn);
 			sk->sk_state = SMC_PEERCLOSEWAIT1;
+
+			/* actively shutdown clcsock before peer close it,
+			 * prevent peer from entering TIME_WAIT state.
+			 */
+			if (smc->clcsock && smc->clcsock->sk)
+				rc = kernel_sock_shutdown(smc->clcsock, SHUT_RDWR);
 		} else {
 			/* peer event has changed the state */
 			goto again;

2.33.0
---
 kernel/power/hibernate.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)
index 02df69a8ee3c0..e68b1c20ad3d2 100644
@@ -668,7 +668,7 @@ static int load_image_and_restore(void)
 		goto Unlock;
 
 	error = swsusp_read(&flags);
-	swsusp_close(FMODE_READ);
+	swsusp_close(FMODE_READ | FMODE_EXCL);
 	if (!error)
 		hibernation_restore(flags & SF_PLATFORM_MODE);
 

@@ -865,7 +865,7 @@ static int software_resume(void)
 	/* The snapshot device should not be opened while we're running */
 	if (!atomic_add_unless(&snapshot_device_available, -1, 0)) {
 		error = -EBUSY;
-		swsusp_close(FMODE_READ);
+		swsusp_close(FMODE_READ | FMODE_EXCL);
 		goto Unlock;
 	}
 

@@ -901,7 +901,7 @@ static int software_resume(void)
 	pm_pr_dbg("Hibernation image not present or could not be loaded.\n");
 	return error;
  Close_Finish:
-	swsusp_close(FMODE_READ);
+	swsusp_close(FMODE_READ | FMODE_EXCL);
 	goto Finish;
 }
 

2.33.0
Ip6InReceives                   87541              0.0
Ip6OutRequests                  129496             0.0
TcpExtTCPHystartTrainDetect     1                  0.0
TcpExtTCPHystartTrainCwnd       30                 0.0
Ip6InReceives                   88514              0.0
Ip6OutRequests                  87975              0.0
---
 net/ipv4/tcp_cubic.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)
index 8b5ba0a5cd386..93530bd332470 100644
@@ -340,8 +340,6 @@ static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 		return;
 
 	if (tcp_in_slow_start(tp)) {
-		if (hystart && after(ack, ca->end_seq))
-			bictcp_hystart_reset(sk);
 		acked = tcp_slow_start(tp, acked);
 		if (!acked)
 			return;

@@ -383,6 +381,9 @@ static void hystart_update(struct sock *sk, u32 delay)
 	if (ca->found & hystart_detect)
 		return;
 
+	if (after(tp->snd_una, ca->end_seq))
+		bictcp_hystart_reset(sk);
+
 	if (hystart_detect & HYSTART_ACK_TRAIN) {
 		u32 now = bictcp_clock();
 

2.33.0
---
 arch/mips/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
index 85afd6b4297b2..45a5801ff467b 100644
@@ -2990,7 +2990,7 @@ config HAVE_LATENCYTOP_SUPPORT
 config PGTABLE_LEVELS
 	int
 	default 4 if PAGE_SIZE_4KB && MIPS_VA_BITS_48
-	default 3 if 64BIT && !PAGE_SIZE_64KB
+	default 3 if 64BIT && (!PAGE_SIZE_64KB || MIPS_VA_BITS_48)
 	default 2
 
 source "init/Kconfig"

2.33.0
---
 net/smc/af_smc.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)
index 8c71f0929fbb7..f2c907d52812b 100644
@@ -1178,8 +1178,10 @@ static unsigned int smc_poll(struct file *file, struct socket *sock,
 static int smc_shutdown(struct socket *sock, int how)
 {
 	struct sock *sk = sock->sk;
+	bool do_shutdown = true;
 	struct smc_sock *smc;
 	int rc = -EINVAL;
+	int old_state;
 	int rc1 = 0;
 
 	smc = smc_sk(sk);

@@ -1206,7 +1208,11 @@ static int smc_shutdown(struct socket *sock, int how)
 	}
 	switch (how) {
 	case SHUT_RDWR:		/* shutdown in both directions */
+		old_state = sk->sk_state;
 		rc = smc_close_active(smc);
+		if (old_state == SMC_ACTIVE &&
+		    sk->sk_state == SMC_PEERCLOSEWAIT1)
+			do_shutdown = false;
 		break;
 	case SHUT_WR:
 		rc = smc_close_shutdown_write(smc);

@@ -1216,7 +1222,7 @@ static int smc_shutdown(struct socket *sock, int how)
 		/* nothing more to do because peer is not involved */
 		break;
 	}
-	if (smc->clcsock)
+	if (do_shutdown && smc->clcsock)
 		rc1 = kernel_sock_shutdown(smc->clcsock, how);
 	/* map sock_shutdown_cmd constants to sk_shutdown value range */
 	sk->sk_shutdown |= how + 1;

2.33.0
---
 drivers/vhost/vsock.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
@@ -490,7 +490,7 @@ static void vhost_vsock_handle_tx_kick(s
 			virtio_transport_free_pkt(pkt);
 
 		len += sizeof(pkt->hdr);
-		vhost_add_used(vq, head, len);
+		vhost_add_used(vq, head, 0);
 		total_len += len;
 		added = true;
 	} while(likely(!vhost_exceeds_weight(vq, ++pkts, total_len)));

---
 kernel/trace/trace_events.c |    7 +++++++
 1 file changed, 7 insertions(+)
@@ -2254,12 +2254,19 @@ static struct trace_event_file *
 trace_create_new_event(struct trace_event_call *call,
 		       struct trace_array *tr)
 {
+	struct trace_pid_list *pid_list;
 	struct trace_event_file *file;
 
 	file = kmem_cache_alloc(file_cachep, GFP_TRACE);
 	if (!file)
 		return NULL;
 
+	pid_list = rcu_dereference_protected(tr->filtered_pids,
+					     lockdep_is_held(&event_mutex));
+
+	if (pid_list)
+		file->flags |= EVENT_FILE_FL_PID_FILTER;
+
 	file->event_call = call;
 	file->tr = tr;
 	atomic_set(&file->sm_ref, 0);

---
 arch/s390/mm/pgtable.c |   13 +++++++++++++
 1 file changed, 13 insertions(+)
@@ -896,6 +896,7 @@ EXPORT_SYMBOL(get_guest_storage_key);
 int pgste_perform_essa(struct mm_struct *mm, unsigned long hva, int orc,
 			unsigned long *oldpte, unsigned long *oldpgste)
 {
+	struct vm_area_struct *vma;
 	unsigned long pgstev;
 	spinlock_t *ptl;
 	pgste_t pgste;

@@ -905,6 +906,10 @@ int pgste_perform_essa(struct mm_struct
 	WARN_ON_ONCE(orc > ESSA_MAX);
 	if (unlikely(orc > ESSA_MAX))
 		return -EINVAL;
+
+	vma = find_vma(mm, hva);
+	if (!vma || hva < vma->vm_start || is_vm_hugetlb_page(vma))
+		return -EFAULT;
 	ptep = get_locked_pte(mm, hva, &ptl);
 	if (unlikely(!ptep))
 		return -EFAULT;

@@ -997,10 +1002,14 @@ EXPORT_SYMBOL(pgste_perform_essa);
 int set_pgste_bits(struct mm_struct *mm, unsigned long hva,
 			unsigned long bits, unsigned long value)
 {
+	struct vm_area_struct *vma;
 	spinlock_t *ptl;
 	pgste_t new;
 	pte_t *ptep;
 
+	vma = find_vma(mm, hva);
+	if (!vma || hva < vma->vm_start || is_vm_hugetlb_page(vma))
+		return -EFAULT;
 	ptep = get_locked_pte(mm, hva, &ptl);
 	if (unlikely(!ptep))
 		return -EFAULT;

@@ -1025,9 +1034,13 @@ EXPORT_SYMBOL(set_pgste_bits);
  */
 int get_pgste(struct mm_struct *mm, unsigned long hva, unsigned long *pgstep)
 {
+	struct vm_area_struct *vma;
 	spinlock_t *ptl;
 	pte_t *ptep;
 
+	vma = find_vma(mm, hva);
+	if (!vma || hva < vma->vm_start || is_vm_hugetlb_page(vma))
+		return -EFAULT;
 	ptep = get_locked_pte(mm, hva, &ptl);
 	if (unlikely(!ptep))
 		return -EFAULT;

  Internal error: Oops - BUG: 0 [#1] PREEMPT SMP
  Modules linked in:
  CPU: 0 PID: 39 Comm: kworker/0:1 Not tainted 4.17.0-dirty #1092
  Hardware name: Renesas Condor board based on r8a77980 (DT)
  Workqueue: events deferred_probe_work_func
  pstate: 80000005 (Nzcv daif -PAN -UAO)
  pc : ioremap_page_range+0x370/0x3c8
  lr : ioremap_page_range+0x40/0x3c8
  sp : ffff000008da39e0
  x29: ffff000008da39e0 x28: 00e8000000000f07
  x27: ffff7dfffee00000 x26: 0140000000000000
  x25: ffff7dfffef00000 x24: 00000000000fe100
  x23: ffff80007b906000 x22: ffff000008ab8000
  x21: ffff000008bb1d58 x20: ffff7dfffef00000
  x19: ffff800009c30fb8 x18: 0000000000000001
  x17: 00000000000152d0 x16: 00000000014012d0
  x15: 0000000000000000 x14: 0720072007200720
  x13: 0720072007200720 x12: 0720072007200720
  x11: 0720072007300730 x10: 00000000000000ae
  x9 : 0000000000000000 x8 : ffff7dffff000000
  x7 : 0000000000000000 x6 : 0000000000000100
  x5 : 0000000000000000 x4 : 000000007b906000
  x3 : ffff80007c61a880 x2 : ffff7dfffeefffff
  x1 : 0000000040000000 x0 : 00e80000fe100f07
  Process kworker/0:1 (pid: 39, stack limit = 0x        (ptrval))
  Call trace:
   ioremap_page_range+0x370/0x3c8
   pci_remap_iospace+0x7c/0xac
   pci_parse_request_of_pci_ranges+0x13c/0x190
   rcar_pcie_probe+0x4c/0xb04
   platform_drv_probe+0x50/0xbc
   driver_probe_device+0x21c/0x308
   __device_attach_driver+0x98/0xc8
   bus_for_each_drv+0x54/0x94
   __device_attach+0xc4/0x12c
   device_initial_probe+0x10/0x18
   bus_probe_device+0x90/0x98
   deferred_probe_work_func+0xb0/0x150
   process_one_work+0x12c/0x29c
   worker_thread+0x200/0x3fc
   kthread+0x108/0x134
   ret_from_fork+0x10/0x18
  Code: f9004ba2 54000080 aa0003fb 17ffff48 (d4210000)
---
 drivers/pci/host/pci-aardvark.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
@@ -932,7 +932,7 @@ static int advk_pcie_parse_request_of_pc
 					     0,	0xF8000000, 0,
 					     lower_32_bits(res->start),
 					     OB_PCIE_IO);
-			err = pci_remap_iospace(res, iobase);
+			err = devm_pci_remap_iospace(dev, res, iobase);
 			if (err) {
 				dev_warn(dev, "error %d: failed to map resource %pR\n",
 					 err, res);

---
 drivers/pci/host/pci-aardvark.c |   13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)
@@ -789,6 +789,7 @@ static int advk_pcie_init_irq_domain(str
 	struct device_node *node = dev->of_node;
 	struct device_node *pcie_intc_node;
 	struct irq_chip *irq_chip;
+	int ret = 0;
 
 	raw_spin_lock_init(&pcie->irq_lock);
 

@@ -803,8 +804,8 @@ static int advk_pcie_init_irq_domain(str
 	irq_chip->name = devm_kasprintf(dev, GFP_KERNEL, "%s-irq",
 					dev_name(dev));
 	if (!irq_chip->name) {
-		of_node_put(pcie_intc_node);
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto out_put_node;
 	}
 
 	irq_chip->irq_mask = advk_pcie_irq_mask;

@@ -816,11 +817,13 @@ static int advk_pcie_init_irq_domain(str
 				      &advk_pcie_irq_domain_ops, pcie);
 	if (!pcie->irq_domain) {
 		dev_err(dev, "Failed to get a INTx IRQ domain\n");
-		of_node_put(pcie_intc_node);
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto out_put_node;
 	}
 
-	return 0;
+out_put_node:
+	of_node_put(pcie_intc_node);
+	return ret;
 }
 
 static void advk_pcie_remove_irq_domain(struct advk_pcie *pcie)

    ...
    pinctrl_bind_pins() /* Here pin goes from gpio to PCIE reset
                           function and PERST# is asserted */
    ...
    drv->probe()
---
 drivers/pci/host/pci-aardvark.c |    8 ++++++++
 1 file changed, 8 insertions(+)
@@ -362,6 +362,14 @@ static void advk_pcie_setup_hw(struct ad
 	reg |= PIO_CTRL_ADDR_WIN_DISABLE;
 	advk_writel(pcie, reg, PIO_CTRL);
 
+	/*
+	 * PERST# signal could have been asserted by pinctrl subsystem before
+	 * probe() callback has been called, making the endpoint going into
+	 * fundamental reset. As required by PCI Express spec a delay for at
+	 * least 100ms after such a reset before link training is needed.
+	 */
+	msleep(PCI_PM_D3COLD_WAIT);
+
 	/* Start link training */
 	reg = advk_readl(pcie, PCIE_CORE_LINK_CTRL_STAT_REG);
 	reg |= PCIE_CORE_LINK_TRAINING;

---
 drivers/pci/host/pci-aardvark.c |   15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)
@@ -324,11 +324,6 @@ static void advk_pcie_setup_hw(struct ad
 	reg |= LANE_COUNT_1;
 	advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG);
 
-	/* Enable link training */
-	reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG);
-	reg |= LINK_TRAINING_EN;
-	advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG);
-
 	/* Enable MSI */
 	reg = advk_readl(pcie, PCIE_CORE_CTRL2_REG);
 	reg |= PCIE_CORE_CTRL2_MSI_ENABLE;

@@ -370,7 +365,15 @@ static void advk_pcie_setup_hw(struct ad
 	 */
 	msleep(PCI_PM_D3COLD_WAIT);
 
-	/* Start link training */
+	/* Enable link training */
+	reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG);
+	reg |= LINK_TRAINING_EN;
+	advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG);
+
+	/*
+	 * Start link training immediately after enabling it.
+	 * This solves problems for some buggy cards.
+	 */
 	reg = advk_readl(pcie, PCIE_CORE_LINK_CTRL_STAT_REG);
 	reg |= PCIE_CORE_LINK_TRAINING;
 	advk_writel(pcie, reg, PCIE_CORE_LINK_CTRL_STAT_REG);

---
 drivers/pci/host/pci-aardvark.c |  114 +++++++++++++++++++++++++++++++---------
 1 file changed, 89 insertions(+), 25 deletions(-)
@@ -36,6 +36,7 @@
 #define PCIE_CORE_LINK_CTRL_STAT_REG				0xd0
 #define     PCIE_CORE_LINK_L0S_ENTRY				BIT(0)
 #define     PCIE_CORE_LINK_TRAINING				BIT(5)
+#define     PCIE_CORE_LINK_SPEED_SHIFT				16
 #define     PCIE_CORE_LINK_WIDTH_SHIFT				20
 #define PCIE_CORE_ERR_CAPCTL_REG				0x118
 #define     PCIE_CORE_ERR_CAPCTL_ECRC_CHK_TX			BIT(5)

@@ -212,6 +213,7 @@ struct advk_pcie {
 	struct mutex msi_used_lock;
 	u16 msi_msg;
 	int root_bus_nr;
+	int link_gen;
 };
 
 static inline void advk_writel(struct advk_pcie *pcie, u32 val, u64 reg)

@@ -235,20 +237,16 @@ static int advk_pcie_link_up(struct advk
 
 static int advk_pcie_wait_for_link(struct advk_pcie *pcie)
 {
-	struct device *dev = &pcie->pdev->dev;
 	int retries;
 
 	/* check if the link is up or not */
 	for (retries = 0; retries < LINK_WAIT_MAX_RETRIES; retries++) {
-		if (advk_pcie_link_up(pcie)) {
-			dev_info(dev, "link up\n");
+		if (advk_pcie_link_up(pcie))
 			return 0;
-		}
 
 		usleep_range(LINK_WAIT_USLEEP_MIN, LINK_WAIT_USLEEP_MAX);
 	}
 
-	dev_err(dev, "link never came up\n");
 	return -ETIMEDOUT;
 }
 

@@ -272,6 +270,85 @@ static void advk_pcie_set_ob_win(struct
 	advk_writel(pcie, match_ls | BIT(0), OB_WIN_MATCH_LS(win_num));
 }
 
+static int advk_pcie_train_at_gen(struct advk_pcie *pcie, int gen)
+{
+	int ret, neg_gen;
+	u32 reg;
+
+	/* Setup link speed */
+	reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG);
+	reg &= ~PCIE_GEN_SEL_MSK;
+	if (gen == 3)
+		reg |= SPEED_GEN_3;
+	else if (gen == 2)
+		reg |= SPEED_GEN_2;
+	else
+		reg |= SPEED_GEN_1;
+	advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG);
+
+	/*
+	 * Enable link training. This is not needed in every call to this
+	 * function, just once suffices, but it does not break anything either.
+	 */
+	reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG);
+	reg |= LINK_TRAINING_EN;
+	advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG);
+
+	/*
+	 * Start link training immediately after enabling it.
+	 * This solves problems for some buggy cards.
+	 */
+	reg = advk_readl(pcie, PCIE_CORE_LINK_CTRL_STAT_REG);
+	reg |= PCIE_CORE_LINK_TRAINING;
+	advk_writel(pcie, reg, PCIE_CORE_LINK_CTRL_STAT_REG);
+
+	ret = advk_pcie_wait_for_link(pcie);
+	if (ret)
+		return ret;
+
+	reg = advk_readl(pcie, PCIE_CORE_LINK_CTRL_STAT_REG);
+	neg_gen = (reg >> PCIE_CORE_LINK_SPEED_SHIFT) & 0xf;
+
+	return neg_gen;
+}
+
+static void advk_pcie_train_link(struct advk_pcie *pcie)
+{
+	struct device *dev = &pcie->pdev->dev;
+	int neg_gen = -1, gen;
+
+	/*
+	 * Try link training at link gen specified by device tree property
+	 * 'max-link-speed'. If this fails, iteratively train at lower gen.
+	 */
+	for (gen = pcie->link_gen; gen > 0; --gen) {
+		neg_gen = advk_pcie_train_at_gen(pcie, gen);
+		if (neg_gen > 0)
+			break;
+	}
+
+	if (neg_gen < 0)
+		goto err;
+
+	/*
+	 * After successful training if negotiated gen is lower than requested,
+	 * train again on negotiated gen. This solves some stability issues for
+	 * some buggy gen1 cards.
+	 */
+	if (neg_gen < gen) {
+		gen = neg_gen;
+		neg_gen = advk_pcie_train_at_gen(pcie, gen);
+	}
+
+	if (neg_gen == gen) {
+		dev_info(dev, "link up at gen %i\n", gen);
+		return;
+	}
+
+err:
+	dev_err(dev, "link never came up\n");
+}
+
 static void advk_pcie_setup_hw(struct advk_pcie *pcie)
 {
 	u32 reg;

@@ -312,12 +389,6 @@ static void advk_pcie_setup_hw(struct ad
 		PCIE_CORE_CTRL2_TD_ENABLE;
 	advk_writel(pcie, reg, PCIE_CORE_CTRL2_REG);
 
-	/* Set GEN2 */
-	reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG);
-	reg &= ~PCIE_GEN_SEL_MSK;
-	reg |= SPEED_GEN_2;
-	advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG);
-
 	/* Set lane X1 */
 	reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG);
 	reg &= ~LANE_CNT_MSK;

@@ -365,20 +436,7 @@ static void advk_pcie_setup_hw(struct ad
 	 */
 	msleep(PCI_PM_D3COLD_WAIT);
 
-	/* Enable link training */
-	reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG);
-	reg |= LINK_TRAINING_EN;
-	advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG);
-
-	/*
-	 * Start link training immediately after enabling it.
-	 * This solves problems for some buggy cards.
-	 */
-	reg = advk_readl(pcie, PCIE_CORE_LINK_CTRL_STAT_REG);
-	reg |= PCIE_CORE_LINK_TRAINING;
-	advk_writel(pcie, reg, PCIE_CORE_LINK_CTRL_STAT_REG);
-
-	advk_pcie_wait_for_link(pcie);
+	advk_pcie_train_link(pcie);
 
 	reg = advk_readl(pcie, PCIE_CORE_CMD_STATUS_REG);
 	reg |= PCIE_CORE_CMD_MEM_ACCESS_EN |

@@ -1017,6 +1075,12 @@ static int advk_pcie_probe(struct platfo
 		return ret;
 	}
 
+	ret = of_pci_get_max_link_speed(dev->of_node);
+	if (ret <= 0 || ret > 3)
+		pcie->link_gen = 3;
+	else
+		pcie->link_gen = ret;
+
 	advk_pcie_setup_hw(pcie);
 
 	ret = advk_pcie_init_irq_domain(pcie);

---
 drivers/pci/host/pci-aardvark.c |   44 +++++++++++++++++++++++++++++++++++++++-
 1 file changed, 43 insertions(+), 1 deletion(-)
@@ -12,6 +12,7 @@
  */
 
 #include <linux/delay.h>
+#include <linux/gpio.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/irqdomain.h>

@@ -20,6 +21,7 @@
 #include <linux/init.h>
 #include <linux/platform_device.h>
 #include <linux/of_address.h>
+#include <linux/of_gpio.h>
 #include <linux/of_pci.h>
 
 /* PCIe core registers */

@@ -214,6 +216,7 @@ struct advk_pcie {
 	u16 msi_msg;
 	int root_bus_nr;
 	int link_gen;
+	struct gpio_desc *reset_gpio;
 };
 
 static inline void advk_writel(struct advk_pcie *pcie, u32 val, u64 reg)

@@ -349,6 +352,25 @@ err:
 	dev_err(dev, "link never came up\n");
 }
 
+static void advk_pcie_issue_perst(struct advk_pcie *pcie)
+{
+	u32 reg;
+
+	if (!pcie->reset_gpio)
+		return;
+
+	/* PERST does not work for some cards when link training is enabled */
+	reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG);
+	reg &= ~LINK_TRAINING_EN;
+	advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG);
+
+	/* 10ms delay is needed for some cards */
+	dev_info(&pcie->pdev->dev, "issuing PERST via reset GPIO for 10ms\n");
+	gpiod_set_value_cansleep(pcie->reset_gpio, 1);
+	usleep_range(10000, 11000);
+	gpiod_set_value_cansleep(pcie->reset_gpio, 0);
+}
+
 static void advk_pcie_setup_hw(struct advk_pcie *pcie)
 {
 	u32 reg;

@@ -358,6 +380,8 @@ static void advk_pcie_setup_hw(struct ad
 	for (i = 0; i < 8; i++)
 		advk_pcie_set_ob_win(pcie, i, 0, 0, 0, 0, 0, 0, 0);
 
+	advk_pcie_issue_perst(pcie);
+
 	/* Set to Direct mode */
 	reg = advk_readl(pcie, CTRL_CONFIG_REG);
 	reg &= ~(CTRL_MODE_MASK << CTRL_MODE_SHIFT);

@@ -430,7 +454,8 @@ static void advk_pcie_setup_hw(struct ad
 
 	/*
 	 * PERST# signal could have been asserted by pinctrl subsystem before
-	 * probe() callback has been called, making the endpoint going into
+	 * probe() callback has been called or issued explicitly by reset gpio
+	 * function advk_pcie_issue_perst(), making the endpoint going into
 	 * fundamental reset. As required by PCI Express spec a delay for at
 	 * least 100ms after such a reset before link training is needed.
 	 */

@@ -1075,6 +1100,23 @@ static int advk_pcie_probe(struct platfo
 		return ret;
 	}
 
+	pcie->reset_gpio = devm_fwnode_get_index_gpiod_from_child(dev, "reset",
+								  0,
+								  dev_fwnode(dev),
+								  GPIOD_OUT_LOW,
+								  "pcie1-reset");
+	ret = PTR_ERR_OR_ZERO(pcie->reset_gpio);
+	if (ret) {
+		if (ret == -ENOENT) {
+			pcie->reset_gpio = NULL;
+		} else {
+			if (ret != -EPROBE_DEFER)
+				dev_err(dev, "Failed to get reset-gpio: %i\n",
+					ret);
+			return ret;
+		}
+	}
+
 	ret = of_pci_get_max_link_speed(dev->of_node);
 	if (ret <= 0 || ret > 3)
 		pcie->link_gen = 3;

---
 drivers/pci/host/pci-aardvark.c |   42 ++++++++++++++++++----------------------
 1 file changed, 19 insertions(+), 23 deletions(-)
@@ -29,17 +29,7 @@
 #define     PCIE_CORE_CMD_IO_ACCESS_EN				BIT(0)
 #define     PCIE_CORE_CMD_MEM_ACCESS_EN				BIT(1)
 #define     PCIE_CORE_CMD_MEM_IO_REQ_EN				BIT(2)
-#define PCIE_CORE_DEV_CTRL_STATS_REG				0xc8
-#define     PCIE_CORE_DEV_CTRL_STATS_RELAX_ORDER_DISABLE	(0 << 4)
-#define     PCIE_CORE_DEV_CTRL_STATS_MAX_PAYLOAD_SZ_SHIFT	5
-#define     PCIE_CORE_DEV_CTRL_STATS_SNOOP_DISABLE		(0 << 11)
-#define     PCIE_CORE_DEV_CTRL_STATS_MAX_RD_REQ_SIZE_SHIFT	12
-#define     PCIE_CORE_DEV_CTRL_STATS_MAX_RD_REQ_SZ		0x2
-#define PCIE_CORE_LINK_CTRL_STAT_REG				0xd0
-#define     PCIE_CORE_LINK_L0S_ENTRY				BIT(0)
-#define     PCIE_CORE_LINK_TRAINING				BIT(5)
-#define     PCIE_CORE_LINK_SPEED_SHIFT				16
-#define     PCIE_CORE_LINK_WIDTH_SHIFT				20
+#define PCIE_CORE_PCIEXP_CAP					0xc0
 #define PCIE_CORE_ERR_CAPCTL_REG				0x118
 #define     PCIE_CORE_ERR_CAPCTL_ECRC_CHK_TX			BIT(5)
 #define     PCIE_CORE_ERR_CAPCTL_ECRC_CHK_TX_EN			BIT(6)

@@ -229,6 +219,11 @@ static inline u32 advk_readl(struct advk
 	return readl(pcie->base + reg);
 }
 
+static inline u16 advk_read16(struct advk_pcie *pcie, u64 reg)
+{
+	return advk_readl(pcie, (reg & ~0x3)) >> ((reg & 0x3) * 8);
+}
+
 static int advk_pcie_link_up(struct advk_pcie *pcie)
 {
 	u32 val, ltssm_state;

@@ -301,16 +296,16 @@ static int advk_pcie_train_at_gen(struct
 	 * Start link training immediately after enabling it.
 	 * This solves problems for some buggy cards.
 	 */
-	reg = advk_readl(pcie, PCIE_CORE_LINK_CTRL_STAT_REG);
-	reg |= PCIE_CORE_LINK_TRAINING;
-	advk_writel(pcie, reg, PCIE_CORE_LINK_CTRL_STAT_REG);
+	reg = advk_readl(pcie, PCIE_CORE_PCIEXP_CAP + PCI_EXP_LNKCTL);
+	reg |= PCI_EXP_LNKCTL_RL;
+	advk_writel(pcie, reg, PCIE_CORE_PCIEXP_CAP + PCI_EXP_LNKCTL);
 
 	ret = advk_pcie_wait_for_link(pcie);
 	if (ret)
 		return ret;
 
-	reg = advk_readl(pcie, PCIE_CORE_LINK_CTRL_STAT_REG);
-	neg_gen = (reg >> PCIE_CORE_LINK_SPEED_SHIFT) & 0xf;
+	reg = advk_read16(pcie, PCIE_CORE_PCIEXP_CAP + PCI_EXP_LNKSTA);
+	neg_gen = reg & PCI_EXP_LNKSTA_CLS;
 
 	return neg_gen;
 }

@@ -400,13 +395,14 @@ static void advk_pcie_setup_hw(struct ad
 		PCIE_CORE_ERR_CAPCTL_ECRC_CHCK_RCV;
 	advk_writel(pcie, reg, PCIE_CORE_ERR_CAPCTL_REG);
 
-	/* Set PCIe Device Control and Status 1 PF0 register */
-	reg = PCIE_CORE_DEV_CTRL_STATS_RELAX_ORDER_DISABLE |
-		(7 << PCIE_CORE_DEV_CTRL_STATS_MAX_PAYLOAD_SZ_SHIFT) |
-		PCIE_CORE_DEV_CTRL_STATS_SNOOP_DISABLE |
-		(PCIE_CORE_DEV_CTRL_STATS_MAX_RD_REQ_SZ <<
-		 PCIE_CORE_DEV_CTRL_STATS_MAX_RD_REQ_SIZE_SHIFT);
-	advk_writel(pcie, reg, PCIE_CORE_DEV_CTRL_STATS_REG);
+	/* Set PCIe Device Control register */
+	reg = advk_readl(pcie, PCIE_CORE_PCIEXP_CAP + PCI_EXP_DEVCTL);
+	reg &= ~PCI_EXP_DEVCTL_RELAX_EN;
+	reg &= ~PCI_EXP_DEVCTL_NOSNOOP_EN;
+	reg &= ~PCI_EXP_DEVCTL_READRQ;
+	reg |= PCI_EXP_DEVCTL_PAYLOAD; /* Set max payload size */
+	reg |= PCI_EXP_DEVCTL_READRQ_512B;
+	advk_writel(pcie, reg, PCIE_CORE_PCIEXP_CAP + PCI_EXP_DEVCTL);
 
 	/* Program PCIe Control 2 to disable strict ordering */
 	reg = PCIE_CORE_CTRL2_RESERVED |

---
 drivers/pci/host/pci-aardvark.c |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)
@@ -631,8 +631,10 @@ static int advk_pcie_rd_conf(struct pci_
 	advk_writel(pcie, 1, PIO_START);
 
 	ret = advk_pcie_wait_pio(pcie);
-	if (ret < 0)
+	if (ret < 0) {
+		*val = 0xffffffff;
 		return PCIBIOS_SET_FAILED;
+	}
 
 	/* Check PIO status and get the read result */
 	ret = advk_pcie_check_pio_status(pcie, val);

---
 drivers/pci/host/pci-aardvark.c |   13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)
@@ -592,6 +592,15 @@ static bool advk_pcie_pio_is_running(str
 	return false;
 }
 
+static bool advk_pcie_valid_device(struct advk_pcie *pcie, struct pci_bus *bus,
+				  int devfn)
+{
+	if ((bus->number == pcie->root_bus_nr) && PCI_SLOT(devfn) != 0)
+		return false;
+
+	return true;
+}
+
 static int advk_pcie_rd_conf(struct pci_bus *bus, u32 devfn,
 			     int where, int size, u32 *val)
 {

@@ -599,7 +608,7 @@ static int advk_pcie_rd_conf(struct pci_
 	u32 reg;
 	int ret;
 
-	if ((bus->number == pcie->root_bus_nr) && PCI_SLOT(devfn) != 0) {
+	if (!advk_pcie_valid_device(pcie, bus, devfn)) {
 		*val = 0xffffffff;
 		return PCIBIOS_DEVICE_NOT_FOUND;
 	}

@@ -660,7 +669,7 @@ static int advk_pcie_wr_conf(struct pci_
 	int offset;
 	int ret;
 
-	if ((bus->number == pcie->root_bus_nr) && PCI_SLOT(devfn) != 0)
+	if (!advk_pcie_valid_device(pcie, bus, devfn))
 		return PCIBIOS_DEVICE_NOT_FOUND;
 
 	if (where % size)

---
 drivers/pci/host/pci-aardvark.c |    7 +++++++
 1 file changed, 7 insertions(+)
@@ -598,6 +598,13 @@ static bool advk_pcie_valid_device(struc
 	if ((bus->number == pcie->root_bus_nr) && PCI_SLOT(devfn) != 0)
 		return false;
 
+	/*
+	 * If the link goes down after we check for link-up, nothing bad
+	 * happens but the config access times out.
+	 */
+	if (bus->number != pcie->root_bus_nr && !advk_pcie_link_up(pcie))
+		return false;
+
 	return true;
 }
 

---
 drivers/pci/host/pci-aardvark.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
@@ -12,7 +12,7 @@
  */
 
 #include <linux/delay.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/irqdomain.h>

---
 drivers/pci/host/pci-aardvark.c |   64 +++++++++++++++++++++-------------------
 1 file changed, 34 insertions(+), 30 deletions(-)
@@ -268,6 +268,25 @@ static void advk_pcie_set_ob_win(struct
 	advk_writel(pcie, match_ls | BIT(0), OB_WIN_MATCH_LS(win_num));
 }
 
+static void advk_pcie_issue_perst(struct advk_pcie *pcie)
+{
+	u32 reg;
+
+	if (!pcie->reset_gpio)
+		return;
+
+	/* PERST does not work for some cards when link training is enabled */
+	reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG);
+	reg &= ~LINK_TRAINING_EN;
+	advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG);
+
+	/* 10ms delay is needed for some cards */
+	dev_info(&pcie->pdev->dev, "issuing PERST via reset GPIO for 10ms\n");
+	gpiod_set_value_cansleep(pcie->reset_gpio, 1);
+	usleep_range(10000, 11000);
+	gpiod_set_value_cansleep(pcie->reset_gpio, 0);
+}
+
 static int advk_pcie_train_at_gen(struct advk_pcie *pcie, int gen)
 {
 	int ret, neg_gen;

@@ -316,6 +335,21 @@ static void advk_pcie_train_link(struct
 	int neg_gen = -1, gen;
 
 	/*
+	 * Reset PCIe card via PERST# signal. Some cards are not detected
+	 * during link training when they are in some non-initial state.
+	 */
+	advk_pcie_issue_perst(pcie);
+
+	/*
+	 * PERST# signal could have been asserted by pinctrl subsystem before
+	 * probe() callback has been called or issued explicitly by reset gpio
+	 * function advk_pcie_issue_perst(), making the endpoint going into
+	 * fundamental reset. As required by PCI Express spec a delay for at
+	 * least 100ms after such a reset before link training is needed.
+	 */
+	msleep(PCI_PM_D3COLD_WAIT);
+
+	/*
 	 * Try link training at link gen specified by device tree property
 	 * 'max-link-speed'. If this fails, iteratively train at lower gen.
 	 */

@@ -347,25 +381,6 @@ err:
 	dev_err(dev, "link never came up\n");
 }
 
-static void advk_pcie_issue_perst(struct advk_pcie *pcie)
-{
-	u32 reg;
-
-	if (!pcie->reset_gpio)
-		return;
-
-	/* PERST does not work for some cards when link training is enabled */
-	reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG);
-	reg &= ~LINK_TRAINING_EN;
-	advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG);
-
-	/* 10ms delay is needed for some cards */
-	dev_info(&pcie->pdev->dev, "issuing PERST via reset GPIO for 10ms\n");
-	gpiod_set_value_cansleep(pcie->reset_gpio, 1);
-	usleep_range(10000, 11000);
-	gpiod_set_value_cansleep(pcie->reset_gpio, 0);
-}
-
 static void advk_pcie_setup_hw(struct advk_pcie *pcie)
 {
 	u32 reg;

@@ -375,8 +390,6 @@ static void advk_pcie_setup_hw(struct ad
 	for (i = 0; i < 8; i++)
 		advk_pcie_set_ob_win(pcie, i, 0, 0, 0, 0, 0, 0, 0);
 
-	advk_pcie_issue_perst(pcie);
-
 	/* Set to Direct mode */
 	reg = advk_readl(pcie, CTRL_CONFIG_REG);
 	reg &= ~(CTRL_MODE_MASK << CTRL_MODE_SHIFT);

@@ -448,15 +461,6 @@ static void advk_pcie_setup_hw(struct ad
 	reg |= PIO_CTRL_ADDR_WIN_DISABLE;
 	advk_writel(pcie, reg, PIO_CTRL);
 
-	/*
-	 * PERST# signal could have been asserted by pinctrl subsystem before
-	 * probe() callback has been called or issued explicitly by reset gpio
-	 * function advk_pcie_issue_perst(), making the endpoint going into
-	 * fundamental reset. As required by PCI Express spec a delay for at
-	 * least 100ms after such a reset before link training is needed.
-	 */
-	msleep(PCI_PM_D3COLD_WAIT);
-
 	advk_pcie_train_link(pcie);
 
 	reg = advk_readl(pcie, PCIE_CORE_CMD_STATUS_REG);

---
 drivers/pci/host/pci-aardvark.c |    9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)
@@ -275,7 +275,14 @@ static void advk_pcie_issue_perst(struct
 	if (!pcie->reset_gpio)
 		return;
 
-	/* PERST does not work for some cards when link training is enabled */
+	/*
+	 * As required by PCI Express spec (PCI Express Base Specification, REV.
+	 * 4.0 PCI Express, February 19 2014, 6.6.1 Conventional Reset) a delay
+	 * for at least 100ms after de-asserting PERST# signal is needed before
+	 * link training is enabled. So ensure that link training is disabled
+	 * prior de-asserting PERST# signal to fulfill that PCI Express spec
+	 * requirement.
+	 */
 	reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG);
 	reg &= ~LINK_TRAINING_EN;
 	advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG);

---
 drivers/pci/host/pci-aardvark.c |   55 ----------------------------------------
 1 file changed, 55 deletions(-)
@@ -107,24 +107,6 @@
 #define PCIE_MSI_PAYLOAD_REG			(CONTROL_BASE_ADDR + 0x9C)
 #define     PCIE_MSI_DATA_MASK			GENMASK(15, 0)
 
-/* PCIe window configuration */
-#define OB_WIN_BASE_ADDR			0x4c00
-#define OB_WIN_BLOCK_SIZE			0x20
-#define OB_WIN_REG_ADDR(win, offset)		(OB_WIN_BASE_ADDR + \
-						 OB_WIN_BLOCK_SIZE * (win) + \
-						 (offset))
-#define OB_WIN_MATCH_LS(win)			OB_WIN_REG_ADDR(win, 0x00)
-#define OB_WIN_MATCH_MS(win)			OB_WIN_REG_ADDR(win, 0x04)
-#define OB_WIN_REMAP_LS(win)			OB_WIN_REG_ADDR(win, 0x08)
-#define OB_WIN_REMAP_MS(win)			OB_WIN_REG_ADDR(win, 0x0c)
-#define OB_WIN_MASK_LS(win)			OB_WIN_REG_ADDR(win, 0x10)
-#define OB_WIN_MASK_MS(win)			OB_WIN_REG_ADDR(win, 0x14)
-#define OB_WIN_ACTIONS(win)			OB_WIN_REG_ADDR(win, 0x18)
-
-/* PCIe window types */
-#define OB_PCIE_MEM				0x0
-#define OB_PCIE_IO				0x4
-
 /* LMI registers base address and register offsets */
 #define LMI_BASE_ADDR				0x6000
 #define CFG_REG					(LMI_BASE_ADDR + 0x0)

@@ -248,26 +230,6 @@ static int advk_pcie_wait_for_link(struc
 	return -ETIMEDOUT;
 }
 
-/*
- * Set PCIe address window register which could be used for memory
- * mapping.
- */
-static void advk_pcie_set_ob_win(struct advk_pcie *pcie,
-				 u32 win_num, u32 match_ms,
-				 u32 match_ls, u32 mask_ms,
-				 u32 mask_ls, u32 remap_ms,
-				 u32 remap_ls, u32 action)
-{
-	advk_writel(pcie, match_ls, OB_WIN_MATCH_LS(win_num));
-	advk_writel(pcie, match_ms, OB_WIN_MATCH_MS(win_num));
-	advk_writel(pcie, mask_ms, OB_WIN_MASK_MS(win_num));
-	advk_writel(pcie, mask_ls, OB_WIN_MASK_LS(win_num));
-	advk_writel(pcie, remap_ms, OB_WIN_REMAP_MS(win_num));
-	advk_writel(pcie, remap_ls, OB_WIN_REMAP_LS(win_num));
-	advk_writel(pcie, action, OB_WIN_ACTIONS(win_num));
-	advk_writel(pcie, match_ls | BIT(0), OB_WIN_MATCH_LS(win_num));
-}
-
 static void advk_pcie_issue_perst(struct advk_pcie *pcie)
 {
 	u32 reg;

@@ -391,11 +353,6 @@ err:
 static void advk_pcie_setup_hw(struct advk_pcie *pcie)
 {
 	u32 reg;
-	int i;
-
-	/* Point PCIe unit MBUS decode windows to DRAM space */
-	for (i = 0; i < 8; i++)
-		advk_pcie_set_ob_win(pcie, i, 0, 0, 0, 0, 0, 0, 0);
 
 	/* Set to Direct mode */
 	reg = advk_readl(pcie, CTRL_CONFIG_REG);

@@ -1048,12 +1005,6 @@ static int advk_pcie_parse_request_of_pc
 
 		switch (resource_type(res)) {
 		case IORESOURCE_IO:
-			advk_pcie_set_ob_win(pcie, 1,
-					     upper_32_bits(res->start),
-					     lower_32_bits(res->start),
-					     0,	0xF8000000, 0,
-					     lower_32_bits(res->start),
-					     OB_PCIE_IO);
 			err = devm_pci_remap_iospace(dev, res, iobase);
 			if (err) {
 				dev_warn(dev, "error %d: failed to map resource %pR\n",

@@ -1062,12 +1013,6 @@ static int advk_pcie_parse_request_of_pc
 			}
 			break;
 		case IORESOURCE_MEM:
-			advk_pcie_set_ob_win(pcie, 0,
-					     upper_32_bits(res->start),
-					     lower_32_bits(res->start),
-					     0x0, 0xF8000000, 0,
-					     lower_32_bits(res->start),
-					     (2 << 20) | OB_PCIE_MEM);
 			res_valid |= !(res->flags & IORESOURCE_PREFETCH);
 			break;
 		case IORESOURCE_BUS:

---
 drivers/pci/host/pci-aardvark.c |  190 +++++++++++++++++++++++++++++++++++++++-
 1 file changed, 189 insertions(+), 1 deletion(-)
@@ -107,6 +107,46 @@
 #define PCIE_MSI_PAYLOAD_REG			(CONTROL_BASE_ADDR + 0x9C)
 #define     PCIE_MSI_DATA_MASK			GENMASK(15, 0)
 
+/* PCIe window configuration */
+#define OB_WIN_BASE_ADDR			0x4c00
+#define OB_WIN_BLOCK_SIZE			0x20
+#define OB_WIN_COUNT				8
+#define OB_WIN_REG_ADDR(win, offset)		(OB_WIN_BASE_ADDR + \
+						 OB_WIN_BLOCK_SIZE * (win) + \
+						 (offset))
+#define OB_WIN_MATCH_LS(win)			OB_WIN_REG_ADDR(win, 0x00)
+#define     OB_WIN_ENABLE			BIT(0)
+#define OB_WIN_MATCH_MS(win)			OB_WIN_REG_ADDR(win, 0x04)
+#define OB_WIN_REMAP_LS(win)			OB_WIN_REG_ADDR(win, 0x08)
+#define OB_WIN_REMAP_MS(win)			OB_WIN_REG_ADDR(win, 0x0c)
+#define OB_WIN_MASK_LS(win)			OB_WIN_REG_ADDR(win, 0x10)
+#define OB_WIN_MASK_MS(win)			OB_WIN_REG_ADDR(win, 0x14)
+#define OB_WIN_ACTIONS(win)			OB_WIN_REG_ADDR(win, 0x18)
+#define OB_WIN_DEFAULT_ACTIONS			(OB_WIN_ACTIONS(OB_WIN_COUNT-1) + 0x4)
+#define     OB_WIN_FUNC_NUM_MASK		GENMASK(31, 24)
+#define     OB_WIN_FUNC_NUM_SHIFT		24
+#define     OB_WIN_FUNC_NUM_ENABLE		BIT(23)
+#define     OB_WIN_BUS_NUM_BITS_MASK		GENMASK(22, 20)
+#define     OB_WIN_BUS_NUM_BITS_SHIFT		20
+#define     OB_WIN_MSG_CODE_ENABLE		BIT(22)
+#define     OB_WIN_MSG_CODE_MASK		GENMASK(21, 14)
+#define     OB_WIN_MSG_CODE_SHIFT		14
+#define     OB_WIN_MSG_PAYLOAD_LEN		BIT(12)
+#define     OB_WIN_ATTR_ENABLE			BIT(11)
+#define     OB_WIN_ATTR_TC_MASK			GENMASK(10, 8)
+#define     OB_WIN_ATTR_TC_SHIFT		8
+#define     OB_WIN_ATTR_RELAXED			BIT(7)
+#define     OB_WIN_ATTR_NOSNOOP			BIT(6)
+#define     OB_WIN_ATTR_POISON			BIT(5)
+#define     OB_WIN_ATTR_IDO			BIT(4)
+#define     OB_WIN_TYPE_MASK			GENMASK(3, 0)
+#define     OB_WIN_TYPE_SHIFT			0
+#define     OB_WIN_TYPE_MEM			0x0
+#define     OB_WIN_TYPE_IO			0x4
+#define     OB_WIN_TYPE_CONFIG_TYPE0		0x8
+#define     OB_WIN_TYPE_CONFIG_TYPE1		0x9
+#define     OB_WIN_TYPE_MSG			0xc
+
 /* LMI registers base address and register offsets */
 #define LMI_BASE_ADDR				0x6000
 #define CFG_REG					(LMI_BASE_ADDR + 0x0)

@@ -175,6 +215,13 @@ struct advk_pcie {
 	struct platform_device *pdev;
 	void __iomem *base;
 	struct list_head resources;
+	struct {
+		phys_addr_t match;
+		phys_addr_t remap;
+		phys_addr_t mask;
+		u32 actions;
+	} wins[OB_WIN_COUNT];
+	u8 wins_count;
 	struct irq_domain *irq_domain;
 	struct irq_chip irq_chip;
 	raw_spinlock_t irq_lock;

@@ -350,9 +397,39 @@ err:
 	dev_err(dev, "link never came up\n");
 }
 
+/*
+ * Set PCIe address window register which could be used for memory
+ * mapping.
+ */
+static void advk_pcie_set_ob_win(struct advk_pcie *pcie, u8 win_num,
+				 phys_addr_t match, phys_addr_t remap,
+				 phys_addr_t mask, u32 actions)
+{
+	advk_writel(pcie, OB_WIN_ENABLE |
+			  lower_32_bits(match), OB_WIN_MATCH_LS(win_num));
+	advk_writel(pcie, upper_32_bits(match), OB_WIN_MATCH_MS(win_num));
+	advk_writel(pcie, lower_32_bits(remap), OB_WIN_REMAP_LS(win_num));
+	advk_writel(pcie, upper_32_bits(remap), OB_WIN_REMAP_MS(win_num));
+	advk_writel(pcie, lower_32_bits(mask), OB_WIN_MASK_LS(win_num));
+	advk_writel(pcie, upper_32_bits(mask), OB_WIN_MASK_MS(win_num));
+	advk_writel(pcie, actions, OB_WIN_ACTIONS(win_num));
+}
+
+static void advk_pcie_disable_ob_win(struct advk_pcie *pcie, u8 win_num)
+{
+	advk_writel(pcie, 0, OB_WIN_MATCH_LS(win_num));
+	advk_writel(pcie, 0, OB_WIN_MATCH_MS(win_num));
+	advk_writel(pcie, 0, OB_WIN_REMAP_LS(win_num));
+	advk_writel(pcie, 0, OB_WIN_REMAP_MS(win_num));
+	advk_writel(pcie, 0, OB_WIN_MASK_LS(win_num));
+	advk_writel(pcie, 0, OB_WIN_MASK_MS(win_num));
+	advk_writel(pcie, 0, OB_WIN_ACTIONS(win_num));
+}
+
 static void advk_pcie_setup_hw(struct advk_pcie *pcie)
 {
 	u32 reg;
+	int i;
 
 	/* Set to Direct mode */
 	reg = advk_readl(pcie, CTRL_CONFIG_REG);

@@ -416,15 +493,51 @@ static void advk_pcie_setup_hw(struct ad
 	reg = PCIE_IRQ_ALL_MASK & (~PCIE_IRQ_ENABLE_INTS_MASK);
 	advk_writel(pcie, reg, HOST_CTRL_INT_MASK_REG);
 
+	/*
+	 * Enable AXI address window location generation:
+	 * When it is enabled, the default outbound window
+	 * configurations (Default User Field: 0xD0074CFC)
+	 * are used to transparent address translation for
+	 * the outbound transactions. Thus, PCIe address
+	 * windows are not required for transparent memory
+	 * access when default outbound window configuration
+	 * is set for memory access.
+	 */
 	reg = advk_readl(pcie, PCIE_CORE_CTRL2_REG);
 	reg |= PCIE_CORE_CTRL2_OB_WIN_ENABLE;
 	advk_writel(pcie, reg, PCIE_CORE_CTRL2_REG);
 
-	/* Bypass the address window mapping for PIO */
+	/*
+	 * Set memory access in Default User Field so it
+	 * is not required to configure PCIe address for
+	 * transparent memory access.
+	 */
+	advk_writel(pcie, OB_WIN_TYPE_MEM, OB_WIN_DEFAULT_ACTIONS);
+
+	/*
+	 * Bypass the address window mapping for PIO:
+	 * Since PIO access already contains all required
+	 * info over AXI interface by PIO registers, the
+	 * address window is not required.
+	 */
 	reg = advk_readl(pcie, PIO_CTRL);
 	reg |= PIO_CTRL_ADDR_WIN_DISABLE;
 	advk_writel(pcie, reg, PIO_CTRL);
 
+	/*
+	 * Configure PCIe address windows for non-memory or
+	 * non-transparent access as by default PCIe uses
+	 * transparent memory access.
+	 */
+	for (i = 0; i < pcie->wins_count; i++)
+		advk_pcie_set_ob_win(pcie, i,
+				     pcie->wins[i].match, pcie->wins[i].remap,
+				     pcie->wins[i].mask, pcie->wins[i].actions);
+
+	/* Disable remaining PCIe outbound windows */
+	for (i = pcie->wins_count; i < OB_WIN_COUNT; i++)
+		advk_pcie_disable_ob_win(pcie, i);
+
 	advk_pcie_train_link(pcie);
 
 	reg = advk_readl(pcie, PCIE_CORE_CMD_STATUS_REG);

@@ -1041,6 +1154,7 @@ static int advk_pcie_probe(struct platfo
 	struct resource *res;
 	struct pci_bus *bus, *child;
 	struct pci_host_bridge *bridge;
+	struct resource_entry *entry;
 	int ret, irq;
 
 	bridge = devm_pci_alloc_host_bridge(dev, sizeof(struct advk_pcie));

@@ -1070,6 +1184,80 @@ static int advk_pcie_probe(struct platfo
 		return ret;
 	}
 
+	resource_list_for_each_entry(entry, &pcie->resources) {
+		resource_size_t start = entry->res->start;
+		resource_size_t size = resource_size(entry->res);
+		unsigned long type = resource_type(entry->res);
+		u64 win_size;
+
+		/*
+		 * Aardvark hardware allows to configure also PCIe window
+		 * for config type 0 and type 1 mapping, but driver uses
+		 * only PIO for issuing configuration transfers which does
+		 * not use PCIe window configuration.
+		 */
+		if (type != IORESOURCE_MEM && type != IORESOURCE_MEM_64 &&
+		    type != IORESOURCE_IO)
+			continue;
+
+		/*
+		 * Skip transparent memory resources. Default outbound access
+		 * configuration is set to transparent memory access so it
+		 * does not need window configuration.
+		 */
+		if ((type == IORESOURCE_MEM || type == IORESOURCE_MEM_64) &&
+		    entry->offset == 0)
+			continue;
+
+		/*
+		 * The n-th PCIe window is configured by tuple (match, remap, mask)
+		 * and an access to address A uses this window if A matches the
+		 * match with given mask.
+		 * So every PCIe window size must be a power of two and every start
+		 * address must be aligned to window size. Minimal size is 64 KiB
+		 * because lower 16 bits of mask must be zero. Remapped address
+		 * may have set only bits from the mask.
+		 */
+		while (pcie->wins_count < OB_WIN_COUNT && size > 0) {
+			/* Calculate the largest aligned window size */
+			win_size = (1ULL << (fls64(size)-1)) |
+				   (start ? (1ULL << __ffs64(start)) : 0);
+			win_size = 1ULL << __ffs64(win_size);
+			if (win_size < 0x10000)
+				break;
+
+			dev_dbg(dev,
+				"Configuring PCIe window %d: [0x%llx-0x%llx] as %lu\n",
+				pcie->wins_count, (unsigned long long)start,
+				(unsigned long long)start + win_size, type);
+
+			if (type == IORESOURCE_IO) {
+				pcie->wins[pcie->wins_count].actions = OB_WIN_TYPE_IO;
+				pcie->wins[pcie->wins_count].match = pci_pio_to_address(start);
+			} else {
+				pcie->wins[pcie->wins_count].actions = OB_WIN_TYPE_MEM;
+				pcie->wins[pcie->wins_count].match = start;
+			}
+			pcie->wins[pcie->wins_count].remap = start - entry->offset;
+			pcie->wins[pcie->wins_count].mask = ~(win_size - 1);
+
+			if (pcie->wins[pcie->wins_count].remap & (win_size - 1))
+				break;
+
+			start += win_size;
+			size -= win_size;
+			pcie->wins_count++;
+		}
+
+		if (size > 0) {
+			dev_err(&pcie->pdev->dev,
+				"Invalid PCIe region [0x%llx-0x%llx]\n",
+				(unsigned long long)entry->res->start,
+				(unsigned long long)entry->res->end + 1);
+			return -EINVAL;
+		}
+	}
+
 	pcie->reset_gpio = devm_fwnode_get_index_gpiod_from_child(dev, "reset",
 								  0,
 								  dev_fwnode(dev),

    pci 0000:01:00.0: Upstream bridge's Max Payload Size set to 256 (was 16384, max 512)
    pci 0000:01:00.0: Upstream bridge's Max Payload Size set to 256 (was 512, max 512)
---
 drivers/pci/host/pci-aardvark.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
@@ -453,8 +453,9 @@ static void advk_pcie_setup_hw(struct ad
 	reg = advk_readl(pcie, PCIE_CORE_PCIEXP_CAP + PCI_EXP_DEVCTL);
 	reg &= ~PCI_EXP_DEVCTL_RELAX_EN;
 	reg &= ~PCI_EXP_DEVCTL_NOSNOOP_EN;
+	reg &= ~PCI_EXP_DEVCTL_PAYLOAD;
 	reg &= ~PCI_EXP_DEVCTL_READRQ;
-	reg |= PCI_EXP_DEVCTL_PAYLOAD; /* Set max payload size */
+	reg |= PCI_EXP_DEVCTL_PAYLOAD_512B;
 	reg |= PCI_EXP_DEVCTL_READRQ_512B;
 	advk_writel(pcie, reg, PCIE_CORE_PCIEXP_CAP + PCI_EXP_DEVCTL);
 

---
 include/uapi/linux/pci_regs.h |    5 +++++
 1 file changed, 5 insertions(+)
@@ -654,6 +654,11 @@
 #define  PCI_EXP_LNKCAP2_SLS_8_0GB	0x00000008 /* Supported Speed 8.0GT/s */
 #define  PCI_EXP_LNKCAP2_CROSSLINK	0x00000100 /* Crosslink supported */
 #define PCI_EXP_LNKCTL2		48	/* Link Control 2 */
+#define PCI_EXP_LNKCTL2_TLS		0x000f
+#define PCI_EXP_LNKCTL2_TLS_2_5GT	0x0001 /* Supported Speed 2.5GT/s */
+#define PCI_EXP_LNKCTL2_TLS_5_0GT	0x0002 /* Supported Speed 5GT/s */
+#define PCI_EXP_LNKCTL2_TLS_8_0GT	0x0003 /* Supported Speed 8GT/s */
+#define PCI_EXP_LNKCTL2_TLS_16_0GT	0x0004 /* Supported Speed 16GT/s */
 #define PCI_EXP_LNKSTA2		50	/* Link Status 2 */
 #define PCI_CAP_EXP_ENDPOINT_SIZEOF_V2	52	/* v2 endpoints with link end here */
 #define PCI_EXP_SLTCAP2		52	/* Slot Capabilities 2 */

---
 drivers/pci/host/pci-aardvark.c |  119 +++++++++++-----------------------------
 1 file changed, 35 insertions(+), 84 deletions(-)
@@ -248,11 +248,6 @@ static inline u32 advk_readl(struct advk
 	return readl(pcie->base + reg);
 }
 
-static inline u16 advk_read16(struct advk_pcie *pcie, u64 reg)
-{
-	return advk_readl(pcie, (reg & ~0x3)) >> ((reg & 0x3) * 8);
-}
-
 static int advk_pcie_link_up(struct advk_pcie *pcie)
 {
 	u32 val, ltssm_state;

@@ -279,23 +274,9 @@ static int advk_pcie_wait_for_link(struc
 
 static void advk_pcie_issue_perst(struct advk_pcie *pcie)
 {
-	u32 reg;
-
 	if (!pcie->reset_gpio)
 		return;
 
-	/*
-	 * As required by PCI Express spec (PCI Express Base Specification, REV.
-	 * 4.0 PCI Express, February 19 2014, 6.6.1 Conventional Reset) a delay
-	 * for at least 100ms after de-asserting PERST# signal is needed before
-	 * link training is enabled. So ensure that link training is disabled
-	 * prior de-asserting PERST# signal to fulfill that PCI Express spec
-	 * requirement.
-	 */
-	reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG);
-	reg &= ~LINK_TRAINING_EN;
-	advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG);
-
 	/* 10ms delay is needed for some cards */
 	dev_info(&pcie->pdev->dev, "issuing PERST via reset GPIO for 10ms\n");
 	gpiod_set_value_cansleep(pcie->reset_gpio, 1);

@@ -303,54 +284,47 @@ static void advk_pcie_issue_perst(struct
 	gpiod_set_value_cansleep(pcie->reset_gpio, 0);
 }
 
-static int advk_pcie_train_at_gen(struct advk_pcie *pcie, int gen)
+static void advk_pcie_train_link(struct advk_pcie *pcie)
 {
-	int ret, neg_gen;
+	struct device *dev = &pcie->pdev->dev;
 	u32 reg;
+	int ret;
 
-	/* Setup link speed */
+	/*
+	 * Setup PCIe rev / gen compliance based on device tree property
+	 * 'max-link-speed' which also forces maximal link speed.
+	 */
 	reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG);
 	reg &= ~PCIE_GEN_SEL_MSK;
-	if (gen == 3)
+	if (pcie->link_gen == 3)
 		reg |= SPEED_GEN_3;
-	else if (gen == 2)
+	else if (pcie->link_gen == 2)
 		reg |= SPEED_GEN_2;
 	else
 		reg |= SPEED_GEN_1;
 	advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG);
 
 	/*
-	 * Enable link training. This is not needed in every call to this
-	 * function, just once suffices, but it does not break anything either.
-	 */
+	 * Set maximal link speed value also into PCIe Link Control 2 register.
+	 * Armada 3700 Functional Specification says that default value is based
+	 * on SPEED_GEN but tests showed that default value is always 8.0 GT/s.
+	 */
+	reg = advk_readl(pcie, PCIE_CORE_PCIEXP_CAP + PCI_EXP_LNKCTL2);
+	reg &= ~PCI_EXP_LNKCTL2_TLS;
+	if (pcie->link_gen == 3)
+		reg |= PCI_EXP_LNKCTL2_TLS_8_0GT;
+	else if (pcie->link_gen == 2)
+		reg |= PCI_EXP_LNKCTL2_TLS_5_0GT;
+	else
+		reg |= PCI_EXP_LNKCTL2_TLS_2_5GT;
+	advk_writel(pcie, reg, PCIE_CORE_PCIEXP_CAP + PCI_EXP_LNKCTL2);
+
+	/* Enable link training after selecting PCIe generation */
 	reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG);
 	reg |= LINK_TRAINING_EN;
 	advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG);
 
 	/*
-	 * Start link training immediately after enabling it.
-	 * This solves problems for some buggy cards.
-	 */
-	reg = advk_readl(pcie, PCIE_CORE_PCIEXP_CAP + PCI_EXP_LNKCTL);
-	reg |= PCI_EXP_LNKCTL_RL;
-	advk_writel(pcie, reg, PCIE_CORE_PCIEXP_CAP + PCI_EXP_LNKCTL);
-
-	ret = advk_pcie_wait_for_link(pcie);
-	if (ret)
-		return ret;
-
-	reg = advk_read16(pcie, PCIE_CORE_PCIEXP_CAP + PCI_EXP_LNKSTA);
-	neg_gen = reg & PCI_EXP_LNKSTA_CLS;
-
-	return neg_gen;
-}
-
-static void advk_pcie_train_link(struct advk_pcie *pcie)
-{
-	struct device *dev = &pcie->pdev->dev;
-	int neg_gen = -1, gen;
-
-	/*
 	 * Reset PCIe card via PERST# signal. Some cards are not detected
 	 * during link training when they are in some non-initial state.
 	 */

@@ -360,41 +334,18 @@ static void advk_pcie_train_link(struct
 	 * PERST# signal could have been asserted by pinctrl subsystem before
 	 * probe() callback has been called or issued explicitly by reset gpio
 	 * function advk_pcie_issue_perst(), making the endpoint going into
-	 * fundamental reset. As required by PCI Express spec a delay for at
-	 * least 100ms after such a reset before link training is needed.
-	 */
-	msleep(PCI_PM_D3COLD_WAIT);
-
-	/*
-	 * Try link training at link gen specified by device tree property
-	 * 'max-link-speed'. If this fails, iteratively train at lower gen.
-	 */
-	for (gen = pcie->link_gen; gen > 0; --gen) {
-		neg_gen = advk_pcie_train_at_gen(pcie, gen);
-		if (neg_gen > 0)
-			break;
-	}
-
-	if (neg_gen < 0)
-		goto err;
-
-	/*
-	 * After successful training if negotiated gen is lower than requested,
-	 * train again on negotiated gen. This solves some stability issues for
-	 * some buggy gen1 cards.
+	 * fundamental reset. As required by PCI Express spec (PCI Express
+	 * Base Specification, REV. 4.0 PCI Express, February 19 2014, 6.6.1
+	 * Conventional Reset) a delay for at least 100ms after such a reset
+	 * before sending a Configuration Request to the device is needed.
+	 * So wait until PCIe link is up. Function advk_pcie_wait_for_link()
+	 * waits for link at least 900ms.
 	 */
-	if (neg_gen < gen) {
-		gen = neg_gen;
-		neg_gen = advk_pcie_train_at_gen(pcie, gen);
-	}
-
-	if (neg_gen == gen) {
-		dev_info(dev, "link up at gen %i\n", gen);
-		return;
-	}
-
-err:
-	dev_err(dev, "link never came up\n");
+	ret = advk_pcie_wait_for_link(pcie);
+	if (ret < 0)
+		dev_err(dev, "link never came up\n");
+	else
+		dev_info(dev, "link up\n");
 }
 
 /*

---
 drivers/pci/host/pci-aardvark.c |   71 +++++++++++++++++++++++++++++++++++++---
 1 file changed, 67 insertions(+), 4 deletions(-)
@@ -152,9 +152,50 @@
 #define CFG_REG					(LMI_BASE_ADDR + 0x0)
 #define     LTSSM_SHIFT				24
 #define     LTSSM_MASK				0x3f
-#define     LTSSM_L0				0x10
 #define     RC_BAR_CONFIG			0x300
 
+/* LTSSM values in CFG_REG */
+enum {
+	LTSSM_DETECT_QUIET			= 0x0,
+	LTSSM_DETECT_ACTIVE			= 0x1,
+	LTSSM_POLLING_ACTIVE			= 0x2,
+	LTSSM_POLLING_COMPLIANCE		= 0x3,
+	LTSSM_POLLING_CONFIGURATION		= 0x4,
+	LTSSM_CONFIG_LINKWIDTH_START		= 0x5,
+	LTSSM_CONFIG_LINKWIDTH_ACCEPT		= 0x6,
+	LTSSM_CONFIG_LANENUM_ACCEPT		= 0x7,
+	LTSSM_CONFIG_LANENUM_WAIT		= 0x8,
+	LTSSM_CONFIG_COMPLETE			= 0x9,
+	LTSSM_CONFIG_IDLE			= 0xa,
+	LTSSM_RECOVERY_RCVR_LOCK		= 0xb,
+	LTSSM_RECOVERY_SPEED			= 0xc,
+	LTSSM_RECOVERY_RCVR_CFG			= 0xd,
+	LTSSM_RECOVERY_IDLE			= 0xe,
+	LTSSM_L0				= 0x10,
+	LTSSM_RX_L0S_ENTRY			= 0x11,
+	LTSSM_RX_L0S_IDLE			= 0x12,
+	LTSSM_RX_L0S_FTS			= 0x13,
+	LTSSM_TX_L0S_ENTRY			= 0x14,
+	LTSSM_TX_L0S_IDLE			= 0x15,
+	LTSSM_TX_L0S_FTS			= 0x16,
+	LTSSM_L1_ENTRY				= 0x17,
+	LTSSM_L1_IDLE				= 0x18,
+	LTSSM_L2_IDLE				= 0x19,
+	LTSSM_L2_TRANSMIT_WAKE			= 0x1a,
+	LTSSM_DISABLED				= 0x20,
+	LTSSM_LOOPBACK_ENTRY_MASTER		= 0x21,
+	LTSSM_LOOPBACK_ACTIVE_MASTER		= 0x22,
+	LTSSM_LOOPBACK_EXIT_MASTER		= 0x23,
+	LTSSM_LOOPBACK_ENTRY_SLAVE		= 0x24,
+	LTSSM_LOOPBACK_ACTIVE_SLAVE		= 0x25,
+	LTSSM_LOOPBACK_EXIT_SLAVE		= 0x26,
+	LTSSM_HOT_RESET				= 0x27,
+	LTSSM_RECOVERY_EQUALIZATION_PHASE0	= 0x28,
+	LTSSM_RECOVERY_EQUALIZATION_PHASE1	= 0x29,
+	LTSSM_RECOVERY_EQUALIZATION_PHASE2	= 0x2a,
+	LTSSM_RECOVERY_EQUALIZATION_PHASE3	= 0x2b,
+};
+
 /* PCIe core controller registers */
 #define CTRL_CORE_BASE_ADDR			0x18000
 #define CTRL_CONFIG_REG				(CTRL_CORE_BASE_ADDR + 0x0)

@@ -248,13 +289,35 @@ static inline u32 advk_readl(struct advk
 	return readl(pcie->base + reg);
 }
 
-static int advk_pcie_link_up(struct advk_pcie *pcie)
+static u8 advk_pcie_ltssm_state(struct advk_pcie *pcie)
 {
-	u32 val, ltssm_state;
+	u32 val;
+	u8 ltssm_state;
 
 	val = advk_readl(pcie, CFG_REG);
 	ltssm_state = (val >> LTSSM_SHIFT) & LTSSM_MASK;
-	return ltssm_state >= LTSSM_L0;
+	return ltssm_state;
+}
+
+static inline bool advk_pcie_link_up(struct advk_pcie *pcie)
+{
+	/* check if LTSSM is in normal operation - some L* state */
+	u8 ltssm_state = advk_pcie_ltssm_state(pcie);
+	return ltssm_state >= LTSSM_L0 && ltssm_state < LTSSM_DISABLED;
+}
+
+static inline bool advk_pcie_link_training(struct advk_pcie *pcie)
+{
+	/*
+	  * According to PCIe Base specification 3.0, Table 4-14: Link
+	  * Status Mapped to the LTSSM is Link Training mapped to LTSSM
+	  * Configuration and Recovery states.
+	  */
+	u8 ltssm_state = advk_pcie_ltssm_state(pcie);
+	return ((ltssm_state >= LTSSM_CONFIG_LINKWIDTH_START &&
+		  ltssm_state < LTSSM_L0) ||
+		(ltssm_state >= LTSSM_RECOVERY_EQUALIZATION_PHASE0 &&
+		  ltssm_state <= LTSSM_RECOVERY_EQUALIZATION_PHASE3));
 }
 
 static int advk_pcie_wait_for_link(struct advk_pcie *pcie)

---
 Documentation/devicetree/bindings/pinctrl/marvell,armada-37xx-pinctrl.txt |   18 +++++++---
 drivers/pinctrl/mvebu/pinctrl-armada-37xx.c                               |   10 +++--
 2 files changed, 19 insertions(+), 9 deletions(-)
@@ -58,11 +58,11 @@ group pwm3
  - functions pwm, gpio
 
 group pmic1
- - pin 17
+ - pin 7
  - functions pmic, gpio
 
 group pmic0
- - pin 16
+ - pin 6
  - functions pmic, gpio
 
 group i2c2

@@ -112,17 +112,25 @@ group usb2_drvvbus1
  - functions drvbus, gpio
 
 group sdio_sb
- - pins 60-64
+ - pins 60-65
  - functions sdio, gpio
 
 group rgmii
- - pins 42-55
+ - pins 42-53
  - functions mii, gpio
 
 group pcie1
- - pins 39-40
+ - pins 39
+ - functions pcie, gpio
+
+group pcie1_clkreq
+ - pins 40
  - functions pcie, gpio
 
+group smi
+ - pins 54-55
+ - functions smi, gpio
+
 group ptp
  - pins 56-58
  - functions ptp, gpio

@@ -157,8 +157,8 @@ static struct armada_37xx_pin_group arma
 	PIN_GRP_GPIO("pwm1", 12, 1, BIT(4), "pwm"),
 	PIN_GRP_GPIO("pwm2", 13, 1, BIT(5), "pwm"),
 	PIN_GRP_GPIO("pwm3", 14, 1, BIT(6), "pwm"),
-	PIN_GRP_GPIO("pmic1", 17, 1, BIT(7), "pmic"),
-	PIN_GRP_GPIO("pmic0", 16, 1, BIT(8), "pmic"),
+	PIN_GRP_GPIO("pmic1", 7, 1, BIT(7), "pmic"),
+	PIN_GRP_GPIO("pmic0", 6, 1, BIT(8), "pmic"),
 	PIN_GRP_GPIO("i2c2", 2, 2, BIT(9), "i2c"),
 	PIN_GRP_GPIO("i2c1", 0, 2, BIT(10), "i2c"),
 	PIN_GRP_GPIO("spi_cs1", 17, 1, BIT(12), "spi"),

@@ -182,8 +182,10 @@ static struct armada_37xx_pin_group arma
 	PIN_GRP_GPIO("usb2_drvvbus1", 1, 1, BIT(1), "drvbus"),
 	PIN_GRP_GPIO("sdio_sb", 24, 6, BIT(2), "sdio"),
 	PIN_GRP_GPIO("rgmii", 6, 12, BIT(3), "mii"),
-	PIN_GRP_GPIO("pcie1", 3, 2, BIT(4), "pcie"),
-	PIN_GRP_GPIO("ptp", 20, 3, BIT(5), "ptp"),
+	PIN_GRP_GPIO("smi", 18, 2, BIT(4), "smi"),
+	PIN_GRP_GPIO("pcie1", 3, 1, BIT(5), "pcie"),
+	PIN_GRP_GPIO("pcie1_clkreq", 4, 1, BIT(9), "pcie"),
+	PIN_GRP_GPIO("ptp", 20, 3, BIT(11) | BIT(12) | BIT(13), "ptp"),
 	PIN_GRP("ptp_clk", 21, 1, BIT(6), "ptp", "mii"),
 	PIN_GRP("ptp_trig", 22, 1, BIT(7), "ptp", "mii"),
 	PIN_GRP_GPIO_3("mii_col", 23, 1, BIT(8) | BIT(14), 0, BIT(8), BIT(14),

---
 drivers/pinctrl/mvebu/pinctrl-armada-37xx.c |    1 +
 1 file changed, 1 insertion(+)
@@ -185,6 +185,7 @@ static struct armada_37xx_pin_group arma
 	PIN_GRP_GPIO("smi", 18, 2, BIT(4), "smi"),
 	PIN_GRP_GPIO("pcie1", 3, 1, BIT(5), "pcie"),
 	PIN_GRP_GPIO("pcie1_clkreq", 4, 1, BIT(9), "pcie"),
+	PIN_GRP_GPIO("pcie1_wakeup", 5, 1, BIT(10), "pcie"),
 	PIN_GRP_GPIO("ptp", 20, 3, BIT(11) | BIT(12) | BIT(13), "ptp"),
 	PIN_GRP("ptp_clk", 21, 1, BIT(6), "ptp", "mii"),
 	PIN_GRP("ptp_trig", 22, 1, BIT(7), "ptp", "mii"),

---
 Documentation/devicetree/bindings/pinctrl/marvell,armada-37xx-pinctrl.txt |    8 ++--
 drivers/pinctrl/mvebu/pinctrl-armada-37xx.c                               |   17 ++++------
 2 files changed, 12 insertions(+), 13 deletions(-)
@@ -43,19 +43,19 @@ group emmc_nb
 
 group pwm0
  - pin 11 (GPIO1-11)
- - functions pwm, gpio
+ - functions pwm, led, gpio
 
 group pwm1
  - pin 12
- - functions pwm, gpio
+ - functions pwm, led, gpio
 
 group pwm2
  - pin 13
- - functions pwm, gpio
+ - functions pwm, led, gpio
 
 group pwm3
  - pin 14
- - functions pwm, gpio
+ - functions pwm, led, gpio
 
 group pmic1
  - pin 7

@@ -153,10 +153,14 @@ static struct armada_37xx_pin_group arma
 	PIN_GRP_GPIO("jtag", 20, 5, BIT(0), "jtag"),
 	PIN_GRP_GPIO("sdio0", 8, 3, BIT(1), "sdio"),
 	PIN_GRP_GPIO("emmc_nb", 27, 9, BIT(2), "emmc"),
-	PIN_GRP_GPIO("pwm0", 11, 1, BIT(3), "pwm"),
-	PIN_GRP_GPIO("pwm1", 12, 1, BIT(4), "pwm"),
-	PIN_GRP_GPIO("pwm2", 13, 1, BIT(5), "pwm"),
-	PIN_GRP_GPIO("pwm3", 14, 1, BIT(6), "pwm"),
+	PIN_GRP_GPIO_3("pwm0", 11, 1, BIT(3) | BIT(20), 0, BIT(20), BIT(3),
+		       "pwm", "led"),
+	PIN_GRP_GPIO_3("pwm1", 12, 1, BIT(4) | BIT(21), 0, BIT(21), BIT(4),
+		       "pwm", "led"),
+	PIN_GRP_GPIO_3("pwm2", 13, 1, BIT(5) | BIT(22), 0, BIT(22), BIT(5),
+		       "pwm", "led"),
+	PIN_GRP_GPIO_3("pwm3", 14, 1, BIT(6) | BIT(23), 0, BIT(23), BIT(6),
+		       "pwm", "led"),
 	PIN_GRP_GPIO("pmic1", 7, 1, BIT(7), "pmic"),
 	PIN_GRP_GPIO("pmic0", 6, 1, BIT(8), "pmic"),
 	PIN_GRP_GPIO("i2c2", 2, 2, BIT(9), "i2c"),

@@ -170,11 +174,6 @@ static struct armada_37xx_pin_group arma
 	PIN_GRP_EXTRA("uart2", 9, 2, BIT(1) | BIT(13) | BIT(14) | BIT(19),
 		      BIT(1) | BIT(13) | BIT(14), BIT(1) | BIT(19),
 		      18, 2, "gpio", "uart"),
-	PIN_GRP_GPIO_2("led0_od", 11, 1, BIT(20), BIT(20), 0, "led"),
-	PIN_GRP_GPIO_2("led1_od", 12, 1, BIT(21), BIT(21), 0, "led"),
-	PIN_GRP_GPIO_2("led2_od", 13, 1, BIT(22), BIT(22), 0, "led"),
-	PIN_GRP_GPIO_2("led3_od", 14, 1, BIT(23), BIT(23), 0, "led"),
-
 };
 
 static struct armada_37xx_pin_group armada_37xx_sb_groups[] = {

---
 arch/arm64/boot/dts/marvell/armada-37xx.dtsi |    9 +++++++++
 1 file changed, 9 insertions(+)
@@ -239,6 +239,15 @@
 					function = "mii";
 				};
 
+				pcie_reset_pins: pcie-reset-pins {
+					groups = "pcie1";
+					function = "pcie";
+				};
+
+				pcie_clkreq_pins: pcie-clkreq-pins {
+					groups = "pcie1_clkreq";
+					function = "pcie";
+				};
 			};
 
 			eth0: ethernet@30000 {

---
 arch/arm64/boot/dts/marvell/armada-3720-db.dts          |    3 +++
 arch/arm64/boot/dts/marvell/armada-3720-espressobin.dts |    3 +++
 arch/arm64/boot/dts/marvell/armada-37xx.dtsi            |    2 +-
 3 files changed, 7 insertions(+), 1 deletion(-)
@@ -155,6 +155,9 @@
 
 /* CON15(V2.0)/CON17(V1.4) : PCIe / CON15(V2.0)/CON12(V1.4) :mini-PCIe */
 &pcie0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pcie_reset_pins &pcie_clkreq_pins>;
+	reset-gpios = <&gpiosb 3 GPIO_ACTIVE_LOW>;
 	status = "okay";
 };
 

@@ -82,6 +82,9 @@
 
 /* J9 */
 &pcie0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pcie_reset_pins &pcie_clkreq_pins>;
+	reset-gpios = <&gpiosb 3 GPIO_ACTIVE_LOW>;
 	status = "okay";
 };
 

@@ -241,7 +241,7 @@
 
 				pcie_reset_pins: pcie-reset-pins {
 					groups = "pcie1";
-					function = "pcie";
+					function = "gpio";
 				};
 
 				pcie_clkreq_pins: pcie-clkreq-pins {

---
 arch/arm/include/asm/tlb.h  |    8 ++++++++
 arch/ia64/include/asm/tlb.h |   10 ++++++++++
 arch/s390/include/asm/tlb.h |   14 ++++++++++++++
 arch/sh/include/asm/tlb.h   |   10 ++++++++++
 arch/um/include/asm/tlb.h   |   12 ++++++++++++
 include/asm-generic/tlb.h   |    2 ++
 mm/hugetlb.c                |   19 +++++++++++++++++++
 mm/memory.c                 |   10 ++++++++++
 8 files changed, 85 insertions(+)
@@ -280,6 +280,14 @@ tlb_remove_pmd_tlb_entry(struct mmu_gath
 	tlb_add_flush(tlb, addr);
 }
 
+static inline void
+tlb_flush_pmd_range(struct mmu_gather *tlb, unsigned long address,
+		    unsigned long size)
+{
+	tlb_add_flush(tlb, address);
+	tlb_add_flush(tlb, address + size - PMD_SIZE);
+}
+
 #define pte_free_tlb(tlb, ptep, addr)	__pte_free_tlb(tlb, ptep, addr)
 #define pmd_free_tlb(tlb, pmdp, addr)	__pmd_free_tlb(tlb, pmdp, addr)
 #define pud_free_tlb(tlb, pudp, addr)	pud_free((tlb)->mm, pudp)

@@ -269,6 +269,16 @@ __tlb_remove_tlb_entry (struct mmu_gathe
 	tlb->end_addr = address + PAGE_SIZE;
 }
 
+static inline void
+tlb_flush_pmd_range(struct mmu_gather *tlb, unsigned long address,
+		    unsigned long size)
+{
+	if (tlb->start_addr > address)
+		tlb->start_addr = address;
+	if (tlb->end_addr < address + size)
+		tlb->end_addr = address + size;
+}
+
 #define tlb_migrate_finish(mm)	platform_tlb_migrate_finish(mm)
 
 #define tlb_start_vma(tlb, vma)			do { } while (0)

@@ -116,6 +116,20 @@ static inline void tlb_remove_page_size(
 	return tlb_remove_page(tlb, page);
 }
 
+static inline void tlb_flush_pmd_range(struct mmu_gather *tlb,
+				unsigned long address, unsigned long size)
+{
+	/*
+	 * the range might exceed the original range that was provided to
+	 * tlb_gather_mmu(), so we need to update it despite the fact it is
+	 * usually not updated.
+	 */
+	if (tlb->start > address)
+		tlb->start = address;
+	if (tlb->end < address + size)
+		tlb->end = address + size;
+}
+
 /*
  * pte_free_tlb frees a pte table and clears the CRSTE for the
  * page table from the tlb.

@@ -127,6 +127,16 @@ static inline void tlb_remove_page_size(
 	return tlb_remove_page(tlb, page);
 }
 
+static inline void
+tlb_flush_pmd_range(struct mmu_gather *tlb, unsigned long address,
+		    unsigned long size)
+{
+	if (tlb->start > address)
+		tlb->start = address;
+	if (tlb->end < address + size)
+		tlb->end = address + size;
+}
+
 #define tlb_remove_check_page_size_change tlb_remove_check_page_size_change
 static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
 						     unsigned int page_size)

@@ -130,6 +130,18 @@ static inline void tlb_remove_page_size(
 	return tlb_remove_page(tlb, page);
 }
 
+static inline void
+tlb_flush_pmd_range(struct mmu_gather *tlb, unsigned long address,
+		    unsigned long size)
+{
+	tlb->need_flush = 1;
+
+	if (tlb->start > address)
+		tlb->start = address;
+	if (tlb->end < address + size)
+		tlb->end = address + size;
+}
+
 /**
  * tlb_remove_tlb_entry - remember a pte unmapping for later tlb invalidation.
  *

@@ -117,6 +117,8 @@ void arch_tlb_gather_mmu(struct mmu_gath
 void tlb_flush_mmu(struct mmu_gather *tlb);
 void arch_tlb_finish_mmu(struct mmu_gather *tlb,
 			 unsigned long start, unsigned long end, bool force);
+void tlb_flush_pmd_range(struct mmu_gather *tlb, unsigned long address,
+			 unsigned long size);
 extern bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page,
 				   int page_size);
 

@@ -3386,6 +3386,7 @@ void __unmap_hugepage_range(struct mmu_g
 	unsigned long sz = huge_page_size(h);
 	const unsigned long mmun_start = start;	/* For mmu_notifiers */
 	const unsigned long mmun_end   = end;	/* For mmu_notifiers */
+	bool force_flush = false;
 
 	WARN_ON(!is_vm_hugetlb_page(vma));
 	BUG_ON(start & ~huge_page_mask(h));

@@ -3407,6 +3408,8 @@ void __unmap_hugepage_range(struct mmu_g
 		ptl = huge_pte_lock(h, mm, ptep);
 		if (huge_pmd_unshare(mm, &address, ptep)) {
 			spin_unlock(ptl);
+			tlb_flush_pmd_range(tlb, address & PUD_MASK, PUD_SIZE);
+			force_flush = true;
 			continue;
 		}
 

@@ -3463,6 +3466,22 @@ void __unmap_hugepage_range(struct mmu_g
 	}
 	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 	tlb_end_vma(tlb, vma);
+
+	/*
+	 * If we unshared PMDs, the TLB flush was not recorded in mmu_gather. We
+	 * could defer the flush until now, since by holding i_mmap_rwsem we
+	 * guaranteed that the last refernece would not be dropped. But we must
+	 * do the flushing before we return, as otherwise i_mmap_rwsem will be
+	 * dropped and the last reference to the shared PMDs page might be
+	 * dropped as well.
+	 *
+	 * In theory we could defer the freeing of the PMD pages as well, but
+	 * huge_pmd_unshare() relies on the exact page_count for the PMD page to
+	 * detect sharing, so we cannot defer the release of the page either.
+	 * Instead, do flush now.
+	 */
+	if (force_flush)
+		tlb_flush_mmu(tlb);
 }
 
 void __unmap_hugepage_range_final(struct mmu_gather *tlb,

@@ -335,6 +335,16 @@ bool __tlb_remove_page_size(struct mmu_g
 	return false;
 }
 
+void tlb_flush_pmd_range(struct mmu_gather *tlb, unsigned long address,
+			 unsigned long size)
+{
+	if (tlb->page_size != 0 && tlb->page_size != PMD_SIZE)
+		tlb_flush_mmu(tlb);
+
+	tlb->page_size = PMD_SIZE;
+	tlb->start = min(tlb->start, address);
+	tlb->end = max(tlb->end, address + size);
+}
 #endif /* HAVE_GENERIC_MMU_GATHER */
 
 #ifdef CONFIG_HAVE_RCU_TABLE_FREE

  BUG: unable to handle page fault for address: 00007f2374e01000
  #PF: supervisor write access in kernel mode
  #PF: error_code(0x0003) - permissions violation
  PGD 7a523067 P4D 7a523067 PUD 7a528067 PMD 7a525067 PTE 800000007048f867
  Oops: 0003 [#1] PREEMPT SMP NOPTI
  CPU: 0 PID: 468 Comm: cp Not tainted 5.15.0+ #6
  Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.14.0-27-g64f37cc530f1-prebuilt.qemu.org 04/01/2014
  RIP: 0010:read_from_oldmem.part.0.cold+0x1d/0x86
  Code: ff ff ff e8 05 ff fe ff e9 b9 e9 7f ff 48 89 de 48 c7 c7 38 3b 60 82 e8 f1 fe fe ff 83 fd 08 72 3c 49 8d 7d 08 4c 89 e9 89 e8 <49> c7 45 00 00 00 00 00 49 c7 44 05 f8 00 00 00 00 48 83 e7 f81
  RSP: 0018:ffffc9000073be08 EFLAGS: 00010212
  RAX: 0000000000001000 RBX: 00000000002fd000 RCX: 00007f2374e01000
  RDX: 0000000000000001 RSI: 00000000ffffdfff RDI: 00007f2374e01008
  RBP: 0000000000001000 R08: 0000000000000000 R09: ffffc9000073bc50
  R10: ffffc9000073bc48 R11: ffffffff829461a8 R12: 000000000000f000
  R13: 00007f2374e01000 R14: 0000000000000000 R15: ffff88807bd421e8
  FS:  00007f2374e12140(0000) GS:ffff88807f000000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 00007f2374e01000 CR3: 000000007a4aa000 CR4: 0000000000350eb0
  Call Trace:
   read_vmcore+0x236/0x2c0
   proc_reg_read+0x55/0xa0
   vfs_read+0x95/0x190
   ksys_read+0x4f/0xc0
   do_syscall_64+0x3b/0x90
   entry_SYSCALL_64_after_hwframe+0x44/0xae
---
 fs/proc/vmcore.c |   15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)
@@ -105,14 +105,19 @@ static ssize_t read_from_oldmem(char *bu
 			nr_bytes = count;
 
 		/* If pfn is not ram, return zeros for sparse dump files */
-		if (pfn_is_ram(pfn) == 0)
-			memset(buf, 0, nr_bytes);
-		else {
+		if (pfn_is_ram(pfn) == 0) {
+			tmp = 0;
+			if (!userbuf)
+				memset(buf, 0, nr_bytes);
+			else if (clear_user(buf, nr_bytes))
+				tmp = -EFAULT;
+		} else {
 			tmp = copy_oldmem_page(pfn, buf, nr_bytes,
 						offset, userbuf);
-			if (tmp < 0)
-				return tmp;
 		}
+		if (tmp < 0)
+			return tmp;
+
 		*ppos += nr_bytes;
 		count -= nr_bytes;
 		buf += nr_bytes;

nfcmrvl_nci_unregister_dev   |  nfc_genl_dev_up
  nci_close_device           |
    flush_workqueue          |
    del_timer_sync           |
  nci_unregister_device      |    nfc_get_device
    destroy_workqueue        |    nfc_dev_up
    nfc_unregister_device    |      nci_dev_up
      device_del             |        nci_open_device
                             |          __nci_request
                             |            nci_send_cmd
                             |              queue_work !!!
  ...                        |  ...
  nci_unregister_device      |  queue_work
    destroy_workqueue        |
    nfc_unregister_device    |  ...
      device_del             |  nci_cmd_work
                             |  mod_timer
                             |  ...
                             |  nci_cmd_timer
                             |    queue_work !!!
---
 include/net/nfc/nci_core.h |    1 +
 net/nfc/nci/core.c         |   19 +++++++++++++++++--
 2 files changed, 18 insertions(+), 2 deletions(-)
@@ -42,6 +42,7 @@ enum nci_flag {
 	NCI_UP,
 	NCI_DATA_EXCHANGE,
 	NCI_DATA_EXCHANGE_TO,
+	NCI_UNREG,
 };
 
 /* NCI device states */

@@ -485,6 +485,11 @@ static int nci_open_device(struct nci_de
 
 	mutex_lock(&ndev->req_lock);
 
+	if (test_bit(NCI_UNREG, &ndev->flags)) {
+		rc = -ENODEV;
+		goto done;
+	}
+
 	if (test_bit(NCI_UP, &ndev->flags)) {
 		rc = -EALREADY;
 		goto done;

@@ -548,6 +553,10 @@ done:
 static int nci_close_device(struct nci_dev *ndev)
 {
 	nci_req_cancel(ndev, ENODEV);
+
+	/* This mutex needs to be held as a barrier for
+	 * caller nci_unregister_device
+	 */
 	mutex_lock(&ndev->req_lock);
 
 	if (!test_and_clear_bit(NCI_UP, &ndev->flags)) {

@@ -585,8 +594,8 @@ static int nci_close_device(struct nci_d
 	/* Flush cmd wq */
 	flush_workqueue(ndev->cmd_wq);
 
-	/* Clear flags */
-	ndev->flags = 0;
+	/* Clear flags except NCI_UNREG */
+	ndev->flags &= BIT(NCI_UNREG);
 
 	mutex_unlock(&ndev->req_lock);
 

@@ -1270,6 +1279,12 @@ void nci_unregister_device(struct nci_de
 {
 	struct nci_conn_info    *conn_info, *n;
 
+	/* This set_bit is not protected with specialized barrier,
+	 * However, it is fine because the mutex_lock(&ndev->req_lock);
+	 * in nci_close_device() will help to emit one.
+	 */
+	set_bit(NCI_UNREG, &ndev->flags);
+
 	nci_close_device(ndev);
 
 	destroy_workqueue(ndev->cmd_wq);

---
 fs/fuse/dev.c |   10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)
@@ -897,17 +897,17 @@ static int fuse_try_move_page(struct fus
 		goto out_put_old;
 	}
 
+	get_page(newpage);
+
+	if (!(buf->flags & PIPE_BUF_FLAG_LRU))
+		lru_cache_add_file(newpage);
+
 	/*
 	 * Release while we have extra ref on stolen page.  Otherwise
 	 * anon_pipe_buf_release() might think the page can be reused.
 	 */
 	pipe_buf_release(cs->pipe, buf);
 
-	get_page(newpage);
-
-	if (!(buf->flags & PIPE_BUF_FLAG_LRU))
-		lru_cache_add_file(newpage);
-
 	err = 0;
 	spin_lock(&cs->req->waitq.lock);
 	if (test_bit(FR_ABORTED, &cs->req->flags))

---
 include/xen/interface/io/ring.h |  307 +++++++++++++++++++++-------------------
 1 file changed, 165 insertions(+), 142 deletions(-)
@@ -1,21 +1,53 @@
-/* SPDX-License-Identifier: GPL-2.0 */
 /******************************************************************************
  * ring.h
  *
  * Shared producer-consumer ring macros.
  *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to
+ * deal in the Software without restriction, including without limitation the
+ * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
+ * sell copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ *
  * Tim Deegan and Andrew Warfield November 2004.
  */
 
 #ifndef __XEN_PUBLIC_IO_RING_H__
 #define __XEN_PUBLIC_IO_RING_H__
 
+/*
+ * When #include'ing this header, you need to provide the following
+ * declaration upfront:
+ * - standard integers types (uint8_t, uint16_t, etc)
+ * They are provided by stdint.h of the standard headers.
+ *
+ * In addition, if you intend to use the FLEX macros, you also need to
+ * provide the following, before invoking the FLEX macros:
+ * - size_t
+ * - memcpy
+ * - grant_ref_t
+ * These declarations are provided by string.h of the standard headers,
+ * and grant_table.h from the Xen public headers.
+ */
+
 #include <xen/interface/grant_table.h>
 
 typedef unsigned int RING_IDX;
 
 /* Round a 32-bit unsigned constant down to the nearest power of two. */
-#define __RD2(_x)  (((_x) & 0x00000002) ? 0x2		       : ((_x) & 0x1))
+#define __RD2(_x)  (((_x) & 0x00000002) ? 0x2                  : ((_x) & 0x1))
 #define __RD4(_x)  (((_x) & 0x0000000c) ? __RD2((_x)>>2)<<2    : __RD2(_x))
 #define __RD8(_x)  (((_x) & 0x000000f0) ? __RD4((_x)>>4)<<4    : __RD4(_x))
 #define __RD16(_x) (((_x) & 0x0000ff00) ? __RD8((_x)>>8)<<8    : __RD8(_x))

@@ -27,82 +59,79 @@ typedef unsigned int RING_IDX;
  * A ring contains as many entries as will fit, rounded down to the nearest
  * power of two (so we can mask with (size-1) to loop around).
  */
-#define __CONST_RING_SIZE(_s, _sz)				\
-	(__RD32(((_sz) - offsetof(struct _s##_sring, ring)) /	\
-		sizeof(((struct _s##_sring *)0)->ring[0])))
-
+#define __CONST_RING_SIZE(_s, _sz) \
+    (__RD32(((_sz) - offsetof(struct _s##_sring, ring)) / \
+	    sizeof(((struct _s##_sring *)0)->ring[0])))
 /*
  * The same for passing in an actual pointer instead of a name tag.
  */
-#define __RING_SIZE(_s, _sz)						\
-	(__RD32(((_sz) - (long)&(_s)->ring + (long)(_s)) / sizeof((_s)->ring[0])))
+#define __RING_SIZE(_s, _sz) \
+    (__RD32(((_sz) - (long)(_s)->ring + (long)(_s)) / sizeof((_s)->ring[0])))
 
 /*
  * Macros to make the correct C datatypes for a new kind of ring.
  *
  * To make a new ring datatype, you need to have two message structures,
- * let's say struct request, and struct response already defined.
+ * let's say request_t, and response_t already defined.
  *
  * In a header where you want the ring datatype declared, you then do:
  *
- *     DEFINE_RING_TYPES(mytag, struct request, struct response);
+ *     DEFINE_RING_TYPES(mytag, request_t, response_t);
  *
  * These expand out to give you a set of types, as you can see below.
  * The most important of these are:
  *
- *     struct mytag_sring      - The shared ring.
- *     struct mytag_front_ring - The 'front' half of the ring.
- *     struct mytag_back_ring  - The 'back' half of the ring.
+ *     mytag_sring_t      - The shared ring.
+ *     mytag_front_ring_t - The 'front' half of the ring.
+ *     mytag_back_ring_t  - The 'back' half of the ring.
  *
  * To initialize a ring in your code you need to know the location and size
  * of the shared memory area (PAGE_SIZE, for instance). To initialise
  * the front half:
  *
- *     struct mytag_front_ring front_ring;
- *     SHARED_RING_INIT((struct mytag_sring *)shared_page);
- *     FRONT_RING_INIT(&front_ring, (struct mytag_sring *)shared_page,
- *		       PAGE_SIZE);
+ *     mytag_front_ring_t front_ring;
+ *     SHARED_RING_INIT((mytag_sring_t *)shared_page);
+ *     FRONT_RING_INIT(&front_ring, (mytag_sring_t *)shared_page, PAGE_SIZE);
  *
  * Initializing the back follows similarly (note that only the front
  * initializes the shared ring):
  *
- *     struct mytag_back_ring back_ring;
- *     BACK_RING_INIT(&back_ring, (struct mytag_sring *)shared_page,
- *		      PAGE_SIZE);
+ *     mytag_back_ring_t back_ring;
+ *     BACK_RING_INIT(&back_ring, (mytag_sring_t *)shared_page, PAGE_SIZE);
  */
 
-#define DEFINE_RING_TYPES(__name, __req_t, __rsp_t)			\
-									\
-/* Shared ring entry */							\
-union __name##_sring_entry {						\
-    __req_t req;							\
-    __rsp_t rsp;							\
-};									\
-									\
-/* Shared ring page */							\
-struct __name##_sring {							\
-    RING_IDX req_prod, req_event;					\
-    RING_IDX rsp_prod, rsp_event;					\
-    uint8_t  pad[48];							\
-    union __name##_sring_entry ring[1]; /* variable-length */		\
-};									\
-									\
-/* "Front" end's private variables */					\
-struct __name##_front_ring {						\
-    RING_IDX req_prod_pvt;						\
-    RING_IDX rsp_cons;							\
-    unsigned int nr_ents;						\
-    struct __name##_sring *sring;					\
-};									\
-									\
-/* "Back" end's private variables */					\
-struct __name##_back_ring {						\
-    RING_IDX rsp_prod_pvt;						\
-    RING_IDX req_cons;							\
-    unsigned int nr_ents;						\
-    struct __name##_sring *sring;					\
-};
-
+#define DEFINE_RING_TYPES(__name, __req_t, __rsp_t)                     \
+                                                                        \
+/* Shared ring entry */                                                 \
+union __name##_sring_entry {                                            \
+    __req_t req;                                                        \
+    __rsp_t rsp;                                                        \
+};                                                                      \
+                                                                        \
+/* Shared ring page */                                                  \
+struct __name##_sring {                                                 \
+    RING_IDX req_prod, req_event;                                       \
+    RING_IDX rsp_prod, rsp_event;                                       \
+    uint8_t __pad[48];                                                  \
+    union __name##_sring_entry ring[1]; /* variable-length */           \
+};                                                                      \
+                                                                        \
+/* "Front" end's private variables */                                   \
+struct __name##_front_ring {                                            \
+    RING_IDX req_prod_pvt;                                              \
+    RING_IDX rsp_cons;                                                  \
+    unsigned int nr_ents;                                               \
+    struct __name##_sring *sring;                                       \
+};                                                                      \
+                                                                        \
+/* "Back" end's private variables */                                    \
+struct __name##_back_ring {                                             \
+    RING_IDX rsp_prod_pvt;                                              \
+    RING_IDX req_cons;                                                  \
+    unsigned int nr_ents;                                               \
+    struct __name##_sring *sring;                                       \
+};                                                                      \
+                                                                        \
 /*
  * Macros for manipulating rings.
  *

@@ -119,105 +148,99 @@ struct __name##_back_ring {						\
  */
 
 /* Initialising empty rings */
-#define SHARED_RING_INIT(_s) do {					\
-    (_s)->req_prod  = (_s)->rsp_prod  = 0;				\
-    (_s)->req_event = (_s)->rsp_event = 1;				\
-    memset((_s)->pad, 0, sizeof((_s)->pad));				\
+#define SHARED_RING_INIT(_s) do {                                       \
+    (_s)->req_prod  = (_s)->rsp_prod  = 0;                              \
+    (_s)->req_event = (_s)->rsp_event = 1;                              \
+    (void)memset((_s)->__pad, 0, sizeof((_s)->__pad));                  \
 } while(0)
 
-#define FRONT_RING_INIT(_r, _s, __size) do {				\
-    (_r)->req_prod_pvt = 0;						\
-    (_r)->rsp_cons = 0;							\
-    (_r)->nr_ents = __RING_SIZE(_s, __size);				\
-    (_r)->sring = (_s);							\
+#define FRONT_RING_ATTACH(_r, _s, _i, __size) do {                      \
+    (_r)->req_prod_pvt = (_i);                                          \
+    (_r)->rsp_cons = (_i);                                              \
+    (_r)->nr_ents = __RING_SIZE(_s, __size);                            \
+    (_r)->sring = (_s);                                                 \
 } while (0)
 
-#define BACK_RING_INIT(_r, _s, __size) do {				\
-    (_r)->rsp_prod_pvt = 0;						\
-    (_r)->req_cons = 0;							\
-    (_r)->nr_ents = __RING_SIZE(_s, __size);				\
-    (_r)->sring = (_s);							\
-} while (0)
+#define FRONT_RING_INIT(_r, _s, __size) FRONT_RING_ATTACH(_r, _s, 0, __size)
 
-/* Initialize to existing shared indexes -- for recovery */
-#define FRONT_RING_ATTACH(_r, _s, __size) do {				\
-    (_r)->sring = (_s);							\
-    (_r)->req_prod_pvt = (_s)->req_prod;				\
-    (_r)->rsp_cons = (_s)->rsp_prod;					\
-    (_r)->nr_ents = __RING_SIZE(_s, __size);				\
+#define BACK_RING_ATTACH(_r, _s, _i, __size) do {                       \
+    (_r)->rsp_prod_pvt = (_i);                                          \
+    (_r)->req_cons = (_i);                                              \
+    (_r)->nr_ents = __RING_SIZE(_s, __size);                            \
+    (_r)->sring = (_s);                                                 \
 } while (0)
 
-#define BACK_RING_ATTACH(_r, _s, __size) do {				\
-    (_r)->sring = (_s);							\
-    (_r)->rsp_prod_pvt = (_s)->rsp_prod;				\
-    (_r)->req_cons = (_s)->req_prod;					\
-    (_r)->nr_ents = __RING_SIZE(_s, __size);				\
-} while (0)
+#define BACK_RING_INIT(_r, _s, __size) BACK_RING_ATTACH(_r, _s, 0, __size)
 
 /* How big is this ring? */
-#define RING_SIZE(_r)							\
+#define RING_SIZE(_r)                                                   \
     ((_r)->nr_ents)
 
 /* Number of free requests (for use on front side only). */
-#define RING_FREE_REQUESTS(_r)						\
+#define RING_FREE_REQUESTS(_r)                                          \
     (RING_SIZE(_r) - ((_r)->req_prod_pvt - (_r)->rsp_cons))
 
 /* Test if there is an empty slot available on the front ring.
  * (This is only meaningful from the front. )
  */
-#define RING_FULL(_r)							\
+#define RING_FULL(_r)                                                   \
     (RING_FREE_REQUESTS(_r) == 0)
 
 /* Test if there are outstanding messages to be processed on a ring. */
-#define RING_HAS_UNCONSUMED_RESPONSES(_r)				\
+#define RING_HAS_UNCONSUMED_RESPONSES(_r)                               \
     ((_r)->sring->rsp_prod - (_r)->rsp_cons)
 
-#define RING_HAS_UNCONSUMED_REQUESTS(_r)				\
-    ({									\
-	unsigned int req = (_r)->sring->req_prod - (_r)->req_cons;	\
-	unsigned int rsp = RING_SIZE(_r) -				\
-			   ((_r)->req_cons - (_r)->rsp_prod_pvt);	\
-	req < rsp ? req : rsp;						\
-    })
+#define RING_HAS_UNCONSUMED_REQUESTS(_r) ({                             \
+    unsigned int req = (_r)->sring->req_prod - (_r)->req_cons;          \
+    unsigned int rsp = RING_SIZE(_r) -                                  \
+        ((_r)->req_cons - (_r)->rsp_prod_pvt);                          \
+    req < rsp ? req : rsp;                                              \
+})
 
 /* Direct access to individual ring elements, by index. */
-#define RING_GET_REQUEST(_r, _idx)					\
+#define RING_GET_REQUEST(_r, _idx)                                      \
     (&((_r)->sring->ring[((_idx) & (RING_SIZE(_r) - 1))].req))
 
+#define RING_GET_RESPONSE(_r, _idx)                                     \
+    (&((_r)->sring->ring[((_idx) & (RING_SIZE(_r) - 1))].rsp))
+
 /*
- * Get a local copy of a request.
+ * Get a local copy of a request/response.
  *
- * Use this in preference to RING_GET_REQUEST() so all processing is
+ * Use this in preference to RING_GET_{REQUEST,RESPONSE}() so all processing is
  * done on a local copy that cannot be modified by the other end.
  *
  * Note that https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58145 may cause this
- * to be ineffective where _req is a struct which consists of only bitfields.
+ * to be ineffective where dest is a struct which consists of only bitfields.
  */
-#define RING_COPY_REQUEST(_r, _idx, _req) do {				\
-	/* Use volatile to force the copy into _req. */			\
-	*(_req) = *(volatile typeof(_req))RING_GET_REQUEST(_r, _idx);	\
+#define RING_COPY_(type, r, idx, dest) do {				\
+	/* Use volatile to force the copy into dest. */			\
+	*(dest) = *(volatile typeof(dest))RING_GET_##type(r, idx);	\
 } while (0)
 
-#define RING_GET_RESPONSE(_r, _idx)					\
-    (&((_r)->sring->ring[((_idx) & (RING_SIZE(_r) - 1))].rsp))
+#define RING_COPY_REQUEST(r, idx, req)  RING_COPY_(REQUEST, r, idx, req)
+#define RING_COPY_RESPONSE(r, idx, rsp) RING_COPY_(RESPONSE, r, idx, rsp)
 
 /* Loop termination condition: Would the specified index overflow the ring? */
-#define RING_REQUEST_CONS_OVERFLOW(_r, _cons)				\
+#define RING_REQUEST_CONS_OVERFLOW(_r, _cons)                           \
     (((_cons) - (_r)->rsp_prod_pvt) >= RING_SIZE(_r))
 
 /* Ill-behaved frontend determination: Can there be this many requests? */
-#define RING_REQUEST_PROD_OVERFLOW(_r, _prod)               \
+#define RING_REQUEST_PROD_OVERFLOW(_r, _prod)                           \
     (((_prod) - (_r)->rsp_prod_pvt) > RING_SIZE(_r))
 
-
-#define RING_PUSH_REQUESTS(_r) do {					\
-    virt_wmb(); /* back sees requests /before/ updated producer index */	\
-    (_r)->sring->req_prod = (_r)->req_prod_pvt;				\
+/* Ill-behaved backend determination: Can there be this many responses? */
+#define RING_RESPONSE_PROD_OVERFLOW(_r, _prod)                          \
+    (((_prod) - (_r)->rsp_cons) > RING_SIZE(_r))
+
+#define RING_PUSH_REQUESTS(_r) do {                                     \
+    virt_wmb(); /* back sees requests /before/ updated producer index */\
+    (_r)->sring->req_prod = (_r)->req_prod_pvt;                         \
 } while (0)
 
-#define RING_PUSH_RESPONSES(_r) do {					\
-    virt_wmb(); /* front sees responses /before/ updated producer index */	\
-    (_r)->sring->rsp_prod = (_r)->rsp_prod_pvt;				\
+#define RING_PUSH_RESPONSES(_r) do {                                    \
+    virt_wmb(); /* front sees resps /before/ updated producer index */  \
+    (_r)->sring->rsp_prod = (_r)->rsp_prod_pvt;                         \
 } while (0)
 
 /*

@@ -250,40 +273,40 @@ struct __name##_back_ring {						\
  *  field appropriately.
  */
 
-#define RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(_r, _notify) do {		\
-    RING_IDX __old = (_r)->sring->req_prod;				\
-    RING_IDX __new = (_r)->req_prod_pvt;				\
-    virt_wmb(); /* back sees requests /before/ updated producer index */	\
-    (_r)->sring->req_prod = __new;					\
-    virt_mb(); /* back sees new requests /before/ we check req_event */	\
-    (_notify) = ((RING_IDX)(__new - (_r)->sring->req_event) <		\
-		 (RING_IDX)(__new - __old));				\
-} while (0)
-
-#define RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(_r, _notify) do {		\
-    RING_IDX __old = (_r)->sring->rsp_prod;				\
-    RING_IDX __new = (_r)->rsp_prod_pvt;				\
-    virt_wmb(); /* front sees responses /before/ updated producer index */	\
-    (_r)->sring->rsp_prod = __new;					\
-    virt_mb(); /* front sees new responses /before/ we check rsp_event */	\
-    (_notify) = ((RING_IDX)(__new - (_r)->sring->rsp_event) <		\
-		 (RING_IDX)(__new - __old));				\
-} while (0)
-
-#define RING_FINAL_CHECK_FOR_REQUESTS(_r, _work_to_do) do {		\
-    (_work_to_do) = RING_HAS_UNCONSUMED_REQUESTS(_r);			\
-    if (_work_to_do) break;						\
-    (_r)->sring->req_event = (_r)->req_cons + 1;			\
-    virt_mb();								\
-    (_work_to_do) = RING_HAS_UNCONSUMED_REQUESTS(_r);			\
-} while (0)
-
-#define RING_FINAL_CHECK_FOR_RESPONSES(_r, _work_to_do) do {		\
-    (_work_to_do) = RING_HAS_UNCONSUMED_RESPONSES(_r);			\
-    if (_work_to_do) break;						\
-    (_r)->sring->rsp_event = (_r)->rsp_cons + 1;			\
-    virt_mb();								\
-    (_work_to_do) = RING_HAS_UNCONSUMED_RESPONSES(_r);			\
+#define RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(_r, _notify) do {           \
+    RING_IDX __old = (_r)->sring->req_prod;                             \
+    RING_IDX __new = (_r)->req_prod_pvt;                                \
+    virt_wmb(); /* back sees requests /before/ updated producer index */\
+    (_r)->sring->req_prod = __new;                                      \
+    virt_mb(); /* back sees new requests /before/ we check req_event */ \
+    (_notify) = ((RING_IDX)(__new - (_r)->sring->req_event) <           \
+                 (RING_IDX)(__new - __old));                            \
+} while (0)
+
+#define RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(_r, _notify) do {          \
+    RING_IDX __old = (_r)->sring->rsp_prod;                             \
+    RING_IDX __new = (_r)->rsp_prod_pvt;                                \
+    virt_wmb(); /* front sees resps /before/ updated producer index */  \
+    (_r)->sring->rsp_prod = __new;                                      \
+    virt_mb(); /* front sees new resps /before/ we check rsp_event */   \
+    (_notify) = ((RING_IDX)(__new - (_r)->sring->rsp_event) <           \
+                 (RING_IDX)(__new - __old));                            \
+} while (0)
+
+#define RING_FINAL_CHECK_FOR_REQUESTS(_r, _work_to_do) do {             \
+    (_work_to_do) = RING_HAS_UNCONSUMED_REQUESTS(_r);                   \
+    if (_work_to_do) break;                                             \
+    (_r)->sring->req_event = (_r)->req_cons + 1;                        \
+    virt_mb();                                                          \
+    (_work_to_do) = RING_HAS_UNCONSUMED_REQUESTS(_r);                   \
+} while (0)
+
+#define RING_FINAL_CHECK_FOR_RESPONSES(_r, _work_to_do) do {            \
+    (_work_to_do) = RING_HAS_UNCONSUMED_RESPONSES(_r);                  \
+    if (_work_to_do) break;                                             \
+    (_r)->sring->rsp_event = (_r)->rsp_cons + 1;                        \
+    virt_mb();                                                          \
+    (_work_to_do) = RING_HAS_UNCONSUMED_RESPONSES(_r);                  \
 } while (0)
 
 

---
 drivers/block/xen-blkfront.c |   35 ++++++++++++++++++-----------------
 1 file changed, 18 insertions(+), 17 deletions(-)
@@ -1550,7 +1550,7 @@ static bool blkif_completion(unsigned lo
 static irqreturn_t blkif_interrupt(int irq, void *dev_id)
 {
 	struct request *req;
-	struct blkif_response *bret;
+	struct blkif_response bret;
 	RING_IDX i, rp;
 	unsigned long flags;
 	struct blkfront_ring_info *rinfo = (struct blkfront_ring_info *)dev_id;

@@ -1567,8 +1567,9 @@ static irqreturn_t blkif_interrupt(int i
 	for (i = rinfo->ring.rsp_cons; i != rp; i++) {
 		unsigned long id;
 
-		bret = RING_GET_RESPONSE(&rinfo->ring, i);
-		id   = bret->id;
+		RING_COPY_RESPONSE(&rinfo->ring, i, &bret);
+		id = bret.id;
+
 		/*
 		 * The backend has messed up and given us an id that we would
 		 * never have given to it (we stamp it up to BLK_RING_SIZE -

@@ -1576,39 +1577,39 @@ static irqreturn_t blkif_interrupt(int i
 		 */
 		if (id >= BLK_RING_SIZE(info)) {
 			WARN(1, "%s: response to %s has incorrect id (%ld)\n",
-			     info->gd->disk_name, op_name(bret->operation), id);
+			     info->gd->disk_name, op_name(bret.operation), id);
 			/* We can't safely get the 'struct request' as
 			 * the id is busted. */
 			continue;
 		}
 		req  = rinfo->shadow[id].request;
 
-		if (bret->operation != BLKIF_OP_DISCARD) {
+		if (bret.operation != BLKIF_OP_DISCARD) {
 			/*
 			 * We may need to wait for an extra response if the
 			 * I/O request is split in 2
 			 */
-			if (!blkif_completion(&id, rinfo, bret))
+			if (!blkif_completion(&id, rinfo, &bret))
 				continue;
 		}
 
 		if (add_id_to_freelist(rinfo, id)) {
 			WARN(1, "%s: response to %s (id %ld) couldn't be recycled!\n",
-			     info->gd->disk_name, op_name(bret->operation), id);
+			     info->gd->disk_name, op_name(bret.operation), id);
 			continue;
 		}
 
-		if (bret->status == BLKIF_RSP_OKAY)
+		if (bret.status == BLKIF_RSP_OKAY)
 			blkif_req(req)->error = BLK_STS_OK;
 		else
 			blkif_req(req)->error = BLK_STS_IOERR;
 
-		switch (bret->operation) {
+		switch (bret.operation) {
 		case BLKIF_OP_DISCARD:
-			if (unlikely(bret->status == BLKIF_RSP_EOPNOTSUPP)) {
+			if (unlikely(bret.status == BLKIF_RSP_EOPNOTSUPP)) {
 				struct request_queue *rq = info->rq;
 				printk(KERN_WARNING "blkfront: %s: %s op failed\n",
-					   info->gd->disk_name, op_name(bret->operation));
+					   info->gd->disk_name, op_name(bret.operation));
 				blkif_req(req)->error = BLK_STS_NOTSUPP;
 				info->feature_discard = 0;
 				info->feature_secdiscard = 0;

@@ -1618,15 +1619,15 @@ static irqreturn_t blkif_interrupt(int i
 			break;
 		case BLKIF_OP_FLUSH_DISKCACHE:
 		case BLKIF_OP_WRITE_BARRIER:
-			if (unlikely(bret->status == BLKIF_RSP_EOPNOTSUPP)) {
+			if (unlikely(bret.status == BLKIF_RSP_EOPNOTSUPP)) {
 				printk(KERN_WARNING "blkfront: %s: %s op failed\n",
-				       info->gd->disk_name, op_name(bret->operation));
+				       info->gd->disk_name, op_name(bret.operation));
 				blkif_req(req)->error = BLK_STS_NOTSUPP;
 			}
-			if (unlikely(bret->status == BLKIF_RSP_ERROR &&
+			if (unlikely(bret.status == BLKIF_RSP_ERROR &&
 				     rinfo->shadow[id].req.u.rw.nr_segments == 0)) {
 				printk(KERN_WARNING "blkfront: %s: empty %s op failed\n",
-				       info->gd->disk_name, op_name(bret->operation));
+				       info->gd->disk_name, op_name(bret.operation));
 				blkif_req(req)->error = BLK_STS_NOTSUPP;
 			}
 			if (unlikely(blkif_req(req)->error)) {

@@ -1639,9 +1640,9 @@ static irqreturn_t blkif_interrupt(int i
 			/* fall through */
 		case BLKIF_OP_READ:
 		case BLKIF_OP_WRITE:
-			if (unlikely(bret->status != BLKIF_RSP_OKAY))
+			if (unlikely(bret.status != BLKIF_RSP_OKAY))
 				dev_dbg(&info->xbdev->dev, "Bad return from blkdev data "
-					"request: %x\n", bret->status);
+					"request: %x\n", bret.status);
 
 			break;
 		default:

---
 drivers/block/xen-blkfront.c |   25 +++++++++++++++----------
 1 file changed, 15 insertions(+), 10 deletions(-)
@@ -537,7 +537,7 @@ static unsigned long blkif_ring_get_requ
 	rinfo->shadow[id].status = REQ_WAITING;
 	rinfo->shadow[id].associated_id = NO_ASSOCIATED_ID;
 
-	(*ring_req)->u.rw.id = id;
+	rinfo->shadow[id].req.u.rw.id = id;
 
 	return id;
 }

@@ -545,11 +545,12 @@ static unsigned long blkif_ring_get_requ
 static int blkif_queue_discard_req(struct request *req, struct blkfront_ring_info *rinfo)
 {
 	struct blkfront_info *info = rinfo->dev_info;
-	struct blkif_request *ring_req;
+	struct blkif_request *ring_req, *final_ring_req;
 	unsigned long id;
 
 	/* Fill out a communications ring structure. */
-	id = blkif_ring_get_request(rinfo, req, &ring_req);
+	id = blkif_ring_get_request(rinfo, req, &final_ring_req);
+	ring_req = &rinfo->shadow[id].req;
 
 	ring_req->operation = BLKIF_OP_DISCARD;
 	ring_req->u.discard.nr_sectors = blk_rq_sectors(req);

@@ -560,8 +561,8 @@ static int blkif_queue_discard_req(struc
 	else
 		ring_req->u.discard.flag = 0;
 
-	/* Keep a private copy so we can reissue requests when recovering. */
-	rinfo->shadow[id].req = *ring_req;
+	/* Copy the request to the ring page. */
+	*final_ring_req = *ring_req;
 
 	return 0;
 }

@@ -694,6 +695,7 @@ static int blkif_queue_rw_req(struct req
 {
 	struct blkfront_info *info = rinfo->dev_info;
 	struct blkif_request *ring_req, *extra_ring_req = NULL;
+	struct blkif_request *final_ring_req, *final_extra_ring_req = NULL;
 	unsigned long id, extra_id = NO_ASSOCIATED_ID;
 	bool require_extra_req = false;
 	int i;

@@ -738,7 +740,8 @@ static int blkif_queue_rw_req(struct req
 	}
 
 	/* Fill out a communications ring structure. */
-	id = blkif_ring_get_request(rinfo, req, &ring_req);
+	id = blkif_ring_get_request(rinfo, req, &final_ring_req);
+	ring_req = &rinfo->shadow[id].req;
 
 	num_sg = blk_rq_map_sg(req->q, req, rinfo->shadow[id].sg);
 	num_grant = 0;

@@ -789,7 +792,9 @@ static int blkif_queue_rw_req(struct req
 		ring_req->u.rw.nr_segments = num_grant;
 		if (unlikely(require_extra_req)) {
 			extra_id = blkif_ring_get_request(rinfo, req,
-							  &extra_ring_req);
+							  &final_extra_ring_req);
+			extra_ring_req = &rinfo->shadow[extra_id].req;
+
 			/*
 			 * Only the first request contains the scatter-gather
 			 * list.

@@ -831,10 +836,10 @@ static int blkif_queue_rw_req(struct req
 	if (setup.segments)
 		kunmap_atomic(setup.segments);
 
-	/* Keep a private copy so we can reissue requests when recovering. */
-	rinfo->shadow[id].req = *ring_req;
+	/* Copy request(s) to the ring page. */
+	*final_ring_req = *ring_req;
 	if (unlikely(require_extra_req))
-		rinfo->shadow[extra_id].req = *extra_ring_req;
+		*final_extra_ring_req = *extra_ring_req;
 
 	if (new_persistent_gnts)
 		gnttab_free_grant_references(setup.gref_head);

---
 drivers/block/xen-blkfront.c |   70 ++++++++++++++++++++++++++++++++-----------
 1 file changed, 53 insertions(+), 17 deletions(-)
@@ -78,6 +78,7 @@ enum blkif_state {
 	BLKIF_STATE_DISCONNECTED,
 	BLKIF_STATE_CONNECTED,
 	BLKIF_STATE_SUSPENDED,
+	BLKIF_STATE_ERROR,
 };
 
 struct grant {

@@ -87,6 +88,7 @@ struct grant {
 };
 
 enum blk_req_status {
+	REQ_PROCESSING,
 	REQ_WAITING,
 	REQ_DONE,
 	REQ_ERROR,

@@ -534,7 +536,7 @@ static unsigned long blkif_ring_get_requ
 
 	id = get_id_from_freelist(rinfo);
 	rinfo->shadow[id].request = req;
-	rinfo->shadow[id].status = REQ_WAITING;
+	rinfo->shadow[id].status = REQ_PROCESSING;
 	rinfo->shadow[id].associated_id = NO_ASSOCIATED_ID;
 
 	rinfo->shadow[id].req.u.rw.id = id;

@@ -563,6 +565,7 @@ static int blkif_queue_discard_req(struc
 
 	/* Copy the request to the ring page. */
 	*final_ring_req = *ring_req;
+	rinfo->shadow[id].status = REQ_WAITING;
 
 	return 0;
 }

@@ -838,8 +841,11 @@ static int blkif_queue_rw_req(struct req
 
 	/* Copy request(s) to the ring page. */
 	*final_ring_req = *ring_req;
-	if (unlikely(require_extra_req))
+	rinfo->shadow[id].status = REQ_WAITING;
+	if (unlikely(require_extra_req)) {
 		*final_extra_ring_req = *extra_ring_req;
+		rinfo->shadow[extra_id].status = REQ_WAITING;
+	}
 
 	if (new_persistent_gnts)
 		gnttab_free_grant_references(setup.gref_head);

@@ -1413,8 +1419,8 @@ static enum blk_req_status blkif_rsp_to_
 static int blkif_get_final_status(enum blk_req_status s1,
 				  enum blk_req_status s2)
 {
-	BUG_ON(s1 == REQ_WAITING);
-	BUG_ON(s2 == REQ_WAITING);
+	BUG_ON(s1 < REQ_DONE);
+	BUG_ON(s2 < REQ_DONE);
 
 	if (s1 == REQ_ERROR || s2 == REQ_ERROR)
 		return BLKIF_RSP_ERROR;

@@ -1447,7 +1453,7 @@ static bool blkif_completion(unsigned lo
 		s->status = blkif_rsp_to_req_status(bret->status);
 
 		/* Wait the second response if not yet here. */
-		if (s2->status == REQ_WAITING)
+		if (s2->status < REQ_DONE)
 			return 0;
 
 		bret->status = blkif_get_final_status(s->status,

@@ -1566,11 +1572,17 @@ static irqreturn_t blkif_interrupt(int i
 
 	spin_lock_irqsave(&rinfo->ring_lock, flags);
  again:
-	rp = rinfo->ring.sring->rsp_prod;
-	rmb(); /* Ensure we see queued responses up to 'rp'. */
+	rp = READ_ONCE(rinfo->ring.sring->rsp_prod);
+	virt_rmb(); /* Ensure we see queued responses up to 'rp'. */
+	if (RING_RESPONSE_PROD_OVERFLOW(&rinfo->ring, rp)) {
+		pr_alert("%s: illegal number of responses %u\n",
+			 info->gd->disk_name, rp - rinfo->ring.rsp_cons);
+		goto err;
+	}
 
 	for (i = rinfo->ring.rsp_cons; i != rp; i++) {
 		unsigned long id;
+		unsigned int op;
 
 		RING_COPY_RESPONSE(&rinfo->ring, i, &bret);
 		id = bret.id;

@@ -1581,14 +1593,28 @@ static irqreturn_t blkif_interrupt(int i
 		 * look in get_id_from_freelist.
 		 */
 		if (id >= BLK_RING_SIZE(info)) {
-			WARN(1, "%s: response to %s has incorrect id (%ld)\n",
-			     info->gd->disk_name, op_name(bret.operation), id);
-			/* We can't safely get the 'struct request' as
-			 * the id is busted. */
-			continue;
+			pr_alert("%s: response has incorrect id (%ld)\n",
+				 info->gd->disk_name, id);
+			goto err;
+		}
+		if (rinfo->shadow[id].status != REQ_WAITING) {
+			pr_alert("%s: response references no pending request\n",
+				 info->gd->disk_name);
+			goto err;
 		}
+
+		rinfo->shadow[id].status = REQ_PROCESSING;
 		req  = rinfo->shadow[id].request;
 
+		op = rinfo->shadow[id].req.operation;
+		if (op == BLKIF_OP_INDIRECT)
+			op = rinfo->shadow[id].req.u.indirect.indirect_op;
+		if (bret.operation != op) {
+			pr_alert("%s: response has wrong operation (%u instead of %u)\n",
+				 info->gd->disk_name, bret.operation, op);
+			goto err;
+		}
+
 		if (bret.operation != BLKIF_OP_DISCARD) {
 			/*
 			 * We may need to wait for an extra response if the

@@ -1613,7 +1639,8 @@ static irqreturn_t blkif_interrupt(int i
 		case BLKIF_OP_DISCARD:
 			if (unlikely(bret.status == BLKIF_RSP_EOPNOTSUPP)) {
 				struct request_queue *rq = info->rq;
-				printk(KERN_WARNING "blkfront: %s: %s op failed\n",
+
+				pr_warn_ratelimited("blkfront: %s: %s op failed\n",
 					   info->gd->disk_name, op_name(bret.operation));
 				blkif_req(req)->error = BLK_STS_NOTSUPP;
 				info->feature_discard = 0;

@@ -1625,13 +1652,13 @@ static irqreturn_t blkif_interrupt(int i
 		case BLKIF_OP_FLUSH_DISKCACHE:
 		case BLKIF_OP_WRITE_BARRIER:
 			if (unlikely(bret.status == BLKIF_RSP_EOPNOTSUPP)) {
-				printk(KERN_WARNING "blkfront: %s: %s op failed\n",
+				pr_warn_ratelimited("blkfront: %s: %s op failed\n",
 				       info->gd->disk_name, op_name(bret.operation));
 				blkif_req(req)->error = BLK_STS_NOTSUPP;
 			}
 			if (unlikely(bret.status == BLKIF_RSP_ERROR &&
 				     rinfo->shadow[id].req.u.rw.nr_segments == 0)) {
-				printk(KERN_WARNING "blkfront: %s: empty %s op failed\n",
+				pr_warn_ratelimited("blkfront: %s: empty %s op failed\n",
 				       info->gd->disk_name, op_name(bret.operation));
 				blkif_req(req)->error = BLK_STS_NOTSUPP;
 			}

@@ -1646,8 +1673,9 @@ static irqreturn_t blkif_interrupt(int i
 		case BLKIF_OP_READ:
 		case BLKIF_OP_WRITE:
 			if (unlikely(bret.status != BLKIF_RSP_OKAY))
-				dev_dbg(&info->xbdev->dev, "Bad return from blkdev data "
-					"request: %x\n", bret.status);
+				dev_dbg_ratelimited(&info->xbdev->dev,
+					"Bad return from blkdev data request: %#x\n",
+					bret.status);
 
 			break;
 		default:

@@ -1672,6 +1700,14 @@ static irqreturn_t blkif_interrupt(int i
 	spin_unlock_irqrestore(&rinfo->ring_lock, flags);
 
 	return IRQ_HANDLED;
+
+ err:
+	info->connected = BLKIF_STATE_ERROR;
+
+	spin_unlock_irqrestore(&rinfo->ring_lock, flags);
+
+	pr_alert("%s disabled for further use\n", info->gd->disk_name);
+	return IRQ_HANDLED;
 }
 
 

---
 drivers/net/xen-netfront.c |   38 +++++++++++++++++++-------------------
 1 file changed, 19 insertions(+), 19 deletions(-)
@@ -389,13 +389,13 @@ static void xennet_tx_buf_gc(struct netf
 		rmb(); /* Ensure we see responses up to 'rp'. */
 
 		for (cons = queue->tx.rsp_cons; cons != prod; cons++) {
-			struct xen_netif_tx_response *txrsp;
+			struct xen_netif_tx_response txrsp;
 
-			txrsp = RING_GET_RESPONSE(&queue->tx, cons);
-			if (txrsp->status == XEN_NETIF_RSP_NULL)
+			RING_COPY_RESPONSE(&queue->tx, cons, &txrsp);
+			if (txrsp.status == XEN_NETIF_RSP_NULL)
 				continue;
 
-			id  = txrsp->id;
+			id  = txrsp.id;
 			skb = queue->tx_skbs[id].skb;
 			if (unlikely(gnttab_query_foreign_access(
 				queue->grant_tx_ref[id]) != 0)) {

@@ -743,7 +743,7 @@ static int xennet_get_extras(struct netf
 			     RING_IDX rp)
 
 {
-	struct xen_netif_extra_info *extra;
+	struct xen_netif_extra_info extra;
 	struct device *dev = &queue->info->netdev->dev;
 	RING_IDX cons = queue->rx.rsp_cons;
 	int err = 0;

@@ -759,24 +759,22 @@ static int xennet_get_extras(struct netf
 			break;
 		}
 
-		extra = (struct xen_netif_extra_info *)
-			RING_GET_RESPONSE(&queue->rx, ++cons);
+		RING_COPY_RESPONSE(&queue->rx, ++cons, &extra);
 
-		if (unlikely(!extra->type ||
-			     extra->type >= XEN_NETIF_EXTRA_TYPE_MAX)) {
+		if (unlikely(!extra.type ||
+			     extra.type >= XEN_NETIF_EXTRA_TYPE_MAX)) {
 			if (net_ratelimit())
 				dev_warn(dev, "Invalid extra type: %d\n",
-					extra->type);
+					 extra.type);
 			err = -EINVAL;
 		} else {
-			memcpy(&extras[extra->type - 1], extra,
-			       sizeof(*extra));
+			extras[extra.type - 1] = extra;
 		}
 
 		skb = xennet_get_rx_skb(queue, cons);
 		ref = xennet_get_rx_ref(queue, cons);
 		xennet_move_rx_slot(queue, skb, ref);
-	} while (extra->flags & XEN_NETIF_EXTRA_FLAG_MORE);
+	} while (extra.flags & XEN_NETIF_EXTRA_FLAG_MORE);
 
 	queue->rx.rsp_cons = cons;
 	return err;

@@ -786,7 +784,7 @@ static int xennet_get_responses(struct n
 				struct netfront_rx_info *rinfo, RING_IDX rp,
 				struct sk_buff_head *list)
 {
-	struct xen_netif_rx_response *rx = &rinfo->rx;
+	struct xen_netif_rx_response *rx = &rinfo->rx, rx_local;
 	struct xen_netif_extra_info *extras = rinfo->extras;
 	struct device *dev = &queue->info->netdev->dev;
 	RING_IDX cons = queue->rx.rsp_cons;

@@ -844,7 +842,8 @@ next:
 			break;
 		}
 
-		rx = RING_GET_RESPONSE(&queue->rx, cons + slots);
+		RING_COPY_RESPONSE(&queue->rx, cons + slots, &rx_local);
+		rx = &rx_local;
 		skb = xennet_get_rx_skb(queue, cons + slots);
 		ref = xennet_get_rx_ref(queue, cons + slots);
 		slots++;

@@ -899,10 +898,11 @@ static int xennet_fill_frags(struct netf
 	struct sk_buff *nskb;
 
 	while ((nskb = __skb_dequeue(list))) {
-		struct xen_netif_rx_response *rx =
-			RING_GET_RESPONSE(&queue->rx, ++cons);
+		struct xen_netif_rx_response rx;
 		skb_frag_t *nfrag = &skb_shinfo(nskb)->frags[0];
 
+		RING_COPY_RESPONSE(&queue->rx, ++cons, &rx);
+
 		if (skb_shinfo(skb)->nr_frags == MAX_SKB_FRAGS) {
 			unsigned int pull_to = NETFRONT_SKB_CB(skb)->pull_to;
 

@@ -917,7 +917,7 @@ static int xennet_fill_frags(struct netf
 
 		skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
 				skb_frag_page(nfrag),
-				rx->offset, rx->status, PAGE_SIZE);
+				rx.offset, rx.status, PAGE_SIZE);
 
 		skb_shinfo(nskb)->nr_frags = 0;
 		kfree_skb(nskb);

@@ -1015,7 +1015,7 @@ static int xennet_poll(struct napi_struc
 	i = queue->rx.rsp_cons;
 	work_done = 0;
 	while ((i != rp) && (work_done < budget)) {
-		memcpy(rx, RING_GET_RESPONSE(&queue->rx, i), sizeof(*rx));
+		RING_COPY_RESPONSE(&queue->rx, i, rx);
 		memset(extras, 0, sizeof(rinfo.extras));
 
 		err = xennet_get_responses(queue, &rinfo, rp, &tmpq);

---
 drivers/net/xen-netfront.c |   80 ++++++++++++++++++++-------------------------
 1 file changed, 37 insertions(+), 43 deletions(-)
@@ -425,7 +425,8 @@ struct xennet_gnttab_make_txreq {
 	struct netfront_queue *queue;
 	struct sk_buff *skb;
 	struct page *page;
-	struct xen_netif_tx_request *tx; /* Last request */
+	struct xen_netif_tx_request *tx;      /* Last request on ring page */
+	struct xen_netif_tx_request tx_local; /* Last request local copy*/
 	unsigned int size;
 };
 

@@ -453,30 +454,27 @@ static void xennet_tx_setup_grant(unsign
 	queue->grant_tx_page[id] = page;
 	queue->grant_tx_ref[id] = ref;
 
-	tx->id = id;
-	tx->gref = ref;
-	tx->offset = offset;
-	tx->size = len;
-	tx->flags = 0;
+	info->tx_local.id = id;
+	info->tx_local.gref = ref;
+	info->tx_local.offset = offset;
+	info->tx_local.size = len;
+	info->tx_local.flags = 0;
+
+	*tx = info->tx_local;
 
 	info->tx = tx;
-	info->size += tx->size;
+	info->size += info->tx_local.size;
 }
 
 static struct xen_netif_tx_request *xennet_make_first_txreq(
-	struct netfront_queue *queue, struct sk_buff *skb,
-	struct page *page, unsigned int offset, unsigned int len)
+	struct xennet_gnttab_make_txreq *info,
+	unsigned int offset, unsigned int len)
 {
-	struct xennet_gnttab_make_txreq info = {
-		.queue = queue,
-		.skb = skb,
-		.page = page,
-		.size = 0,
-	};
+	info->size = 0;
 
-	gnttab_for_one_grant(page, offset, len, xennet_tx_setup_grant, &info);
+	gnttab_for_one_grant(info->page, offset, len, xennet_tx_setup_grant, info);
 
-	return info.tx;
+	return info->tx;
 }
 
 static void xennet_make_one_txreq(unsigned long gfn, unsigned int offset,

@@ -489,35 +487,27 @@ static void xennet_make_one_txreq(unsign
 	xennet_tx_setup_grant(gfn, offset, len, data);
 }
 
-static struct xen_netif_tx_request *xennet_make_txreqs(
-	struct netfront_queue *queue, struct xen_netif_tx_request *tx,
-	struct sk_buff *skb, struct page *page,
+static void xennet_make_txreqs(
+	struct xennet_gnttab_make_txreq *info,
+	struct page *page,
 	unsigned int offset, unsigned int len)
 {
-	struct xennet_gnttab_make_txreq info = {
-		.queue = queue,
-		.skb = skb,
-		.tx = tx,
-	};
-
 	/* Skip unused frames from start of page */
 	page += offset >> PAGE_SHIFT;
 	offset &= ~PAGE_MASK;
 
 	while (len) {
-		info.page = page;
-		info.size = 0;
+		info->page = page;
+		info->size = 0;
 
 		gnttab_foreach_grant_in_range(page, offset, len,
 					      xennet_make_one_txreq,
-					      &info);
+					      info);
 
 		page++;
 		offset = 0;
-		len -= info.size;
+		len -= info->size;
 	}
-
-	return info.tx;
 }
 
 /*

@@ -570,7 +560,7 @@ static int xennet_start_xmit(struct sk_b
 {
 	struct netfront_info *np = netdev_priv(dev);
 	struct netfront_stats *tx_stats = this_cpu_ptr(np->tx_stats);
-	struct xen_netif_tx_request *tx, *first_tx;
+	struct xen_netif_tx_request *first_tx;
 	unsigned int i;
 	int notify;
 	int slots;

@@ -579,6 +569,7 @@ static int xennet_start_xmit(struct sk_b
 	unsigned int len;
 	unsigned long flags;
 	struct netfront_queue *queue = NULL;
+	struct xennet_gnttab_make_txreq info = { };
 	unsigned int num_queues = dev->real_num_tx_queues;
 	u16 queue_index;
 	struct sk_buff *nskb;

@@ -636,21 +627,24 @@ static int xennet_start_xmit(struct sk_b
 	}
 
 	/* First request for the linear area. */
-	first_tx = tx = xennet_make_first_txreq(queue, skb,
-						page, offset, len);
-	offset += tx->size;
+	info.queue = queue;
+	info.skb = skb;
+	info.page = page;
+	first_tx = xennet_make_first_txreq(&info, offset, len);
+	offset += info.tx_local.size;
 	if (offset == PAGE_SIZE) {
 		page++;
 		offset = 0;
 	}
-	len -= tx->size;
+	len -= info.tx_local.size;
 
 	if (skb->ip_summed == CHECKSUM_PARTIAL)
 		/* local packet? */
-		tx->flags |= XEN_NETTXF_csum_blank | XEN_NETTXF_data_validated;
+		first_tx->flags |= XEN_NETTXF_csum_blank |
+				   XEN_NETTXF_data_validated;
 	else if (skb->ip_summed == CHECKSUM_UNNECESSARY)
 		/* remote but checksummed. */
-		tx->flags |= XEN_NETTXF_data_validated;
+		first_tx->flags |= XEN_NETTXF_data_validated;
 
 	/* Optional extra info after the first request. */
 	if (skb_shinfo(skb)->gso_size) {

@@ -659,7 +653,7 @@ static int xennet_start_xmit(struct sk_b
 		gso = (struct xen_netif_extra_info *)
 			RING_GET_REQUEST(&queue->tx, queue->tx.req_prod_pvt++);
 
-		tx->flags |= XEN_NETTXF_extra_info;
+		first_tx->flags |= XEN_NETTXF_extra_info;
 
 		gso->u.gso.size = skb_shinfo(skb)->gso_size;
 		gso->u.gso.type = (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6) ?

@@ -673,13 +667,13 @@ static int xennet_start_xmit(struct sk_b
 	}
 
 	/* Requests for the rest of the linear area. */
-	tx = xennet_make_txreqs(queue, tx, skb, page, offset, len);
+	xennet_make_txreqs(&info, page, offset, len);
 
 	/* Requests for all the frags. */
 	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
 		skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
-		tx = xennet_make_txreqs(queue, tx, skb,
-					skb_frag_page(frag), frag->page_offset,
+		xennet_make_txreqs(&info, skb_frag_page(frag),
+					frag->page_offset,
 					skb_frag_size(frag));
 	}
 

---
 drivers/net/xen-netfront.c |   61 ++++++++++++++++++---------------------------
 1 file changed, 25 insertions(+), 36 deletions(-)
@@ -121,17 +121,11 @@ struct netfront_queue {
 
 	/*
 	 * {tx,rx}_skbs store outstanding skbuffs. Free tx_skb entries
-	 * are linked from tx_skb_freelist through skb_entry.link.
-	 *
-	 *  NB. Freelist index entries are always going to be less than
-	 *  PAGE_OFFSET, whereas pointers to skbs will always be equal or
-	 *  greater than PAGE_OFFSET: we use this property to distinguish
-	 *  them.
+	 * are linked from tx_skb_freelist through tx_link.
 	 */
-	union skb_entry {
-		struct sk_buff *skb;
-		unsigned long link;
-	} tx_skbs[NET_TX_RING_SIZE];
+	struct sk_buff *tx_skbs[NET_TX_RING_SIZE];
+	unsigned short tx_link[NET_TX_RING_SIZE];
+#define TX_LINK_NONE 0xffff
 	grant_ref_t gref_tx_head;
 	grant_ref_t grant_tx_ref[NET_TX_RING_SIZE];
 	struct page *grant_tx_page[NET_TX_RING_SIZE];

@@ -169,33 +163,25 @@ struct netfront_rx_info {
 	struct xen_netif_extra_info extras[XEN_NETIF_EXTRA_TYPE_MAX - 1];
 };
 
-static void skb_entry_set_link(union skb_entry *list, unsigned short id)
-{
-	list->link = id;
-}
-
-static int skb_entry_is_link(const union skb_entry *list)
-{
-	BUILD_BUG_ON(sizeof(list->skb) != sizeof(list->link));
-	return (unsigned long)list->skb < PAGE_OFFSET;
-}
-
 /*
  * Access macros for acquiring freeing slots in tx_skbs[].
  */
 
-static void add_id_to_freelist(unsigned *head, union skb_entry *list,
-			       unsigned short id)
+static void add_id_to_list(unsigned *head, unsigned short *list,
+			   unsigned short id)
 {
-	skb_entry_set_link(&list[id], *head);
+	list[id] = *head;
 	*head = id;
 }
 
-static unsigned short get_id_from_freelist(unsigned *head,
-					   union skb_entry *list)
+static unsigned short get_id_from_list(unsigned *head, unsigned short *list)
 {
 	unsigned int id = *head;
-	*head = list[id].link;
+
+	if (id != TX_LINK_NONE) {
+		*head = list[id];
+		list[id] = TX_LINK_NONE;
+	}
 	return id;
 }
 

@@ -396,7 +382,8 @@ static void xennet_tx_buf_gc(struct netf
 				continue;
 
 			id  = txrsp.id;
-			skb = queue->tx_skbs[id].skb;
+			skb = queue->tx_skbs[id];
+			queue->tx_skbs[id] = NULL;
 			if (unlikely(gnttab_query_foreign_access(
 				queue->grant_tx_ref[id]) != 0)) {
 				pr_alert("%s: warning -- grant still in use by backend domain\n",

@@ -409,7 +396,7 @@ static void xennet_tx_buf_gc(struct netf
 				&queue->gref_tx_head, queue->grant_tx_ref[id]);
 			queue->grant_tx_ref[id] = GRANT_INVALID_REF;
 			queue->grant_tx_page[id] = NULL;
-			add_id_to_freelist(&queue->tx_skb_freelist, queue->tx_skbs, id);
+			add_id_to_list(&queue->tx_skb_freelist, queue->tx_link, id);
 			dev_kfree_skb_irq(skb);
 		}
 

@@ -442,7 +429,7 @@ static void xennet_tx_setup_grant(unsign
 	struct netfront_queue *queue = info->queue;
 	struct sk_buff *skb = info->skb;
 
-	id = get_id_from_freelist(&queue->tx_skb_freelist, queue->tx_skbs);
+	id = get_id_from_list(&queue->tx_skb_freelist, queue->tx_link);
 	tx = RING_GET_REQUEST(&queue->tx, queue->tx.req_prod_pvt++);
 	ref = gnttab_claim_grant_reference(&queue->gref_tx_head);
 	WARN_ON_ONCE(IS_ERR_VALUE((unsigned long)(int)ref));

@@ -450,7 +437,7 @@ static void xennet_tx_setup_grant(unsign
 	gnttab_grant_foreign_access_ref(ref, queue->info->xbdev->otherend_id,
 					gfn, GNTMAP_readonly);
 
-	queue->tx_skbs[id].skb = skb;
+	queue->tx_skbs[id] = skb;
 	queue->grant_tx_page[id] = page;
 	queue->grant_tx_ref[id] = ref;
 

@@ -1131,17 +1118,18 @@ static void xennet_release_tx_bufs(struc
 
 	for (i = 0; i < NET_TX_RING_SIZE; i++) {
 		/* Skip over entries which are actually freelist references */
-		if (skb_entry_is_link(&queue->tx_skbs[i]))
+		if (!queue->tx_skbs[i])
 			continue;
 
-		skb = queue->tx_skbs[i].skb;
+		skb = queue->tx_skbs[i];
+		queue->tx_skbs[i] = NULL;
 		get_page(queue->grant_tx_page[i]);
 		gnttab_end_foreign_access(queue->grant_tx_ref[i],
 					  GNTMAP_readonly,
 					  (unsigned long)page_address(queue->grant_tx_page[i]));
 		queue->grant_tx_page[i] = NULL;
 		queue->grant_tx_ref[i] = GRANT_INVALID_REF;
-		add_id_to_freelist(&queue->tx_skb_freelist, queue->tx_skbs, i);
+		add_id_to_list(&queue->tx_skb_freelist, queue->tx_link, i);
 		dev_kfree_skb_irq(skb);
 	}
 }

@@ -1624,13 +1612,14 @@ static int xennet_init_queue(struct netf
 	snprintf(queue->name, sizeof(queue->name), "vif%s-q%u",
 		 devid, queue->id);
 
-	/* Initialise tx_skbs as a free chain containing every entry. */
+	/* Initialise tx_skb_freelist as a free chain containing every entry. */
 	queue->tx_skb_freelist = 0;
 	for (i = 0; i < NET_TX_RING_SIZE; i++) {
-		skb_entry_set_link(&queue->tx_skbs[i], i+1);
+		queue->tx_link[i] = i + 1;
 		queue->grant_tx_ref[i] = GRANT_INVALID_REF;
 		queue->grant_tx_page[i] = NULL;
 	}
+	queue->tx_link[NET_TX_RING_SIZE - 1] = TX_LINK_NONE;
 
 	/* Clear out rx_skbs */
 	for (i = 0; i < NET_RX_RING_SIZE; i++) {

---
 drivers/net/xen-netfront.c |   80 ++++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 75 insertions(+), 5 deletions(-)
@@ -126,10 +126,12 @@ struct netfront_queue {
 	struct sk_buff *tx_skbs[NET_TX_RING_SIZE];
 	unsigned short tx_link[NET_TX_RING_SIZE];
 #define TX_LINK_NONE 0xffff
+#define TX_PENDING   0xfffe
 	grant_ref_t gref_tx_head;
 	grant_ref_t grant_tx_ref[NET_TX_RING_SIZE];
 	struct page *grant_tx_page[NET_TX_RING_SIZE];
 	unsigned tx_skb_freelist;
+	unsigned int tx_pend_queue;
 
 	spinlock_t   rx_lock ____cacheline_aligned_in_smp;
 	struct xen_netif_rx_front_ring rx;

@@ -155,6 +157,9 @@ struct netfront_info {
 	struct netfront_stats __percpu *rx_stats;
 	struct netfront_stats __percpu *tx_stats;
 
+	/* Is device behaving sane? */
+	bool broken;
+
 	atomic_t rx_gso_checksum_fixup;
 };
 

@@ -339,7 +344,7 @@ static int xennet_open(struct net_device
 	unsigned int i = 0;
 	struct netfront_queue *queue = NULL;
 
-	if (!np->queues)
+	if (!np->queues || np->broken)
 		return -ENODEV;
 
 	for (i = 0; i < num_queues; ++i) {

@@ -367,11 +372,17 @@ static void xennet_tx_buf_gc(struct netf
 	unsigned short id;
 	struct sk_buff *skb;
 	bool more_to_do;
+	const struct device *dev = &queue->info->netdev->dev;
 
 	BUG_ON(!netif_carrier_ok(queue->info->netdev));
 
 	do {
 		prod = queue->tx.sring->rsp_prod;
+		if (RING_RESPONSE_PROD_OVERFLOW(&queue->tx, prod)) {
+			dev_alert(dev, "Illegal number of responses %u\n",
+				  prod - queue->tx.rsp_cons);
+			goto err;
+		}
 		rmb(); /* Ensure we see responses up to 'rp'. */
 
 		for (cons = queue->tx.rsp_cons; cons != prod; cons++) {

@@ -381,14 +392,27 @@ static void xennet_tx_buf_gc(struct netf
 			if (txrsp.status == XEN_NETIF_RSP_NULL)
 				continue;
 
-			id  = txrsp.id;
+			id = txrsp.id;
+			if (id >= RING_SIZE(&queue->tx)) {
+				dev_alert(dev,
+					  "Response has incorrect id (%u)\n",
+					  id);
+				goto err;
+			}
+			if (queue->tx_link[id] != TX_PENDING) {
+				dev_alert(dev,
+					  "Response for inactive request\n");
+				goto err;
+			}
+
+			queue->tx_link[id] = TX_LINK_NONE;
 			skb = queue->tx_skbs[id];
 			queue->tx_skbs[id] = NULL;
 			if (unlikely(gnttab_query_foreign_access(
 				queue->grant_tx_ref[id]) != 0)) {
-				pr_alert("%s: warning -- grant still in use by backend domain\n",
-					 __func__);
-				BUG();
+				dev_alert(dev,
+					  "Grant still in use by backend domain\n");
+				goto err;
 			}
 			gnttab_end_foreign_access_ref(
 				queue->grant_tx_ref[id], GNTMAP_readonly);

@@ -406,6 +430,12 @@ static void xennet_tx_buf_gc(struct netf
 	} while (more_to_do);
 
 	xennet_maybe_wake_tx(queue);
+
+	return;
+
+ err:
+	queue->info->broken = true;
+	dev_alert(dev, "Disabled for further use\n");
 }
 
 struct xennet_gnttab_make_txreq {

@@ -449,6 +479,12 @@ static void xennet_tx_setup_grant(unsign
 
 	*tx = info->tx_local;
 
+	/*
+	 * Put the request in the pending queue, it will be set to be pending
+	 * when the producer index is about to be raised.
+	 */
+	add_id_to_list(&queue->tx_pend_queue, queue->tx_link, id);
+
 	info->tx = tx;
 	info->size += info->tx_local.size;
 }

@@ -541,6 +577,15 @@ static u16 xennet_select_queue(struct ne
 	return queue_idx;
 }
 
+static void xennet_mark_tx_pending(struct netfront_queue *queue)
+{
+	unsigned int i;
+
+	while ((i = get_id_from_list(&queue->tx_pend_queue, queue->tx_link)) !=
+		TX_LINK_NONE)
+		queue->tx_link[i] = TX_PENDING;
+}
+
 #define MAX_XEN_SKB_FRAGS (65536 / XEN_PAGE_SIZE + 1)
 
 static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev)

@@ -564,6 +609,8 @@ static int xennet_start_xmit(struct sk_b
 	/* Drop the packet if no queues are set up */
 	if (num_queues < 1)
 		goto drop;
+	if (unlikely(np->broken))
+		goto drop;
 	/* Determine which queue to transmit this SKB on */
 	queue_index = skb_get_queue_mapping(skb);
 	queue = &np->queues[queue_index];

@@ -667,6 +714,8 @@ static int xennet_start_xmit(struct sk_b
 	/* First request has the packet length. */
 	first_tx->size = skb->len;
 
+	xennet_mark_tx_pending(queue);
+
 	RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&queue->tx, notify);
 	if (notify)
 		notify_remote_via_irq(queue->tx_irq);

@@ -991,6 +1040,13 @@ static int xennet_poll(struct napi_struc
 	skb_queue_head_init(&tmpq);
 
 	rp = queue->rx.sring->rsp_prod;
+	if (RING_RESPONSE_PROD_OVERFLOW(&queue->rx, rp)) {
+		dev_alert(&dev->dev, "Illegal number of responses %u\n",
+			  rp - queue->rx.rsp_cons);
+		queue->info->broken = true;
+		spin_unlock(&queue->rx_lock);
+		return 0;
+	}
 	rmb(); /* Ensure we see queued responses up to 'rp'. */
 
 	i = queue->rx.rsp_cons;

@@ -1209,6 +1265,9 @@ static irqreturn_t xennet_tx_interrupt(i
 	struct netfront_queue *queue = dev_id;
 	unsigned long flags;
 
+	if (queue->info->broken)
+		return IRQ_HANDLED;
+
 	spin_lock_irqsave(&queue->tx_lock, flags);
 	xennet_tx_buf_gc(queue);
 	spin_unlock_irqrestore(&queue->tx_lock, flags);

@@ -1221,6 +1280,9 @@ static irqreturn_t xennet_rx_interrupt(i
 	struct netfront_queue *queue = dev_id;
 	struct net_device *dev = queue->info->netdev;
 
+	if (queue->info->broken)
+		return IRQ_HANDLED;
+
 	if (likely(netif_carrier_ok(dev) &&
 		   RING_HAS_UNCONSUMED_RESPONSES(&queue->rx)))
 		napi_schedule(&queue->napi);

@@ -1242,6 +1304,10 @@ static void xennet_poll_controller(struc
 	struct netfront_info *info = netdev_priv(dev);
 	unsigned int num_queues = dev->real_num_tx_queues;
 	unsigned int i;
+
+	if (info->broken)
+		return;
+
 	for (i = 0; i < num_queues; ++i)
 		xennet_interrupt(0, &info->queues[i]);
 }

@@ -1614,6 +1680,7 @@ static int xennet_init_queue(struct netf
 
 	/* Initialise tx_skb_freelist as a free chain containing every entry. */
 	queue->tx_skb_freelist = 0;
+	queue->tx_pend_queue = TX_LINK_NONE;
 	for (i = 0; i < NET_TX_RING_SIZE; i++) {
 		queue->tx_link[i] = i + 1;
 		queue->grant_tx_ref[i] = GRANT_INVALID_REF;

@@ -1824,6 +1891,9 @@ static int talk_to_netback(struct xenbus
 	if (info->queues)
 		xennet_destroy_queues(info);
 
+	/* For the case of a reconnect reset the "broken" indicator. */
+	info->broken = false;
+
 	err = xennet_create_queues(info, &num_queues);
 	if (err < 0) {
 		xenbus_dev_fatal(dev, err, "creating queues");

---
 drivers/tty/hvc/hvc_xen.c |   17 ++++++++++++++---
 1 file changed, 14 insertions(+), 3 deletions(-)
@@ -99,7 +99,11 @@ static int __write_console(struct xencon
 	cons = intf->out_cons;
 	prod = intf->out_prod;
 	mb();			/* update queue values before going on */
-	BUG_ON((prod - cons) > sizeof(intf->out));
+
+	if ((prod - cons) > sizeof(intf->out)) {
+		pr_err_once("xencons: Illegal ring page indices");
+		return -EINVAL;
+	}
 
 	while ((sent < len) && ((prod - cons) < sizeof(intf->out)))
 		intf->out[MASK_XENCONS_IDX(prod++, intf->out)] = data[sent++];

@@ -127,7 +131,10 @@ static int domU_write_console(uint32_t v
 	 */
 	while (len) {
 		int sent = __write_console(cons, data, len);
-		
+
+		if (sent < 0)
+			return sent;
+
 		data += sent;
 		len -= sent;
 

@@ -151,7 +158,11 @@ static int domU_read_console(uint32_t vt
 	cons = intf->in_cons;
 	prod = intf->in_prod;
 	mb();			/* get pointers before reading ring */
-	BUG_ON((prod - cons) > sizeof(intf->in));
+
+	if ((prod - cons) > sizeof(intf->in)) {
+		pr_err_once("xencons: Illegal ring page indices");
+		return -EINVAL;
+	}
 
 	while (cons != prod && recv < len)
 		buf[recv++] = intf->in[MASK_XENCONS_IDX(cons++, intf->in)];

---
 include/linux/ipc_namespace.h |   15 +++
 include/linux/sched/task.h    |    2 
 include/linux/shm.h           |   13 ++-
 ipc/shm.c                     |  176 +++++++++++++++++++++++++++++++-----------
 4 files changed, 159 insertions(+), 47 deletions(-)
@@ -127,6 +127,16 @@ static inline struct ipc_namespace *get_
 	return ns;
 }
 
+static inline struct ipc_namespace *get_ipc_ns_not_zero(struct ipc_namespace *ns)
+{
+	if (ns) {
+		if (refcount_inc_not_zero(&ns->count))
+			return ns;
+	}
+
+	return NULL;
+}
+
 extern void put_ipc_ns(struct ipc_namespace *ns);
 #else
 static inline struct ipc_namespace *copy_ipcs(unsigned long flags,

@@ -142,6 +152,11 @@ static inline struct ipc_namespace *get_
 {
 	return ns;
 }
+
+static inline struct ipc_namespace *get_ipc_ns_not_zero(struct ipc_namespace *ns)
+{
+	return ns;
+}
 
 static inline void put_ipc_ns(struct ipc_namespace *ns)
 {

@@ -122,7 +122,7 @@ static inline struct vm_struct *task_sta
  * Protects ->fs, ->files, ->mm, ->group_info, ->comm, keyring
  * subscriptions and synchronises with wait4().  Also used in procfs.  Also
  * pins the final release of task.io_context.  Also protects ->cpuset and
- * ->cgroup.subsys[]. And ->vfork_done.
+ * ->cgroup.subsys[]. And ->vfork_done. And ->sysvshm.shm_clist.
  *
  * Nests both inside and outside of read_lock(&tasklist_lock).
  * It must not be nested with write_lock_irq(&tasklist_lock),

@@ -20,9 +20,18 @@ struct shmid_kernel /* private to the ke
 	pid_t			shm_lprid;
 	struct user_struct	*mlock_user;
 
-	/* The task created the shm object.  NULL if the task is dead. */
+	/*
+	 * The task created the shm object, for
+	 * task_lock(shp->shm_creator)
+	 */
 	struct task_struct	*shm_creator;
-	struct list_head	shm_clist;	/* list by creator */
+
+	/*
+	 * List by creator. task_lock(->shm_creator) required for read/write.
+	 * If list_empty(), then the creator is dead already.
+	 */
+	struct list_head	shm_clist;
+	struct ipc_namespace	*ns;
 } __randomize_layout;
 
 /* shm_mode upper byte flags */

---
 ipc/util.c |    6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)
@@ -409,8 +409,8 @@ static int ipcget_public(struct ipc_name
 static void ipc_kht_remove(struct ipc_ids *ids, struct kern_ipc_perm *ipcp)
 {
 	if (ipcp->key != IPC_PRIVATE)
-		rhashtable_remove_fast(&ids->key_ht, &ipcp->khtnode,
-				       ipc_kht_params);
+		WARN_ON_ONCE(rhashtable_remove_fast(&ids->key_ht, &ipcp->khtnode,
+				       ipc_kht_params));
 }
 
 /**

@@ -425,7 +425,7 @@ void ipc_rmid(struct ipc_ids *ids, struc
 {
 	int lid = ipcid_to_idx(ipcp->id);
 
-	idr_remove(&ids->ipcs_idr, lid);
+	WARN_ON_ONCE(idr_remove(&ids->ipcs_idr, lid) != ipcp);
 	ipc_kht_remove(ids, ipcp);
 	ids->in_use--;
 	ipcp->deleted = true;

---
 fs/nfs/nfs42proc.c |    5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)
@@ -186,8 +186,9 @@ static ssize_t _nfs42_proc_copy(struct f
 		goto out;
 	}
 
-	truncate_pagecache_range(dst_inode, pos_dst,
-				 pos_dst + res->write_res.count);
+	WARN_ON_ONCE(invalidate_inode_pages2_range(dst_inode->i_mapping,
+					pos_dst >> PAGE_SHIFT,
+					(pos_dst + res->write_res.count - 1) >> PAGE_SHIFT));
 
 	status = res->write_res.count;
 out:

---
 mm/hugetlb.c |   53 +++++++++++++++++++++++++++++++++++++++++++----------
 1 file changed, 43 insertions(+), 10 deletions(-)
@@ -3384,8 +3384,8 @@ void __unmap_hugepage_range(struct mmu_g
 	struct page *page;
 	struct hstate *h = hstate_vma(vma);
 	unsigned long sz = huge_page_size(h);
-	const unsigned long mmun_start = start;	/* For mmu_notifiers */
-	const unsigned long mmun_end   = end;	/* For mmu_notifiers */
+	unsigned long mmun_start = start;	/* For mmu_notifiers */
+	unsigned long mmun_end   = end;		/* For mmu_notifiers */
 	bool force_flush = false;
 
 	WARN_ON(!is_vm_hugetlb_page(vma));

@@ -3398,6 +3398,11 @@ void __unmap_hugepage_range(struct mmu_g
 	 */
 	tlb_remove_check_page_size_change(tlb, sz);
 	tlb_start_vma(tlb, vma);
+
+	/*
+	 * If sharing possible, alert mmu notifiers of worst case.
+	 */
+	adjust_range_if_pmd_sharing_possible(vma, &mmun_start, &mmun_end);
 	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
 	address = start;
 	for (; address < end; address += sz) {

@@ -3508,12 +3513,23 @@ void unmap_hugepage_range(struct vm_area
 {
 	struct mm_struct *mm;
 	struct mmu_gather tlb;
+	unsigned long tlb_start = start;
+	unsigned long tlb_end = end;
+
+	/*
+	 * If shared PMDs were possibly used within this vma range, adjust
+	 * start/end for worst case tlb flushing.
+	 * Note that we can not be sure if PMDs are shared until we try to
+	 * unmap pages.  However, we want to make sure TLB flushing covers
+	 * the largest possible range.
+	 */
+	adjust_range_if_pmd_sharing_possible(vma, &tlb_start, &tlb_end);
 
 	mm = vma->vm_mm;
 
-	tlb_gather_mmu(&tlb, mm, start, end);
+	tlb_gather_mmu(&tlb, mm, tlb_start, tlb_end);
 	__unmap_hugepage_range(&tlb, vma, start, end, ref_page);
-	tlb_finish_mmu(&tlb, start, end);
+	tlb_finish_mmu(&tlb, tlb_start, tlb_end);
 }
 
 /*

@@ -4408,11 +4424,21 @@ unsigned long hugetlb_change_protection(
 	pte_t pte;
 	struct hstate *h = hstate_vma(vma);
 	unsigned long pages = 0;
+	unsigned long f_start = start;
+	unsigned long f_end = end;
+	bool shared_pmd = false;
+
+	/*
+	 * In the case of shared PMDs, the area to flush could be beyond
+	 * start/end.  Set f_start/f_end to cover the maximum possible
+	 * range if PMD sharing is possible.
+	 */
+	adjust_range_if_pmd_sharing_possible(vma, &f_start, &f_end);
 
 	BUG_ON(address >= end);
-	flush_cache_range(vma, address, end);
+	flush_cache_range(vma, f_start, f_end);
 
-	mmu_notifier_invalidate_range_start(mm, start, end);
+	mmu_notifier_invalidate_range_start(mm, f_start, f_end);
 	i_mmap_lock_write(vma->vm_file->f_mapping);
 	for (; address < end; address += huge_page_size(h)) {
 		spinlock_t *ptl;

@@ -4423,6 +4449,7 @@ unsigned long hugetlb_change_protection(
 		if (huge_pmd_unshare(mm, &address, ptep)) {
 			pages++;
 			spin_unlock(ptl);
+			shared_pmd = true;
 			continue;
 		}
 		pte = huge_ptep_get(ptep);

@@ -4458,12 +4485,18 @@ unsigned long hugetlb_change_protection(
 	 * Must flush TLB before releasing i_mmap_rwsem: x86's huge_pmd_unshare
 	 * may have cleared our pud entry and done put_page on the page table:
 	 * once we release i_mmap_rwsem, another task can do the final put_page
-	 * and that page table be reused and filled with junk.
+	 * and that page table be reused and filled with junk.  If we actually
+	 * did unshare a page of pmds, flush the range corresponding to the pud.
 	 */
-	flush_hugetlb_tlb_range(vma, start, end);
-	mmu_notifier_invalidate_range(mm, start, end);
+	if (shared_pmd) {
+		flush_hugetlb_tlb_range(vma, f_start, f_end);
+		mmu_notifier_invalidate_range(mm, f_start, f_end);
+	} else {
+		flush_hugetlb_tlb_range(vma, start, end);
+		mmu_notifier_invalidate_range(mm, start, end);
+	}
 	i_mmap_unlock_write(vma->vm_file->f_mapping);
-	mmu_notifier_invalidate_range_end(mm, start, end);
+	mmu_notifier_invalidate_range_end(mm, f_start, f_end);
 
 	return pages << h->order;
 }

---
 net/ipv4/devinet.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
index d4d53aea2c600..d9bb3ae785608 100644
@@ -2324,7 +2324,7 @@ static int __devinet_sysctl_register(struct net *net, char *dev_name,
 free:
 	kfree(t);
 out:
-	return -ENOBUFS;
+	return -ENOMEM;
 }
 
 static void __devinet_sysctl_unregister(struct net *net,

2.33.0
---
 drivers/platform/x86/thinkpad_acpi.c | 12 ------------
 1 file changed, 12 deletions(-)
index 9d836d779d475..05b3e0f724fcf 100644
@@ -1180,15 +1180,6 @@ static int tpacpi_rfk_update_swstate(const struct tpacpi_rfk *tp_rfk)
 	return status;
 }
 
-/* Query FW and update rfkill sw state for all rfkill switches */
-static void tpacpi_rfk_update_swstate_all(void)
-{
-	unsigned int i;
-
-	for (i = 0; i < TPACPI_RFK_SW_MAX; i++)
-		tpacpi_rfk_update_swstate(tpacpi_rfkill_switches[i]);
-}
-
 /*
  * Sync the HW-blocking state of all rfkill switches,
  * do notice it causes the rfkill core to schedule uevents

@@ -3025,9 +3016,6 @@ static void tpacpi_send_radiosw_update(void)
 	if (wlsw == TPACPI_RFK_RADIO_OFF)
 		tpacpi_rfk_update_hwblock_state(true);
 
-	/* Sync sw blocking state */
-	tpacpi_rfk_update_swstate_all();
-
 	/* Sync hw blocking state last if it is hw-unblocked */
 	if (wlsw == TPACPI_RFK_RADIO_ON)
 		tpacpi_rfk_update_hwblock_state(false);

2.33.0
---
 arch/s390/kernel/setup.c | 3 ---
 1 file changed, 3 deletions(-)
index ceaee215e2436..e9ef093eb6767 100644
@@ -706,9 +706,6 @@ static void __init setup_memory(void)
 		storage_key_init_range(reg->base, reg->base + reg->size);
 	}
 	psw_set_key(PAGE_DEFAULT_KEY);
-
-	/* Only cosmetics */
-	memblock_enforce_memory_limit(memblock_end_of_DRAM());
 }
 
 /*

2.33.0
  ------------[ cut here ]------------
  WARNING: CPU: 28 PID: 843680 at fs/btrfs/check-integrity.c:2196 btrfsic_process_written_superblock+0x22a/0x2a0 [btrfs]
  CPU: 28 PID: 843680 Comm: umount Not tainted 5.15.0-0.rc5.39.el8.x86_64 #1
  Hardware name: Dell Inc. Precision T7610/0NK70N, BIOS A18 09/11/2019
  RIP: 0010:btrfsic_process_written_superblock+0x22a/0x2a0 [btrfs]
  RSP: 0018:ffffb642afb47940 EFLAGS: 00010246
  RAX: 0000000000000000 RBX: 0000000000000002 RCX: 0000000000000000
  RDX: 00000000ffffffff RSI: ffff8b722fc97d00 RDI: ffff8b722fc97d00
  RBP: ffff8b5601c00000 R08: 0000000000000000 R09: c0000000ffff7fff
  R10: 0000000000000001 R11: ffffb642afb476f8 R12: ffffffffffffffff
  R13: ffffb642afb47974 R14: ffff8b5499254c00 R15: 0000000000000003
  FS:  00007f00a06d4080(0000) GS:ffff8b722fc80000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 00007fff5cff5ff0 CR3: 00000001c0c2a006 CR4: 00000000001706e0
  Call Trace:
   btrfsic_process_written_block+0x2f7/0x850 [btrfs]
   __btrfsic_submit_bio.part.19+0x310/0x330 [btrfs]
   ? bio_associate_blkg_from_css+0xa4/0x2c0
   btrfsic_submit_bio+0x18/0x30 [btrfs]
   write_dev_supers+0x81/0x2a0 [btrfs]
   ? find_get_pages_range_tag+0x219/0x280
   ? pagevec_lookup_range_tag+0x24/0x30
   ? __filemap_fdatawait_range+0x6d/0xf0
   ? __raw_callee_save___native_queued_spin_unlock+0x11/0x1e
   ? find_first_extent_bit+0x9b/0x160 [btrfs]
   ? __raw_callee_save___native_queued_spin_unlock+0x11/0x1e
   write_all_supers+0x1b3/0xa70 [btrfs]
   ? __raw_callee_save___native_queued_spin_unlock+0x11/0x1e
   btrfs_commit_transaction+0x59d/0xac0 [btrfs]
   close_ctree+0x11d/0x339 [btrfs]
   generic_shutdown_super+0x71/0x110
   kill_anon_super+0x14/0x30
   btrfs_kill_super+0x12/0x20 [btrfs]
   deactivate_locked_super+0x31/0x70
   cleanup_mnt+0xb8/0x140
   task_work_run+0x6d/0xb0
   exit_to_user_mode_prepare+0x1f0/0x200
   syscall_exit_to_user_mode+0x12/0x30
   do_syscall_64+0x46/0x80
   entry_SYSCALL_64_after_hwframe+0x44/0xae
  RIP: 0033:0x7f009f711dfb
  RSP: 002b:00007fff5cff7928 EFLAGS: 00000246 ORIG_RAX: 00000000000000a6
  RAX: 0000000000000000 RBX: 000055b68c6c9970 RCX: 00007f009f711dfb
  RDX: 0000000000000001 RSI: 0000000000000000 RDI: 000055b68c6c9b50
  RBP: 0000000000000000 R08: 000055b68c6ca900 R09: 00007f009f795580
  R10: 0000000000000000 R11: 0000000000000246 R12: 000055b68c6c9b50
  R13: 00007f00a04bf184 R14: 0000000000000000 R15: 00000000ffffffff
  ---[ end trace 2c4b82abcef9eec4 ]---
  S-65536(sdb2/65536/1)
   -->
  M-1064960(sdb2/1064960/1)
---
 fs/btrfs/disk-io.c | 14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)
index ace58d6a270b6..41ebc613ca4cf 100644
@@ -3339,11 +3339,23 @@ static void btrfs_end_empty_barrier(struct bio *bio)
  */
 static void write_dev_flush(struct btrfs_device *device)
 {
-	struct request_queue *q = bdev_get_queue(device->bdev);
 	struct bio *bio = device->flush_bio;
 
+#ifndef CONFIG_BTRFS_FS_CHECK_INTEGRITY
+	/*
+	 * When a disk has write caching disabled, we skip submission of a bio
+	 * with flush and sync requests before writing the superblock, since
+	 * it's not needed. However when the integrity checker is enabled, this
+	 * results in reports that there are metadata blocks referred by a
+	 * superblock that were not properly flushed. So don't skip the bio
+	 * submission only when the integrity checker is enabled for the sake
+	 * of simplicity, since this is a debug tool and not meant for use in
+	 * non-debug builds.
+	 */
+	struct request_queue *q = bdev_get_queue(device->bdev);
 	if (!test_bit(QUEUE_FLAG_WC, &q->queue_flags))
 		return;
+#endif
 
 	bio_reset(bio);
 	bio->bi_end_io = btrfs_end_empty_barrier;

2.33.0
---
 drivers/thermal/thermal_core.c | 2 ++
 1 file changed, 2 insertions(+)
index 94820f25a15ff..8374b8078b7df 100644
@@ -457,6 +457,8 @@ static void thermal_zone_device_init(struct thermal_zone_device *tz)
 {
 	struct thermal_instance *pos;
 	tz->temperature = THERMAL_TEMP_INVALID;
+	tz->prev_low_trip = -INT_MAX;
+	tz->prev_high_trip = INT_MAX;
 	list_for_each_entry(pos, &tz->thermal_instances, tz_node)
 		pos->initialized = false;
 }

2.33.0
---
 drivers/scsi/scsi_transport_iscsi.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)
index d276d84c0f7a2..26c6f1b288013 100644
@@ -1892,12 +1892,12 @@ static void session_recovery_timedout(struct work_struct *work)
 	}
 	spin_unlock_irqrestore(&session->lock, flags);
 
-	if (session->transport->session_recovery_timedout)
-		session->transport->session_recovery_timedout(session);
-
 	ISCSI_DBG_TRANS_SESSION(session, "Unblocking SCSI target\n");
 	scsi_target_unblock(&session->dev, SDEV_TRANSPORT_OFFLINE);
 	ISCSI_DBG_TRANS_SESSION(session, "Completed unblocking SCSI target\n");
+
+	if (session->transport->session_recovery_timedout)
+		session->transport->session_recovery_timedout(session);
 }
 
 static void __iscsi_unblock_session(struct work_struct *work)

2.33.0
        return;
---
 drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c | 4 ++++
 1 file changed, 4 insertions(+)
index 408b63faf9a81..c4e56784ed1b8 100644
@@ -336,6 +336,10 @@ static void hns_dsaf_ge_srst_by_port(struct dsaf_device *dsaf_dev, u32 port,
 		return;
 
 	if (!HNS_DSAF_IS_DEBUG(dsaf_dev)) {
+		/* DSAF_MAX_PORT_NUM is 6, but DSAF_GE_NUM is 8.
+		   We need check to prevent array overflow */
+		if (port >= DSAF_MAX_PORT_NUM)
+			return;
 		reg_val_1  = 0x1 << port;
 		port_rst_off = dsaf_dev->mac_cb[port]->port_rst_off;
 		/* there is difference between V1 and V2 in register.*/

2.33.0
---
 drivers/net/ethernet/dec/tulip/de4x5.c | 30 +++++++++++++++-----------
 1 file changed, 17 insertions(+), 13 deletions(-)
index 8f108a30cba66..84cf7b4582f3e 100644
@@ -4994,19 +4994,23 @@ mii_get_phy(struct net_device *dev)
 	}
 	if ((j == limit) && (i < DE4X5_MAX_MII)) {
 	    for (k=0; k < DE4X5_MAX_PHY && lp->phy[k].id; k++);
-	    lp->phy[k].addr = i;
-	    lp->phy[k].id = id;
-	    lp->phy[k].spd.reg = GENERIC_REG;      /* ANLPA register         */
-	    lp->phy[k].spd.mask = GENERIC_MASK;    /* 100Mb/s technologies   */
-	    lp->phy[k].spd.value = GENERIC_VALUE;  /* TX & T4, H/F Duplex    */
-	    lp->mii_cnt++;
-	    lp->active++;
-	    printk("%s: Using generic MII device control. If the board doesn't operate,\nplease mail the following dump to the author:\n", dev->name);
-	    j = de4x5_debug;
-	    de4x5_debug |= DEBUG_MII;
-	    de4x5_dbg_mii(dev, k);
-	    de4x5_debug = j;
-	    printk("\n");
+	    if (k < DE4X5_MAX_PHY) {
+		lp->phy[k].addr = i;
+		lp->phy[k].id = id;
+		lp->phy[k].spd.reg = GENERIC_REG;      /* ANLPA register         */
+		lp->phy[k].spd.mask = GENERIC_MASK;    /* 100Mb/s technologies   */
+		lp->phy[k].spd.value = GENERIC_VALUE;  /* TX & T4, H/F Duplex    */
+		lp->mii_cnt++;
+		lp->active++;
+		printk("%s: Using generic MII device control. If the board doesn't operate,\nplease mail the following dump to the author:\n", dev->name);
+		j = de4x5_debug;
+		de4x5_debug |= DEBUG_MII;
+		de4x5_dbg_mii(dev, k);
+		de4x5_debug = j;
+		printk("\n");
+	    } else {
+		goto purgatory;
+	    }
 	}
     }
   purgatory:

2.33.0
---
 drivers/net/ethernet/dec/tulip/de4x5.c | 4 ++++
 1 file changed, 4 insertions(+)
index 84cf7b4582f3e..09a65f8f62038 100644
@@ -4703,6 +4703,10 @@ type3_infoblock(struct net_device *dev, u_char count, u_char *p)
         lp->ibn = 3;
         lp->active = *p++;
 	if (MOTO_SROM_BUG) lp->active = 0;
+	/* if (MOTO_SROM_BUG) statement indicates lp->active could
+	 * be 8 (i.e. the size of array lp->phy) */
+	if (WARN_ON(lp->active >= ARRAY_SIZE(lp->phy)))
+		return -EINVAL;
 	lp->phy[lp->active].gep = (*p ? p : NULL); p += (2 * (*p) + 1);
 	lp->phy[lp->active].rst = (*p ? p : NULL); p += (2 * (*p) + 1);
 	lp->phy[lp->active].mc  = get_unaligned_le16(p); p += 2;

2.33.0
---
 tools/perf/ui/hist.c   | 28 ++++++++++++++--------------
 tools/perf/util/hist.h |  1 -
 2 files changed, 14 insertions(+), 15 deletions(-)
index 706f6f1e9c7d6..445a7012b1179 100644
@@ -468,6 +468,18 @@ struct perf_hpp_list perf_hpp_list = {
 #undef __HPP_SORT_ACC_FN
 #undef __HPP_SORT_RAW_FN
 
+static void fmt_free(struct perf_hpp_fmt *fmt)
+{
+	/*
+	 * At this point fmt should be completely
+	 * unhooked, if not it's a bug.
+	 */
+	BUG_ON(!list_empty(&fmt->list));
+	BUG_ON(!list_empty(&fmt->sort_list));
+
+	if (fmt->free)
+		fmt->free(fmt);
+}
 
 void perf_hpp__init(void)
 {

@@ -531,9 +543,10 @@ void perf_hpp_list__prepend_sort_field(struct perf_hpp_list *list,
 	list_add(&format->sort_list, &list->sorts);
 }
 
-void perf_hpp__column_unregister(struct perf_hpp_fmt *format)
+static void perf_hpp__column_unregister(struct perf_hpp_fmt *format)
 {
 	list_del_init(&format->list);
+	fmt_free(format);
 }
 
 void perf_hpp__cancel_cumulate(void)

@@ -605,19 +618,6 @@ void perf_hpp__append_sort_keys(struct perf_hpp_list *list)
 }
 
 
-static void fmt_free(struct perf_hpp_fmt *fmt)
-{
-	/*
-	 * At this point fmt should be completely
-	 * unhooked, if not it's a bug.
-	 */
-	BUG_ON(!list_empty(&fmt->list));
-	BUG_ON(!list_empty(&fmt->sort_list));
-
-	if (fmt->free)
-		fmt->free(fmt);
-}
-
 void perf_hpp__reset_output_field(struct perf_hpp_list *list)
 {
 	struct perf_hpp_fmt *fmt, *tmp;

index 595f91f46811f..2eb71eeec4858 100644
@@ -339,7 +339,6 @@ enum {
 };
 
 void perf_hpp__init(void);
-void perf_hpp__column_unregister(struct perf_hpp_fmt *format);
 void perf_hpp__cancel_cumulate(void);
 void perf_hpp__setup_output_field(struct perf_hpp_list *list);
 void perf_hpp__reset_output_field(struct perf_hpp_list *list);

2.33.0
---
 drivers/net/vrf.c |    2 ++
 1 file changed, 2 insertions(+)
@@ -208,6 +208,7 @@ static netdev_tx_t vrf_process_v6_outbou
 	/* strip the ethernet header added for pass through VRF device */
 	__skb_pull(skb, skb_network_offset(skb));
 
+	memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
 	ret = vrf_ip6_local_out(net, skb->sk, skb);
 	if (unlikely(net_xmit_eval(ret)))
 		dev->stats.tx_errors++;

@@ -289,6 +290,7 @@ static netdev_tx_t vrf_process_v4_outbou
 					       RT_SCOPE_LINK);
 	}
 
+	memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
 	ret = vrf_ip_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb);
 	if (unlikely(net_xmit_eval(ret)))
 		vrf_dev->stats.tx_errors++;

---
 include/linux/kprobes.h |    2 ++
 kernel/kprobes.c        |    3 +++
 2 files changed, 5 insertions(+)
@@ -193,6 +193,8 @@ struct kretprobe {
 	raw_spinlock_t lock;
 };
 
+#define KRETPROBE_MAX_DATA_SIZE	4096
+
 struct kretprobe_instance {
 	struct hlist_node hlist;
 	struct kretprobe *rp;

@@ -2004,6 +2004,9 @@ int register_kretprobe(struct kretprobe
 		}
 	}
 
+	if (rp->data_size > KRETPROBE_MAX_DATA_SIZE)
+		return -E2BIG;
+
 	rp->kp.pre_handler = pre_handler_kretprobe;
 	rp->kp.post_handler = NULL;
 	rp->kp.fault_handler = NULL;

 BUG: Unable to handle kernel data access on read at 0x80000800805b502c
 Oops: Kernel access of bad area, sig: 11 [#1]
 NIP [c0000000000388a4] .ioread32+0x4/0x20
 LR [80000000000c6034] .sata_fsl_port_stop+0x44/0xe0 [sata_fsl]
 Call Trace:
  .free_irq+0x1c/0x4e0 (unreliable)
  .ata_host_stop+0x74/0xd0 [libata]
  .release_nodes+0x330/0x3f0
  .device_release_driver_internal+0x178/0x2c0
  .driver_detach+0x64/0xd0
  .bus_remove_driver+0x70/0xf0
  .driver_unregister+0x38/0x80
  .platform_driver_unregister+0x14/0x30
  .fsl_sata_driver_exit+0x18/0xa20 [sata_fsl]
  .__se_sys_delete_module+0x1ec/0x2d0
  .system_call_exception+0xfc/0x1f0
  system_call_common+0xf8/0x200
 ==================================================================
    __device_release_driver
      drv->remove(dev) --> platform_drv_remove/platform_remove
        drv->remove(dev) --> sata_fsl_remove
          iounmap(host_priv->hcr_base);			<---- unmap
          kfree(host_priv);                             <---- free
      devres_release_all
        release_nodes
          dr->node.release(dev, dr->data) --> ata_host_stop
            ap->ops->port_stop(ap) --> sata_fsl_port_stop
                ioread32(hcr_base + HCONTROL)           <---- UAF
            host->ops->host_stop(host)
---
 drivers/ata/sata_fsl.c |   12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)
@@ -1406,6 +1406,14 @@ static int sata_fsl_init_controller(stru
 	return 0;
 }
 
+static void sata_fsl_host_stop(struct ata_host *host)
+{
+        struct sata_fsl_host_priv *host_priv = host->private_data;
+
+        iounmap(host_priv->hcr_base);
+        kfree(host_priv);
+}
+
 /*
  * scsi mid-layer and libata interface structures
  */

@@ -1438,6 +1446,8 @@ static struct ata_port_operations sata_f
 	.port_start = sata_fsl_port_start,
 	.port_stop = sata_fsl_port_stop,
 
+	.host_stop      = sata_fsl_host_stop,
+
 	.pmp_attach = sata_fsl_pmp_attach,
 	.pmp_detach = sata_fsl_pmp_detach,
 };

@@ -1570,8 +1580,6 @@ static int sata_fsl_remove(struct platfo
 	ata_host_detach(host);
 
 	irq_dispose_mapping(host_priv->irq);
-	iounmap(host_priv->hcr_base);
-	kfree(host_priv);
 
 	return 0;
 }

 ------------[ cut here ]------------
 remove_proc_entry: removing non-empty directory 'irq/69',
   leaking at least 'fsl-sata[ff0221000.sata]'
 WARNING: CPU: 3 PID: 1048 at fs/proc/generic.c:722
   .remove_proc_entry+0x20c/0x220
 IRQMASK: 0
 NIP [c00000000033826c] .remove_proc_entry+0x20c/0x220
 LR [c000000000338268] .remove_proc_entry+0x208/0x220
 Call Trace:
  .remove_proc_entry+0x208/0x220 (unreliable)
  .unregister_irq_proc+0x104/0x140
  .free_desc+0x44/0xb0
  .irq_free_descs+0x9c/0xf0
  .irq_dispose_mapping+0x64/0xa0
  .sata_fsl_remove+0x58/0xa0 [sata_fsl]
  .platform_drv_remove+0x40/0x90
  .device_release_driver_internal+0x160/0x2c0
  .driver_detach+0x64/0xd0
  .bus_remove_driver+0x70/0xf0
  .driver_unregister+0x38/0x80
  .platform_driver_unregister+0x14/0x30
  .fsl_sata_driver_exit+0x18/0xa20 [sata_fsl]
 ---[ end trace 0ea876d4076908f5 ]---
---
 drivers/ata/sata_fsl.c |    8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)
@@ -1502,9 +1502,9 @@ static int sata_fsl_probe(struct platfor
 	host_priv->ssr_base = ssr_base;
 	host_priv->csr_base = csr_base;
 
-	irq = irq_of_parse_and_map(ofdev->dev.of_node, 0);
-	if (!irq) {
-		dev_err(&ofdev->dev, "invalid irq from platform\n");
+	irq = platform_get_irq(ofdev, 0);
+	if (irq < 0) {
+		retval = irq;
 		goto error_exit_with_cleanup;
 	}
 	host_priv->irq = irq;

@@ -1579,8 +1579,6 @@ static int sata_fsl_remove(struct platfo
 
 	ata_host_detach(host);
 
-	irq_dispose_mapping(host_priv->irq);
-
 	return 0;
 }
 

---
 fs/file.c            |   15 ++++++++++-----
 fs/file_table.c      |    9 +++++++--
 include/linux/file.h |    2 ++
 include/linux/fs.h   |    4 +++-
 4 files changed, 22 insertions(+), 8 deletions(-)
@@ -679,7 +679,7 @@ void do_close_on_exec(struct files_struc
 	spin_unlock(&files->file_lock);
 }
 
-static struct file *__fget(unsigned int fd, fmode_t mask)
+static struct file *__fget(unsigned int fd, fmode_t mask, unsigned int refs)
 {
 	struct files_struct *files = current->files;
 	struct file *file;

@@ -694,7 +694,7 @@ loop:
 		 */
 		if (file->f_mode & mask)
 			file = NULL;
-		else if (!get_file_rcu(file))
+		else if (!get_file_rcu_many(file, refs))
 			goto loop;
 	}
 	rcu_read_unlock();

@@ -702,15 +702,20 @@ loop:
 	return file;
 }
 
+struct file *fget_many(unsigned int fd, unsigned int refs)
+{
+	return __fget(fd, FMODE_PATH, refs);
+}
+
 struct file *fget(unsigned int fd)
 {
-	return __fget(fd, FMODE_PATH);
+	return __fget(fd, FMODE_PATH, 1);
 }
 EXPORT_SYMBOL(fget);
 
 struct file *fget_raw(unsigned int fd)
 {
-	return __fget(fd, 0);
+	return __fget(fd, 0, 1);
 }
 EXPORT_SYMBOL(fget_raw);
 

@@ -741,7 +746,7 @@ static unsigned long __fget_light(unsign
 			return 0;
 		return (unsigned long)file;
 	} else {
-		file = __fget(fd, mask);
+		file = __fget(fd, mask, 1);
 		if (!file)
 			return 0;
 		return FDPUT_FPUT | (unsigned long)file;

@@ -261,9 +261,9 @@ void flush_delayed_fput(void)
 
 static DECLARE_DELAYED_WORK(delayed_fput_work, delayed_fput);
 
-void fput(struct file *file)
+void fput_many(struct file *file, unsigned int refs)
 {
-	if (atomic_long_dec_and_test(&file->f_count)) {
+	if (atomic_long_sub_and_test(refs, &file->f_count)) {
 		struct task_struct *task = current;
 
 		if (likely(!in_interrupt() && !(task->flags & PF_KTHREAD))) {

@@ -282,6 +282,11 @@ void fput(struct file *file)
 	}
 }
 
+void fput(struct file *file)
+{
+	fput_many(file, 1);
+}
+
 /*
  * synchronous analog of fput(); for kernel threads that might be needed
  * in some umount() (and thus can't use flush_delayed_fput() without

@@ -13,6 +13,7 @@
 struct file;
 
 extern void fput(struct file *);
+extern void fput_many(struct file *, unsigned int);
 
 struct file_operations;
 struct vfsmount;

@@ -41,6 +42,7 @@ static inline void fdput(struct fd fd)
 }
 
 extern struct file *fget(unsigned int fd);
+extern struct file *fget_many(unsigned int fd, unsigned int refs);
 extern struct file *fget_raw(unsigned int fd);
 extern unsigned long __fdget(unsigned int fd);
 extern unsigned long __fdget_raw(unsigned int fd);

@@ -908,7 +908,9 @@ static inline struct file *get_file(stru
 	atomic_long_inc(&f->f_count);
 	return f;
 }
-#define get_file_rcu(x) atomic_long_inc_not_zero(&(x)->f_count)
+#define get_file_rcu_many(x, cnt)	\
+	atomic_long_add_unless(&(x)->f_count, (cnt), 0)
+#define get_file_rcu(x) get_file_rcu_many((x), 1)
 #define fput_atomic(x)	atomic_long_add_unless(&(x)->f_count, -1, 1)
 #define file_count(x)	atomic_long_read(&(x)->f_count)
 

---
 fs/file.c |    4 ++++
 1 file changed, 4 insertions(+)
@@ -696,6 +696,10 @@ loop:
 			file = NULL;
 		else if (!get_file_rcu_many(file, refs))
 			goto loop;
+		else if (__fcheck_files(files, fd) != file) {
+			fput_many(file, refs);
+			goto loop;
+		}
 	}
 	rcu_read_unlock();
 

---
 drivers/net/ethernet/natsemi/xtsonic.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
@@ -128,7 +128,7 @@ static const struct net_device_ops xtson
 	.ndo_set_mac_address	= eth_mac_addr,
 };
 
-static int __init sonic_probe1(struct net_device *dev)
+static int sonic_probe1(struct net_device *dev)
 {
 	static unsigned version_printed = 0;
 	unsigned int silicon_revision;

---
 drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c |   10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)
@@ -1078,8 +1078,14 @@ static int qlcnic_83xx_add_rings(struct
 	sds_mbx_size = sizeof(struct qlcnic_sds_mbx);
 	context_id = recv_ctx->context_id;
 	num_sds = adapter->drv_sds_rings - QLCNIC_MAX_SDS_RINGS;
-	ahw->hw_ops->alloc_mbx_args(&cmd, adapter,
-				    QLCNIC_CMD_ADD_RCV_RINGS);
+	err = ahw->hw_ops->alloc_mbx_args(&cmd, adapter,
+					QLCNIC_CMD_ADD_RCV_RINGS);
+	if (err) {
+		dev_err(&adapter->pdev->dev,
+			"Failed to alloc mbx args %d\n", err);
+		return err;
+	}
+
 	cmd.req.arg[1] = 0 | (num_sds << 8) | (context_id << 16);
 
 	/* set up status rings, mbx 2-81 */

---
 net/mpls/af_mpls.c |   68 ++++++++++++++++++++++++++++++++++++++++-------------
 1 file changed, 52 insertions(+), 16 deletions(-)
@@ -1407,22 +1407,52 @@ static void mpls_dev_destroy_rcu(struct
 	kfree(mdev);
 }
 
-static void mpls_ifdown(struct net_device *dev, int event)
+static int mpls_ifdown(struct net_device *dev, int event)
 {
 	struct mpls_route __rcu **platform_label;
 	struct net *net = dev_net(dev);
-	u8 alive, deleted;
 	unsigned index;
 
 	platform_label = rtnl_dereference(net->mpls.platform_label);
 	for (index = 0; index < net->mpls.platform_labels; index++) {
 		struct mpls_route *rt = rtnl_dereference(platform_label[index]);
+		bool nh_del = false;
+		u8 alive = 0;
 
 		if (!rt)
 			continue;
 
-		alive = 0;
-		deleted = 0;
+		if (event == NETDEV_UNREGISTER) {
+			u8 deleted = 0;
+
+			for_nexthops(rt) {
+				struct net_device *nh_dev =
+					rtnl_dereference(nh->nh_dev);
+
+				if (!nh_dev || nh_dev == dev)
+					deleted++;
+				if (nh_dev == dev)
+					nh_del = true;
+			} endfor_nexthops(rt);
+
+			/* if there are no more nexthops, delete the route */
+			if (deleted == rt->rt_nhn) {
+				mpls_route_update(net, index, NULL, NULL);
+				continue;
+			}
+
+			if (nh_del) {
+				size_t size = sizeof(*rt) + rt->rt_nhn *
+					rt->rt_nh_size;
+				struct mpls_route *orig = rt;
+
+				rt = kmalloc(size, GFP_KERNEL);
+				if (!rt)
+					return -ENOMEM;
+				memcpy(rt, orig, size);
+			}
+		}
+
 		change_nexthops(rt) {
 			unsigned int nh_flags = nh->nh_flags;
 

@@ -1446,16 +1476,15 @@ static void mpls_ifdown(struct net_devic
 next:
 			if (!(nh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN)))
 				alive++;
-			if (!rtnl_dereference(nh->nh_dev))
-				deleted++;
 		} endfor_nexthops(rt);
 
 		WRITE_ONCE(rt->rt_nhn_alive, alive);
 
-		/* if there are no more nexthops, delete the route */
-		if (event == NETDEV_UNREGISTER && deleted == rt->rt_nhn)
-			mpls_route_update(net, index, NULL, NULL);
+		if (nh_del)
+			mpls_route_update(net, index, rt, NULL);
 	}
+
+	return 0;
 }
 
 static void mpls_ifup(struct net_device *dev, unsigned int flags)

@@ -1519,8 +1548,12 @@ static int mpls_dev_notify(struct notifi
 		return NOTIFY_OK;
 
 	switch (event) {
+		int err;
+
 	case NETDEV_DOWN:
-		mpls_ifdown(dev, event);
+		err = mpls_ifdown(dev, event);
+		if (err)
+			return notifier_from_errno(err);
 		break;
 	case NETDEV_UP:
 		flags = dev_get_flags(dev);

@@ -1531,13 +1564,18 @@ static int mpls_dev_notify(struct notifi
 		break;
 	case NETDEV_CHANGE:
 		flags = dev_get_flags(dev);
-		if (flags & (IFF_RUNNING | IFF_LOWER_UP))
+		if (flags & (IFF_RUNNING | IFF_LOWER_UP)) {
 			mpls_ifup(dev, RTNH_F_DEAD | RTNH_F_LINKDOWN);
-		else
-			mpls_ifdown(dev, event);
+		} else {
+			err = mpls_ifdown(dev, event);
+			if (err)
+				return notifier_from_errno(err);
+		}
 		break;
 	case NETDEV_UNREGISTER:
-		mpls_ifdown(dev, event);
+		err = mpls_ifdown(dev, event);
+		if (err)
+			return notifier_from_errno(err);
 		mdev = mpls_dev_get(dev);
 		if (mdev) {
 			mpls_dev_sysctl_unregister(dev, mdev);

@@ -1548,8 +1586,6 @@ static int mpls_dev_notify(struct notifi
 	case NETDEV_CHANGENAME:
 		mdev = mpls_dev_get(dev);
 		if (mdev) {
-			int err;
-
 			mpls_dev_sysctl_unregister(dev, mdev);
 			err = mpls_dev_sysctl_register(dev, mdev);
 			if (err)

---
 include/linux/siphash.h |   14 ++++----------
 lib/siphash.c           |   12 ++++++------
 2 files changed, 10 insertions(+), 16 deletions(-)
@@ -27,9 +27,7 @@ static inline bool siphash_key_is_zero(c
 }
 
 u64 __siphash_aligned(const void *data, size_t len, const siphash_key_t *key);
-#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
 u64 __siphash_unaligned(const void *data, size_t len, const siphash_key_t *key);
-#endif
 
 u64 siphash_1u64(const u64 a, const siphash_key_t *key);
 u64 siphash_2u64(const u64 a, const u64 b, const siphash_key_t *key);

@@ -82,10 +80,9 @@ static inline u64 ___siphash_aligned(con
 static inline u64 siphash(const void *data, size_t len,
 			  const siphash_key_t *key)
 {
-#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
-	if (!IS_ALIGNED((unsigned long)data, SIPHASH_ALIGNMENT))
+	if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) ||
+	    !IS_ALIGNED((unsigned long)data, SIPHASH_ALIGNMENT))
 		return __siphash_unaligned(data, len, key);
-#endif
 	return ___siphash_aligned(data, len, key);
 }
 

@@ -96,10 +93,8 @@ typedef struct {
 
 u32 __hsiphash_aligned(const void *data, size_t len,
 		       const hsiphash_key_t *key);
-#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
 u32 __hsiphash_unaligned(const void *data, size_t len,
 			 const hsiphash_key_t *key);
-#endif
 
 u32 hsiphash_1u32(const u32 a, const hsiphash_key_t *key);
 u32 hsiphash_2u32(const u32 a, const u32 b, const hsiphash_key_t *key);

@@ -135,10 +130,9 @@ static inline u32 ___hsiphash_aligned(co
 static inline u32 hsiphash(const void *data, size_t len,
 			   const hsiphash_key_t *key)
 {
-#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
-	if (!IS_ALIGNED((unsigned long)data, HSIPHASH_ALIGNMENT))
+	if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) ||
+	    !IS_ALIGNED((unsigned long)data, HSIPHASH_ALIGNMENT))
 		return __hsiphash_unaligned(data, len, key);
-#endif
 	return ___hsiphash_aligned(data, len, key);
 }
 

@@ -49,6 +49,7 @@
 	SIPROUND; \
 	return (v0 ^ v1) ^ (v2 ^ v3);
 
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
 u64 __siphash_aligned(const void *data, size_t len, const siphash_key_t *key)
 {
 	const u8 *end = data + len - (len % sizeof(u64));

@@ -80,8 +81,8 @@ u64 __siphash_aligned(const void *data,
 	POSTAMBLE
 }
 EXPORT_SYMBOL(__siphash_aligned);
+#endif
 
-#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
 u64 __siphash_unaligned(const void *data, size_t len, const siphash_key_t *key)
 {
 	const u8 *end = data + len - (len % sizeof(u64));

@@ -113,7 +114,6 @@ u64 __siphash_unaligned(const void *data
 	POSTAMBLE
 }
 EXPORT_SYMBOL(__siphash_unaligned);
-#endif
 
 /**
  * siphash_1u64 - compute 64-bit siphash PRF value of a u64

@@ -250,6 +250,7 @@ EXPORT_SYMBOL(siphash_3u32);
 	HSIPROUND; \
 	return (v0 ^ v1) ^ (v2 ^ v3);
 
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
 u32 __hsiphash_aligned(const void *data, size_t len, const hsiphash_key_t *key)
 {
 	const u8 *end = data + len - (len % sizeof(u64));

@@ -280,8 +281,8 @@ u32 __hsiphash_aligned(const void *data,
 	HPOSTAMBLE
 }
 EXPORT_SYMBOL(__hsiphash_aligned);
+#endif
 
-#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
 u32 __hsiphash_unaligned(const void *data, size_t len,
 			 const hsiphash_key_t *key)
 {

@@ -313,7 +314,6 @@ u32 __hsiphash_unaligned(const void *dat
 	HPOSTAMBLE
 }
 EXPORT_SYMBOL(__hsiphash_unaligned);
-#endif
 
 /**
  * hsiphash_1u32 - compute 64-bit hsiphash PRF value of a u32

@@ -418,6 +418,7 @@ EXPORT_SYMBOL(hsiphash_4u32);
 	HSIPROUND; \
 	return v1 ^ v3;
 
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
 u32 __hsiphash_aligned(const void *data, size_t len, const hsiphash_key_t *key)
 {
 	const u8 *end = data + len - (len % sizeof(u32));

@@ -438,8 +439,8 @@ u32 __hsiphash_aligned(const void *data,
 	HPOSTAMBLE
 }
 EXPORT_SYMBOL(__hsiphash_aligned);
+#endif
 
-#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
 u32 __hsiphash_unaligned(const void *data, size_t len,
 			 const hsiphash_key_t *key)
 {

@@ -461,7 +462,6 @@ u32 __hsiphash_unaligned(const void *dat
 	HPOSTAMBLE
 }
 EXPORT_SYMBOL(__hsiphash_unaligned);
-#endif
 
 /**
  * hsiphash_1u32 - compute 32-bit hsiphash PRF value of a u32

---
 drivers/net/ethernet/mellanox/mlx4/en_netdev.c |    9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)
@@ -2283,9 +2283,14 @@ int mlx4_en_try_alloc_resources(struct m
 				bool carry_xdp_prog)
 {
 	struct bpf_prog *xdp_prog;
-	int i, t;
+	int i, t, ret;
 
-	mlx4_en_copy_priv(tmp, priv, prof);
+	ret = mlx4_en_copy_priv(tmp, priv, prof);
+	if (ret) {
+		en_warn(priv, "%s: mlx4_en_copy_priv() failed, return\n",
+			__func__);
+		return ret;
+	}
 
 	if (mlx4_en_alloc_resources(tmp)) {
 		en_warn(priv,

---
 drivers/net/usb/lan78xx.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
@@ -2052,7 +2052,7 @@ static int lan78xx_phy_init(struct lan78
 	if (dev->domain_data.phyirq > 0)
 		phydev->irq = dev->domain_data.phyirq;
 	else
-		phydev->irq = 0;
+		phydev->irq = PHY_POLL;
 	netdev_dbg(dev->net, "phydev->irq = %d\n", phydev->irq);
 
 	/* set to AUTOMDIX */

---
 net/rds/tcp.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
@@ -392,7 +392,7 @@ void rds_tcp_tune(struct socket *sock)
 		sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
 	}
 	if (rtn->rcvbuf_size > 0) {
-		sk->sk_sndbuf = rtn->rcvbuf_size;
+		sk->sk_rcvbuf = rtn->rcvbuf_size;
 		sk->sk_userlocks |= SOCK_RCVBUF_LOCK;
 	}
 	release_sock(sk);

---
 net/smc/smc_close.c |    8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)
@@ -180,6 +180,7 @@ int smc_close_active(struct smc_sock *sm
 	int old_state;
 	long timeout;
 	int rc = 0;
+	int rc1 = 0;
 
 	timeout = current->flags & PF_EXITING ?
 		  0 : sock_flag(sk, SOCK_LINGER) ?

@@ -219,8 +220,11 @@ again:
 			/* actively shutdown clcsock before peer close it,
 			 * prevent peer from entering TIME_WAIT state.
 			 */
-			if (smc->clcsock && smc->clcsock->sk)
-				rc = kernel_sock_shutdown(smc->clcsock, SHUT_RDWR);
+			if (smc->clcsock && smc->clcsock->sk) {
+				rc1 = kernel_sock_shutdown(smc->clcsock,
+							   SHUT_RDWR);
+				rc = rc ? rc : rc1;
+			}
 		} else {
 			/* peer event has changed the state */
 			goto again;

---
 arch/parisc/Makefile |    5 +++++
 1 file changed, 5 insertions(+)
@@ -17,7 +17,12 @@
 # Mike Shaver, Helge Deller and Martin K. Petersen
 #
 
+ifdef CONFIG_PARISC_SELF_EXTRACT
+boot := arch/parisc/boot
+KBUILD_IMAGE := $(boot)/bzImage
+else
 KBUILD_IMAGE := vmlinuz
+endif
 
 KBUILD_DEFCONFIG := default_defconfig
 

---
 arch/parisc/install.sh |    1 +
 1 file changed, 1 insertion(+)
@@ -39,6 +39,7 @@ verify "$3"
 if [ -n "${INSTALLKERNEL}" ]; then
   if [ -x ~/bin/${INSTALLKERNEL} ]; then exec ~/bin/${INSTALLKERNEL} "$@"; fi
   if [ -x /sbin/${INSTALLKERNEL} ]; then exec /sbin/${INSTALLKERNEL} "$@"; fi
+  if [ -x /usr/sbin/${INSTALLKERNEL} ]; then exec /usr/sbin/${INSTALLKERNEL} "$@"; fi
 fi
 
 # Default install

---
 drivers/video/console/vgacon.c |   14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)
@@ -365,11 +365,17 @@ static void vgacon_init(struct vc_data *
 	struct uni_pagedir *p;
 
 	/*
-	 * We cannot be loaded as a module, therefore init is always 1,
-	 * but vgacon_init can be called more than once, and init will
-	 * not be 1.
+	 * We cannot be loaded as a module, therefore init will be 1
+	 * if we are the default console, however if we are a fallback
+	 * console, for example if fbcon has failed registration, then
+	 * init will be 0, so we need to make sure our boot parameters
+	 * have been copied to the console structure for vgacon_resize
+	 * ultimately called by vc_resize.  Any subsequent calls to
+	 * vgacon_init init will have init set to 0 too.
 	 */
 	c->vc_can_do_color = vga_can_do_color;
+	c->vc_scan_lines = vga_scan_lines;
+	c->vc_font.height = c->vc_cell_height = vga_video_font_height;
 
 	/* set dimensions manually if init != 0 since vc_resize() will fail */
 	if (init) {

@@ -378,8 +384,6 @@ static void vgacon_init(struct vc_data *
 	} else
 		vc_resize(c, vga_video_num_columns, vga_video_num_lines);
 
-	c->vc_scan_lines = vga_scan_lines;
-	c->vc_font.height = c->vc_cell_height = vga_video_font_height;
 	c->vc_complement_mask = 0x7700;
 	if (vga_512_chars)
 		c->vc_hi_font_mask = 0x0800;

---
 drivers/usb/host/xhci-ring.c |   21 ++++++++++++++-------
 1 file changed, 14 insertions(+), 7 deletions(-)
@@ -350,7 +350,9 @@ static void xhci_handle_stopped_cmd_ring
 /* Must be called with xhci->lock held, releases and aquires lock back */
 static int xhci_abort_cmd_ring(struct xhci_hcd *xhci, unsigned long flags)
 {
-	u32 temp_32;
+	struct xhci_segment *new_seg	= xhci->cmd_ring->deq_seg;
+	union xhci_trb *new_deq		= xhci->cmd_ring->dequeue;
+	u64 crcr;
 	int ret;
 
 	xhci_dbg(xhci, "Abort command ring\n");

@@ -359,13 +361,18 @@ static int xhci_abort_cmd_ring(struct xh
 
 	/*
 	 * The control bits like command stop, abort are located in lower
-	 * dword of the command ring control register. Limit the write
-	 * to the lower dword to avoid corrupting the command ring pointer
-	 * in case if the command ring is stopped by the time upper dword
-	 * is written.
+	 * dword of the command ring control register.
+	 * Some controllers require all 64 bits to be written to abort the ring.
+	 * Make sure the upper dword is valid, pointing to the next command,
+	 * avoiding corrupting the command ring pointer in case the command ring
+	 * is stopped by the time the upper dword is written.
 	 */
-	temp_32 = readl(&xhci->op_regs->cmd_ring);
-	writel(temp_32 | CMD_RING_ABORT, &xhci->op_regs->cmd_ring);
+	next_trb(xhci, NULL, &new_seg, &new_deq);
+	if (trb_is_link(new_deq))
+		next_trb(xhci, NULL, &new_seg, &new_deq);
+
+	crcr = xhci_trb_virt_to_dma(new_seg, new_deq);
+	xhci_write_64(xhci, crcr | CMD_RING_ABORT, &xhci->op_regs->cmd_ring);
 
 	/* Section 4.6.1.2 of xHCI 1.0 spec says software should also time the
 	 * completion of the Command Abort operation. If CRR is not negated in 5

[ 6169.280751] CC1: 0 -> 0, CC2: 0 -> 5 [state TOGGLING, polarity 0, connected]
[ 6169.280759] state change TOGGLING -> SNK_ATTACH_WAIT [rev2 NONE_AMS]
[ 6169.280771] pending state change SNK_ATTACH_WAIT -> SNK_DEBOUNCED @ 170 ms [rev2 NONE_AMS]
[ 6169.282427] CC1: 0 -> 0, CC2: 5 -> 5 [state SNK_ATTACH_WAIT, polarity 0, connected]
[ 6169.450825] state change SNK_ATTACH_WAIT -> SNK_DEBOUNCED [delayed 170 ms]
[ 6169.450834] pending state change SNK_DEBOUNCED -> PORT_RESET @ 480 ms [rev2 NONE_AMS]
[ 6169.930892] state change SNK_DEBOUNCED -> PORT_RESET [delayed 480 ms]
[ 6169.931296] disable vbus discharge ret:0
[ 6169.931301] Setting usb_comm capable false
[ 6169.932783] Setting voltage/current limit 0 mV 0 mA
[ 6169.932802] polarity 0
[ 6169.933706] Requesting mux state 0, usb-role 0, orientation 0
[ 6169.936689] cc:=0
[ 6169.936812] pending state change PORT_RESET -> PORT_RESET_WAIT_OFF @ 100 ms [rev2 NONE_AMS]
[ 6169.937157] CC1: 0 -> 0, CC2: 5 -> 0 [state PORT_RESET, polarity 0, disconnected]
[ 6170.036880] state change PORT_RESET -> PORT_RESET_WAIT_OFF [delayed 100 ms]
[ 6170.036890] state change PORT_RESET_WAIT_OFF -> SNK_UNATTACHED [rev2 NONE_AMS]
[ 6170.036896] Start toggling
[ 6170.041412] CC1: 0 -> 0, CC2: 0 -> 0 [state TOGGLING, polarity 0, disconnected]
[ 6170.042973] CC1: 0 -> 0, CC2: 0 -> 5 [state TOGGLING, polarity 0, connected]
[ 6170.042976] state change TOGGLING -> SNK_ATTACH_WAIT [rev2 NONE_AMS]
[ 6170.042981] pending state change SNK_ATTACH_WAIT -> SNK_DEBOUNCED @ 170 ms [rev2 NONE_AMS]
[ 6170.213014] state change SNK_ATTACH_WAIT -> SNK_DEBOUNCED [delayed 170 ms]
[ 6170.213019] pending state change SNK_DEBOUNCED -> PORT_RESET @ 480 ms [rev2 NONE_AMS]
[ 6170.693068] state change SNK_DEBOUNCED -> PORT_RESET [delayed 480 ms]
[ 6170.693304] disable vbus discharge ret:0
[ 6170.693308] Setting usb_comm capable false
[ 6170.695193] Setting voltage/current limit 0 mV 0 mA
[ 6170.695210] polarity 0
[ 6170.695990] Requesting mux state 0, usb-role 0, orientation 0
[ 6170.701896] cc:=0
[ 6170.702181] pending state change PORT_RESET -> PORT_RESET_WAIT_OFF @ 100 ms [rev2 NONE_AMS]
[ 6170.703343] CC1: 0 -> 0, CC2: 5 -> 0 [state PORT_RESET, polarity 0, disconnected]
---
 drivers/staging/typec/tcpm.c |    4 ----
 1 file changed, 4 deletions(-)
@@ -2386,11 +2386,7 @@ static void run_state_machine(struct tcp
 				       tcpm_try_src(port) ? SRC_TRY
 							  : SNK_ATTACHED,
 				       0);
-		else
-			/* Wait for VBUS, but not forever */
-			tcpm_set_state(port, PORT_RESET, PD_T_PS_SOURCE_ON);
 		break;
-
 	case SRC_TRY:
 		port->try_src_count++;
 		tcpm_set_cc(port, tcpm_rp_cc(port));

  #ifdef CONFIG_X86_32
  	load_cr3(initial_page_table);
  #else
  	write_cr3(real_mode_header->trampoline_pgd);

  	/* Exiting long mode will fail if CR4.PCIDE is set. */
  	if (boot_cpu_has(X86_FEATURE_PCID))
  		cr4_clear_bits(X86_CR4_PCIDE);
  #endif

  	/* Jump to the identity-mapped low memory code */
  #ifdef CONFIG_X86_32
  	asm volatile("jmpl *%0" : :
  		     "rm" (real_mode_header->machine_real_restart_asm),
  		     "a" (type));
  #else
  	asm volatile("ljmpl *%0" : :
  		     "m" (real_mode_header->machine_real_restart_asm),
  		     "D" (type));
  #endif
---
 arch/x86/realmode/init.c |   12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)
@@ -57,6 +57,7 @@ static void __init setup_real_mode(void)
 #ifdef CONFIG_X86_64
 	u64 *trampoline_pgd;
 	u64 efer;
+	int i;
 #endif
 
 	base = (unsigned char *)real_mode_header;

@@ -114,8 +115,17 @@ static void __init setup_real_mode(void)
 		trampoline_header->flags |= TH_FLAGS_SME_ACTIVE;
 
 	trampoline_pgd = (u64 *) __va(real_mode_header->trampoline_pgd);
+
+	/* Map the real mode stub as virtual == physical */
 	trampoline_pgd[0] = trampoline_pgd_entry.pgd;
-	trampoline_pgd[511] = init_top_pgt[511].pgd;
+
+	/*
+	 * Include the entirety of the kernel mapping into the trampoline
+	 * PGD.  This way, all mappings present in the normal kernel page
+	 * tables are usable while running on trampoline_pgd.
+	 */
+	for (i = pgd_index(__PAGE_OFFSET); i < PTRS_PER_PGD; i++)
+		trampoline_pgd[i] = init_top_pgt[i].pgd;
 #endif
 }
 

---
 drivers/tty/serial/msm_serial.c |    3 +++
 1 file changed, 3 insertions(+)
@@ -611,6 +611,9 @@ static void msm_start_rx_dma(struct msm_
 	u32 val;
 	int ret;
 
+	if (IS_ENABLED(CONFIG_CONSOLE_POLL))
+		return;
+
 	if (!dma->chan)
 		return;
 

---
 drivers/tty/serial/amba-pl011.c |    1 +
 1 file changed, 1 insertion(+)
@@ -2790,6 +2790,7 @@ MODULE_DEVICE_TABLE(of, sbsa_uart_of_mat
 
 static const struct acpi_device_id sbsa_uart_acpi_match[] = {
 	{ "ARMH0011", 0 },
+	{ "ARMHB000", 0 },
 	{},
 };
 MODULE_DEVICE_TABLE(acpi, sbsa_uart_acpi_match);

---
 drivers/tty/serial/serial_core.c |   13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)
@@ -1541,6 +1541,7 @@ static void uart_tty_port_shutdown(struc
 {
 	struct uart_state *state = container_of(port, struct uart_state, port);
 	struct uart_port *uport = uart_port_check(state);
+	char *buf;
 
 	/*
 	 * At this point, we stop accepting input.  To do this, we

@@ -1562,8 +1563,18 @@ static void uart_tty_port_shutdown(struc
 	 */
 	tty_port_set_suspended(port, 0);
 
-	uart_change_pm(state, UART_PM_STATE_OFF);
+	/*
+	 * Free the transmit buffer.
+	 */
+	spin_lock_irq(&uport->lock);
+	buf = state->xmit.buf;
+	state->xmit.buf = NULL;
+	spin_unlock_irq(&uport->lock);
+
+	if (buf)
+		free_page((unsigned long)buf);
 
+	uart_change_pm(state, UART_PM_STATE_OFF);
 }
 
 static void uart_wait_until_sent(struct tty_struct *tty, int timeout)

---
 arch/parisc/kernel/time.c |   24 +++++-------------------
 1 file changed, 5 insertions(+), 19 deletions(-)
@@ -245,27 +245,13 @@ void __init time_init(void)
 static int __init init_cr16_clocksource(void)
 {
 	/*
-	 * The cr16 interval timers are not syncronized across CPUs on
-	 * different sockets, so mark them unstable and lower rating on
-	 * multi-socket SMP systems.
+	 * The cr16 interval timers are not syncronized across CPUs, even if
+	 * they share the same socket.
 	 */
 	if (num_online_cpus() > 1 && !running_on_qemu) {
-		int cpu;
-		unsigned long cpu0_loc;
-		cpu0_loc = per_cpu(cpu_data, 0).cpu_loc;
-
-		for_each_online_cpu(cpu) {
-			if (cpu == 0)
-				continue;
-			if ((cpu0_loc != 0) &&
-			    (cpu0_loc == per_cpu(cpu_data, cpu).cpu_loc))
-				continue;
-
-			clocksource_cr16.name = "cr16_unstable";
-			clocksource_cr16.flags = CLOCK_SOURCE_UNSTABLE;
-			clocksource_cr16.rating = 0;
-			break;
-		}
+		clocksource_cr16.name = "cr16_unstable";
+		clocksource_cr16.flags = CLOCK_SOURCE_UNSTABLE;
+		clocksource_cr16.rating = 0;
 	}
 
 	/* XXX: We may want to mark sched_clock stable here if cr16 clocks are

	https://www.kernel.org/pub/linux/kernel/v4.x/stable-review/patch-4.14.257-rc1.gz
    8 builds:	8 pass, 0 fail
    16 boots:	16 pass, 0 fail
    32 tests:	32 pass, 0 fail
                tegra210-p2371-2180, tegra30-cardhu-a04
	total: 168 pass: 168 fail: 0
Qemu test results:
	total: 423 pass: 423 fail: 0