Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted

Pull networking updates from Jakub Kicinski:
 "Core:

   - Add dedicated kmem_cache for typical/small skb->head, avoid having
     to access struct page at kfree time, and improve memory use.

   - Introduce sysctl to set default RPS configuration for new netdevs.

   - Define Netlink protocol specification format which can be used to
     describe messages used by each family and auto-generate parsers.
     Add tools for generating kernel data structures and uAPI headers.

   - Expose all net/core sysctls inside netns.

   - Remove 4s sleep in netpoll if carrier is instantly detected on
     boot.

   - Add configurable limit of MDB entries per port, and port-vlan.

   - Continue populating drop reasons throughout the stack.

   - Retire a handful of legacy Qdiscs and classifiers.

  Protocols:

   - Support IPv4 big TCP (TSO frames larger than 64kB).

   - Add IP_LOCAL_PORT_RANGE socket option, to control local port range
     on socket by socket basis.

   - Track and report in procfs number of MPTCP sockets used.

   - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path
     manager.

   - IPv6: don't check net.ipv6.route.max_size and rely on garbage
     collection to free memory (similarly to IPv4).

   - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986).

   - ICMP: add per-rate limit counters.

   - Add support for user scanning requests in ieee802154.

   - Remove static WEP support.

   - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate
     reporting.

   - WiFi 7 EHT channel puncturing support (client & AP).

  BPF:

   - Add a rbtree data structure following the "next-gen data structure"
     precedent set by recently added linked list, that is, by using
     kfunc + kptr instead of adding a new BPF map type.

   - Expose XDP hints via kfuncs with initial support for RX hash and
     timestamp metadata.

   - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to
     better support decap on GRE tunnel devices not operating in collect
     metadata.

   - Improve x86 JIT's codegen for PROBE_MEM runtime error checks.

   - Remove the need for trace_printk_lock for bpf_trace_printk and
     bpf_trace_vprintk helpers.

   - Extend libbpf's bpf_tracing.h support for tracing arguments of
     kprobes/uprobes and syscall as a special case.

   - Significantly reduce the search time for module symbols by
     livepatch and BPF.

   - Enable cpumasks to be used as kptrs, which is useful for tracing
     programs tracking which tasks end up running on which CPUs in
     different time intervals.

   - Add support for BPF trampoline on s390x and riscv64.

   - Add capability to export the XDP features supported by the NIC.

   - Add __bpf_kfunc tag for marking kernel functions as kfuncs.

   - Add cgroup.memory=nobpf kernel parameter option to disable BPF
     memory accounting for container environments.

  Netfilter:

   - Remove the CLUSTERIP target. It has been marked as obsolete for
     years, and we still have WARN splats wrt races of the out-of-band
     /proc interface installed by this target.

   - Add 'destroy' commands to nf_tables. They are identical to the
     existing 'delete' commands, but do not return an error if the
     referenced object (set, chain, rule...) did not exist.

  Driver API:

   - Improve cpumask_local_spread() locality to help NICs set the right
     IRQ affinity on AMD platforms.

   - Separate C22 and C45 MDIO bus transactions more clearly.

   - Introduce new DCB table to control DSCP rewrite on egress.

   - Support configuration of Physical Layer Collision Avoidance (PLCA)
     Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of
     shared medium Ethernet.

   - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing
     preemption of low priority frames by high priority frames.

   - Add support for controlling MACSec offload using netlink SET.

   - Rework devlink instance refcounts to allow registration and
     de-registration under the instance lock. Split the code into
     multiple files, drop some of the unnecessarily granular locks and
     factor out common parts of netlink operation handling.

   - Add TX frame aggregation parameters (for USB drivers).

   - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning
     messages with notifications for debug.

   - Allow offloading of UDP NEW connections via act_ct.

   - Add support for per action HW stats in TC.

   - Support hardware miss to TC action (continue processing in SW from
     a specific point in the action chain).

   - Warn if old Wireless Extension user space interface is used with
     modern cfg80211/mac80211 drivers. Do not support Wireless
     Extensions for Wi-Fi 7 devices at all. Everyone should switch to
     using nl80211 interface instead.

   - Improve the CAN bit timing configuration. Use extack to return
     error messages directly to user space, update the SJW handling,
     including the definition of a new default value that will benefit
     CAN-FD controllers, by increasing their oscillator tolerance.

  New hardware / drivers:

   - Ethernet:
      - nVidia BlueField-3 support (control traffic driver)
      - Ethernet support for imx93 SoCs
      - Motorcomm yt8531 gigabit Ethernet PHY
      - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA)
      - Microchip LAN8841 PHY (incl. cable diagnostics and PTP)
      - Amlogic gxl MDIO mux

   - WiFi:
      - RealTek RTL8188EU (rtl8xxxu)
      - Qualcomm Wi-Fi 7 devices (ath12k)

   - CAN:
      - Renesas R-Car V4H

  Drivers:

   - Bluetooth:
      - Set Per Platform Antenna Gain (PPAG) for Intel controllers.

   - Ethernet NICs:
      - Intel (1G, igc):
         - support TSN / Qbv / packet scheduling features of i226 model
      - Intel (100G, ice):
         - use GNSS subsystem instead of TTY
         - multi-buffer XDP support
         - extend support for GPIO pins to E823 devices
      - nVidia/Mellanox:
         - update the shared buffer configuration on PFC commands
         - implement PTP adjphase function for HW offset control
         - TC support for Geneve and GRE with VF tunnel offload
         - more efficient crypto key management method
         - multi-port eswitch support
      - Netronome/Corigine:
         - add DCB IEEE support
         - support IPsec offloading for NFP3800
      - Freescale/NXP (enetc):
         - support XDP_REDIRECT for XDP non-linear buffers
         - improve reconfig, avoid link flap and waiting for idle
         - support MAC Merge layer
      - Other NICs:
         - sfc/ef100: add basic devlink support for ef100
         - ionic: rx_push mode operation (writing descriptors via MMIO)
         - bnxt: use the auxiliary bus abstraction for RDMA
         - r8169: disable ASPM and reset bus in case of tx timeout
         - cpsw: support QSGMII mode for J721e CPSW9G
         - cpts: support pulse-per-second output
         - ngbe: add an mdio bus driver
         - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing
         - r8152: handle devices with FW with NCM support
         - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation
         - virtio-net: support multi buffer XDP
         - virtio/vsock: replace virtio_vsock_pkt with sk_buff
         - tsnep: XDP support

   - Ethernet high-speed switches:
      - nVidia/Mellanox (mlxsw):
         - add support for latency TLV (in FW control messages)
      - Microchip (sparx5):
         - separate explicit and implicit traffic forwarding rules, make
           the implicit rules always active
         - add support for egress DSCP rewrite
         - IS0 VCAP support (Ingress Classification)
         - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS
           etc.)
         - ES2 VCAP support (Egress Access Control)
         - support for Per-Stream Filtering and Policing (802.1Q,
           8.6.5.1)

   - Ethernet embedded switches:
      - Marvell (mv88e6xxx):
         - add MAB (port auth) offload support
         - enable PTP receive for mv88e6390
      - NXP (ocelot):
         - support MAC Merge layer
         - support for the the vsc7512 internal copper phys
      - Microchip:
         - lan9303: convert to PHYLINK
         - lan966x: support TC flower filter statistics
         - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x
         - lan937x: support Credit Based Shaper configuration
         - ksz9477: support Energy Efficient Ethernet
      - other:
         - qca8k: convert to regmap read/write API, use bulk operations
         - rswitch: Improve TX timestamp accuracy

   - Intel WiFi (iwlwifi):
      - EHT (Wi-Fi 7) rate reporting
      - STEP equalizer support: transfer some STEP (connection to radio
        on platforms with integrated wifi) related parameters from the
        BIOS to the firmware.

   - Qualcomm 802.11ax WiFi (ath11k):
      - IPQ5018 support
      - Fine Timing Measurement (FTM) responder role support
      - channel 177 support

   - MediaTek WiFi (mt76):
      - per-PHY LED support
      - mt7996: EHT (Wi-Fi 7) support
      - Wireless Ethernet Dispatch (WED) reset support
      - switch to using page pool allocator

   - RealTek WiFi (rtw89):
      - support new version of Bluetooth co-existance

   - Mobile:
      - rmnet: support TX aggregation"

* tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits)
  page_pool: add a comment explaining the fragment counter usage
  net: ethtool: fix __ethtool_dev_mm_supported() implementation
  ethtool: pse-pd: Fix double word in comments
  xsk: add linux/vmalloc.h to xsk.c
  sefltests: netdevsim: wait for devlink instance after netns removal
  selftest: fib_tests: Always cleanup before exit
  net/mlx5e: Align IPsec ASO result memory to be as required by hardware
  net/mlx5e: TC, Set CT miss to the specific ct action instance
  net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG
  net/mlx5: Refactor tc miss handling to a single function
  net/mlx5: Kconfig: Make tc offload depend on tc skb extension
  net/sched: flower: Support hardware miss to tc action
  net/sched: flower: Move filter handle initialization earlier
  net/sched: cls_api: Support hardware miss to tc action
  net/sched: Rename user cookie and act cookie
  sfc: fix builds without CONFIG_RTC_LIB
  sfc: clean up some inconsistent indentings
  net/mlx4_en: Introduce flexible array to silence overflow warning
  net: lan966x: Fix possible deadlock inside PTP
  net/ulp: Remove redundant ->clone() test in inet_clone_ulp().
  ...

1 files changed, 724 insertions, 0 deletions

diff --git a/drivers/s390/block/dasd_eer.c b/drivers/s390/block/dasd_eer.c
new file mode 100644
index 000000000..a4cc77220
--- /dev/null
+++ b/drivers/s390/block/dasd_eer.c
@@ -0,0 +1,724 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  Character device driver for extended error reporting.
+ *
+ *  Copyright IBM Corp. 2005
+ *  extended error reporting for DASD ECKD devices
+ *  Author(s): Stefan Weinhuber <wein@de.ibm.com>
+ */
+
+#define KMSG_COMPONENT "dasd-eckd"
+
+#include <linux/init.h>
+#include <linux/fs.h>
+#include <linux/kernel.h>
+#include <linux/miscdevice.h>
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/device.h>
+#include <linux/poll.h>
+#include <linux/mutex.h>
+#include <linux/err.h>
+#include <linux/slab.h>
+
+#include <linux/uaccess.h>
+#include <linux/atomic.h>
+#include <asm/ebcdic.h>
+
+#include "dasd_int.h"
+#include "dasd_eckd.h"
+
+#ifdef PRINTK_HEADER
+#undef PRINTK_HEADER
+#endif				/* PRINTK_HEADER */
+#define PRINTK_HEADER "dasd(eer):"
+
+/*
+ * SECTION: the internal buffer
+ */
+
+/*
+ * The internal buffer is meant to store obaque blobs of data, so it does
+ * not know of higher level concepts like triggers.
+ * It consists of a number of pages that are used as a ringbuffer. Each data
+ * blob is stored in a simple record that consists of an integer, which
+ * contains the size of the following data, and the data bytes themselfes.
+ *
+ * To allow for multiple independent readers we create one internal buffer
+ * each time the device is opened and destroy the buffer when the file is
+ * closed again. The number of pages used for this buffer is determined by
+ * the module parmeter eer_pages.
+ *
+ * One record can be written to a buffer by using the functions
+ * - dasd_eer_start_record (one time per record to write the size to the
+ *                          buffer and reserve the space for the data)
+ * - dasd_eer_write_buffer (one or more times per record to write the data)
+ * The data can be written in several steps but you will have to compute
+ * the total size up front for the invocation of dasd_eer_start_record.
+ * If the ringbuffer is full, dasd_eer_start_record will remove the required
+ * number of old records.
+ *
+ * A record is typically read in two steps, first read the integer that
+ * specifies the size of the following data, then read the data.
+ * Both can be done by
+ * - dasd_eer_read_buffer
+ *
+ * For all mentioned functions you need to get the bufferlock first and keep
+ * it until a complete record is written or read.
+ *
+ * All information necessary to keep track of an internal buffer is kept in
+ * a struct eerbuffer. The buffer specific to a file pointer is strored in
+ * the private_data field of that file. To be able to write data to all
+ * existing buffers, each buffer is also added to the bufferlist.
+ * If the user does not want to read a complete record in one go, we have to
+ * keep track of the rest of the record. residual stores the number of bytes
+ * that are still to deliver. If the rest of the record is invalidated between
+ * two reads then residual will be set to -1 so that the next read will fail.
+ * All entries in the eerbuffer structure are protected with the bufferlock.
+ * To avoid races between writing to a buffer on the one side and creating
+ * and destroying buffers on the other side, the bufferlock must also be used
+ * to protect the bufferlist.
+ */
+
+static int eer_pages = 5;
+module_param(eer_pages, int, S_IRUGO|S_IWUSR);
+
+struct eerbuffer {
+	struct list_head list;
+	char **buffer;
+	int buffersize;
+	int buffer_page_count;
+	int head;
+        int tail;
+	int residual;
+};
+
+static LIST_HEAD(bufferlist);
+static DEFINE_SPINLOCK(bufferlock);
+static DECLARE_WAIT_QUEUE_HEAD(dasd_eer_read_wait_queue);
+
+/*
+ * How many free bytes are available on the buffer.
+ * Needs to be called with bufferlock held.
+ */
+static int dasd_eer_get_free_bytes(struct eerbuffer *eerb)
+{
+	if (eerb->head < eerb->tail)
+		return eerb->tail - eerb->head - 1;
+	return eerb->buffersize - eerb->head + eerb->tail -1;
+}
+
+/*
+ * How many bytes of buffer space are used.
+ * Needs to be called with bufferlock held.
+ */
+static int dasd_eer_get_filled_bytes(struct eerbuffer *eerb)
+{
+
+	if (eerb->head >= eerb->tail)
+		return eerb->head - eerb->tail;
+	return eerb->buffersize - eerb->tail + eerb->head;
+}
+
+/*
+ * The dasd_eer_write_buffer function just copies count bytes of data
+ * to the buffer. Make sure to call dasd_eer_start_record first, to
+ * make sure that enough free space is available.
+ * Needs to be called with bufferlock held.
+ */
+static void dasd_eer_write_buffer(struct eerbuffer *eerb,
+				  char *data, int count)
+{
+
+	unsigned long headindex,localhead;
+	unsigned long rest, len;
+	char *nextdata;
+
+	nextdata = data;
+	rest = count;
+	while (rest > 0) {
+ 		headindex = eerb->head / PAGE_SIZE;
+ 		localhead = eerb->head % PAGE_SIZE;
+		len = min(rest, PAGE_SIZE - localhead);
+		memcpy(eerb->buffer[headindex]+localhead, nextdata, len);
+		nextdata += len;
+		rest -= len;
+		eerb->head += len;
+		if (eerb->head == eerb->buffersize)
+			eerb->head = 0; /* wrap around */
+		BUG_ON(eerb->head > eerb->buffersize);
+	}
+}
+
+/*
+ * Needs to be called with bufferlock held.
+ */
+static int dasd_eer_read_buffer(struct eerbuffer *eerb, char *data, int count)
+{
+
+	unsigned long tailindex,localtail;
+	unsigned long rest, len, finalcount;
+	char *nextdata;
+
+	finalcount = min(count, dasd_eer_get_filled_bytes(eerb));
+	nextdata = data;
+	rest = finalcount;
+	while (rest > 0) {
+ 		tailindex = eerb->tail / PAGE_SIZE;
+ 		localtail = eerb->tail % PAGE_SIZE;
+		len = min(rest, PAGE_SIZE - localtail);
+		memcpy(nextdata, eerb->buffer[tailindex] + localtail, len);
+		nextdata += len;
+		rest -= len;
+		eerb->tail += len;
+		if (eerb->tail == eerb->buffersize)
+			eerb->tail = 0; /* wrap around */
+		BUG_ON(eerb->tail > eerb->buffersize);
+	}
+	return finalcount;
+}
+
+/*
+ * Whenever you want to write a blob of data to the internal buffer you
+ * have to start by using this function first. It will write the number
+ * of bytes that will be written to the buffer. If necessary it will remove
+ * old records to make room for the new one.
+ * Needs to be called with bufferlock held.
+ */
+static int dasd_eer_start_record(struct eerbuffer *eerb, int count)
+{
+	int tailcount;
+
+	if (count + sizeof(count) > eerb->buffersize)
+		return -ENOMEM;
+	while (dasd_eer_get_free_bytes(eerb) < count + sizeof(count)) {
+		if (eerb->residual > 0) {
+			eerb->tail += eerb->residual;
+			if (eerb->tail >= eerb->buffersize)
+				eerb->tail -= eerb->buffersize;
+			eerb->residual = -1;
+		}
+		dasd_eer_read_buffer(eerb, (char *) &tailcount,
+				     sizeof(tailcount));
+		eerb->tail += tailcount;
+		if (eerb->tail >= eerb->buffersize)
+			eerb->tail -= eerb->buffersize;
+	}
+	dasd_eer_write_buffer(eerb, (char*) &count, sizeof(count));
+
+	return 0;
+};
+
+/*
+ * Release pages that are not used anymore.
+ */
+static void dasd_eer_free_buffer_pages(char **buf, int no_pages)
+{
+	int i;
+
+	for (i = 0; i < no_pages; i++)
+		free_page((unsigned long) buf[i]);
+}
+
+/*
+ * Allocate a new set of memory pages.
+ */
+static int dasd_eer_allocate_buffer_pages(char **buf, int no_pages)
+{
+	int i;
+
+	for (i = 0; i < no_pages; i++) {
+		buf[i] = (char *) get_zeroed_page(GFP_KERNEL);
+		if (!buf[i]) {
+			dasd_eer_free_buffer_pages(buf, i);
+			return -ENOMEM;
+		}
+	}
+	return 0;
+}
+
+/*
+ * SECTION: The extended error reporting functionality
+ */
+
+/*
+ * When a DASD device driver wants to report an error, it calls the
+ * function dasd_eer_write and gives the respective trigger ID as
+ * parameter. Currently there are four kinds of triggers:
+ *
+ * DASD_EER_FATALERROR:  all kinds of unrecoverable I/O problems
+ * DASD_EER_PPRCSUSPEND: PPRC was suspended
+ * DASD_EER_NOPATH:      There is no path to the device left.
+ * DASD_EER_STATECHANGE: The state of the device has changed.
+ *
+ * For the first three triggers all required information can be supplied by
+ * the caller. For these triggers a record is written by the function
+ * dasd_eer_write_standard_trigger.
+ *
+ * The DASD_EER_STATECHANGE trigger is special since a sense subsystem
+ * status ccw need to be executed to gather the necessary sense data first.
+ * The dasd_eer_snss function will queue the SNSS request and the request
+ * callback will then call dasd_eer_write with the DASD_EER_STATCHANGE
+ * trigger.
+ *
+ * To avoid memory allocations at runtime, the necessary memory is allocated
+ * when the extended error reporting is enabled for a device (by
+ * dasd_eer_probe). There is one sense subsystem status request for each
+ * eer enabled DASD device. The presence of the cqr in device->eer_cqr
+ * indicates that eer is enable for the device. The use of the snss request
+ * is protected by the DASD_FLAG_EER_IN_USE bit. When this flag indicates
+ * that the cqr is currently in use, dasd_eer_snss cannot start a second
+ * request but sets the DASD_FLAG_EER_SNSS flag instead. The callback of
+ * the SNSS request will check the bit and call dasd_eer_snss again.
+ */
+
+#define SNSS_DATA_SIZE 44
+
+#define DASD_EER_BUSID_SIZE 10
+struct dasd_eer_header {
+	__u32 total_size;
+	__u32 trigger;
+	__u64 tv_sec;
+	__u64 tv_usec;
+	char busid[DASD_EER_BUSID_SIZE];
+} __attribute__ ((packed));
+
+/*
+ * The following function can be used for those triggers that have
+ * all necessary data available when the function is called.
+ * If the parameter cqr is not NULL, the chain of requests will be searched
+ * for valid sense data, and all valid sense data sets will be added to
+ * the triggers data.
+ */
+static void dasd_eer_write_standard_trigger(struct dasd_device *device,
+					    struct dasd_ccw_req *cqr,
+					    int trigger)
+{
+	struct dasd_ccw_req *temp_cqr;
+	int data_size;
+	struct timespec64 ts;
+	struct dasd_eer_header header;
+	unsigned long flags;
+	struct eerbuffer *eerb;
+	char *sense;
+
+	/* go through cqr chain and count the valid sense data sets */
+	data_size = 0;
+	for (temp_cqr = cqr; temp_cqr; temp_cqr = temp_cqr->refers)
+		if (dasd_get_sense(&temp_cqr->irb))
+			data_size += 32;
+
+	header.total_size = sizeof(header) + data_size + 4; /* "EOR" */
+	header.trigger = trigger;
+	ktime_get_real_ts64(&ts);
+	header.tv_sec = ts.tv_sec;
+	header.tv_usec = ts.tv_nsec / NSEC_PER_USEC;
+	strscpy(header.busid, dev_name(&device->cdev->dev),
+		DASD_EER_BUSID_SIZE);
+
+	spin_lock_irqsave(&bufferlock, flags);
+	list_for_each_entry(eerb, &bufferlist, list) {
+		dasd_eer_start_record(eerb, header.total_size);
+		dasd_eer_write_buffer(eerb, (char *) &header, sizeof(header));
+		for (temp_cqr = cqr; temp_cqr; temp_cqr = temp_cqr->refers) {
+			sense = dasd_get_sense(&temp_cqr->irb);
+			if (sense)
+				dasd_eer_write_buffer(eerb, sense, 32);
+		}
+		dasd_eer_write_buffer(eerb, "EOR", 4);
+	}
+	spin_unlock_irqrestore(&bufferlock, flags);
+	wake_up_interruptible(&dasd_eer_read_wait_queue);
+}
+
+/*
+ * This function writes a DASD_EER_STATECHANGE trigger.
+ */
+static void dasd_eer_write_snss_trigger(struct dasd_device *device,
+					struct dasd_ccw_req *cqr,
+					int trigger)
+{
+	int data_size;
+	int snss_rc;
+	struct timespec64 ts;
+	struct dasd_eer_header header;
+	unsigned long flags;
+	struct eerbuffer *eerb;
+
+	snss_rc = (cqr->status == DASD_CQR_DONE) ? 0 : -EIO;
+	if (snss_rc)
+		data_size = 0;
+	else
+		data_size = SNSS_DATA_SIZE;
+
+	header.total_size = sizeof(header) + data_size + 4; /* "EOR" */
+	header.trigger = DASD_EER_STATECHANGE;
+	ktime_get_real_ts64(&ts);
+	header.tv_sec = ts.tv_sec;
+	header.tv_usec = ts.tv_nsec / NSEC_PER_USEC;
+	strscpy(header.busid, dev_name(&device->cdev->dev),
+		DASD_EER_BUSID_SIZE);
+
+	spin_lock_irqsave(&bufferlock, flags);
+	list_for_each_entry(eerb, &bufferlist, list) {
+		dasd_eer_start_record(eerb, header.total_size);
+		dasd_eer_write_buffer(eerb, (char *) &header , sizeof(header));
+		if (!snss_rc)
+			dasd_eer_write_buffer(eerb, cqr->data, SNSS_DATA_SIZE);
+		dasd_eer_write_buffer(eerb, "EOR", 4);
+	}
+	spin_unlock_irqrestore(&bufferlock, flags);
+	wake_up_interruptible(&dasd_eer_read_wait_queue);
+}
+
+/*
+ * This function is called for all triggers. It calls the appropriate
+ * function that writes the actual trigger records.
+ */
+void dasd_eer_write(struct dasd_device *device, struct dasd_ccw_req *cqr,
+		    unsigned int id)
+{
+	if (!device->eer_cqr)
+		return;
+	switch (id) {
+	case DASD_EER_FATALERROR:
+	case DASD_EER_PPRCSUSPEND:
+		dasd_eer_write_standard_trigger(device, cqr, id);
+		break;
+	case DASD_EER_NOPATH:
+	case DASD_EER_NOSPC:
+		dasd_eer_write_standard_trigger(device, NULL, id);
+		break;
+	case DASD_EER_STATECHANGE:
+		dasd_eer_write_snss_trigger(device, cqr, id);
+		break;
+	default: /* unknown trigger, so we write it without any sense data */
+		dasd_eer_write_standard_trigger(device, NULL, id);
+		break;
+	}
+}
+EXPORT_SYMBOL(dasd_eer_write);
+
+/*
+ * Start a sense subsystem status request.
+ * Needs to be called with the device held.
+ */
+void dasd_eer_snss(struct dasd_device *device)
+{
+	struct dasd_ccw_req *cqr;
+
+	cqr = device->eer_cqr;
+	if (!cqr)	/* Device not eer enabled. */
+		return;
+	if (test_and_set_bit(DASD_FLAG_EER_IN_USE, &device->flags)) {
+		/* Sense subsystem status request in use. */
+		set_bit(DASD_FLAG_EER_SNSS, &device->flags);
+		return;
+	}
+	/* cdev is already locked, can't use dasd_add_request_head */
+	clear_bit(DASD_FLAG_EER_SNSS, &device->flags);
+	cqr->status = DASD_CQR_QUEUED;
+	list_add(&cqr->devlist, &device->ccw_queue);
+	dasd_schedule_device_bh(device);
+}
+
+/*
+ * Callback function for use with sense subsystem status request.
+ */
+static void dasd_eer_snss_cb(struct dasd_ccw_req *cqr, void *data)
+{
+	struct dasd_device *device = cqr->startdev;
+	unsigned long flags;
+
+	dasd_eer_write(device, cqr, DASD_EER_STATECHANGE);
+	spin_lock_irqsave(get_ccwdev_lock(device->cdev), flags);
+	if (device->eer_cqr == cqr) {
+		clear_bit(DASD_FLAG_EER_IN_USE, &device->flags);
+		if (test_bit(DASD_FLAG_EER_SNSS, &device->flags))
+			/* Another SNSS has been requested in the meantime. */
+			dasd_eer_snss(device);
+		cqr = NULL;
+	}
+	spin_unlock_irqrestore(get_ccwdev_lock(device->cdev), flags);
+	if (cqr)
+		/*
+		 * Extended error recovery has been switched off while
+		 * the SNSS request was running. It could even have
+		 * been switched off and on again in which case there
+		 * is a new ccw in device->eer_cqr. Free the "old"
+		 * snss request now.
+		 */
+		dasd_sfree_request(cqr, device);
+}
+
+/*
+ * Enable error reporting on a given device.
+ */
+int dasd_eer_enable(struct dasd_device *device)
+{
+	struct dasd_ccw_req *cqr = NULL;
+	unsigned long flags;
+	struct ccw1 *ccw;
+	int rc = 0;
+
+	spin_lock_irqsave(get_ccwdev_lock(device->cdev), flags);
+	if (device->eer_cqr)
+		goto out;
+	else if (!device->discipline ||
+		 strcmp(device->discipline->name, "ECKD"))
+		rc = -EMEDIUMTYPE;
+	else if (test_bit(DASD_FLAG_OFFLINE, &device->flags))
+		rc = -EBUSY;
+
+	if (rc)
+		goto out;
+
+	cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1 /* SNSS */,
+				   SNSS_DATA_SIZE, device, NULL);
+	if (IS_ERR(cqr)) {
+		rc = -ENOMEM;
+		cqr = NULL;
+		goto out;
+	}
+
+	cqr->startdev = device;
+	cqr->retries = 255;
+	cqr->expires = 10 * HZ;
+	clear_bit(DASD_CQR_FLAGS_USE_ERP, &cqr->flags);
+	set_bit(DASD_CQR_ALLOW_SLOCK, &cqr->flags);
+
+	ccw = cqr->cpaddr;
+	ccw->cmd_code = DASD_ECKD_CCW_SNSS;
+	ccw->count = SNSS_DATA_SIZE;
+	ccw->flags = 0;
+	ccw->cda = (__u32)virt_to_phys(cqr->data);
+
+	cqr->buildclk = get_tod_clock();
+	cqr->status = DASD_CQR_FILLED;
+	cqr->callback = dasd_eer_snss_cb;
+
+	if (!device->eer_cqr) {
+		device->eer_cqr = cqr;
+		cqr = NULL;
+	}
+
+out:
+	spin_unlock_irqrestore(get_ccwdev_lock(device->cdev), flags);
+
+	if (cqr)
+		dasd_sfree_request(cqr, device);
+
+	return rc;
+}
+
+/*
+ * Disable error reporting on a given device.
+ */
+void dasd_eer_disable(struct dasd_device *device)
+{
+	struct dasd_ccw_req *cqr;
+	unsigned long flags;
+	int in_use;
+
+	if (!device->eer_cqr)
+		return;
+	spin_lock_irqsave(get_ccwdev_lock(device->cdev), flags);
+	cqr = device->eer_cqr;
+	device->eer_cqr = NULL;
+	clear_bit(DASD_FLAG_EER_SNSS, &device->flags);
+	in_use = test_and_clear_bit(DASD_FLAG_EER_IN_USE, &device->flags);
+	spin_unlock_irqrestore(get_ccwdev_lock(device->cdev), flags);
+	if (cqr && !in_use)
+		dasd_sfree_request(cqr, device);
+}
+
+/*
+ * SECTION: the device operations
+ */
+
+/*
+ * On the one side we need a lock to access our internal buffer, on the
+ * other side a copy_to_user can sleep. So we need to copy the data we have
+ * to transfer in a readbuffer, which is protected by the readbuffer_mutex.
+ */
+static char readbuffer[PAGE_SIZE];
+static DEFINE_MUTEX(readbuffer_mutex);
+
+static int dasd_eer_open(struct inode *inp, struct file *filp)
+{
+	struct eerbuffer *eerb;
+	unsigned long flags;
+
+	eerb = kzalloc(sizeof(struct eerbuffer), GFP_KERNEL);
+	if (!eerb)
+		return -ENOMEM;
+	eerb->buffer_page_count = eer_pages;
+	if (eerb->buffer_page_count < 1 ||
+	    eerb->buffer_page_count > INT_MAX / PAGE_SIZE) {
+		kfree(eerb);
+		DBF_EVENT(DBF_WARNING, "can't open device since module "
+			"parameter eer_pages is smaller than 1 or"
+			" bigger than %d", (int)(INT_MAX / PAGE_SIZE));
+		return -EINVAL;
+	}
+	eerb->buffersize = eerb->buffer_page_count * PAGE_SIZE;
+	eerb->buffer = kmalloc_array(eerb->buffer_page_count, sizeof(char *),
+				     GFP_KERNEL);
+        if (!eerb->buffer) {
+		kfree(eerb);
+                return -ENOMEM;
+	}
+	if (dasd_eer_allocate_buffer_pages(eerb->buffer,
+					   eerb->buffer_page_count)) {
+		kfree(eerb->buffer);
+		kfree(eerb);
+		return -ENOMEM;
+	}
+	filp->private_data = eerb;
+	spin_lock_irqsave(&bufferlock, flags);
+	list_add(&eerb->list, &bufferlist);
+	spin_unlock_irqrestore(&bufferlock, flags);
+
+	return nonseekable_open(inp,filp);
+}
+
+static int dasd_eer_close(struct inode *inp, struct file *filp)
+{
+	struct eerbuffer *eerb;
+	unsigned long flags;
+
+	eerb = (struct eerbuffer *) filp->private_data;
+	spin_lock_irqsave(&bufferlock, flags);
+	list_del(&eerb->list);
+	spin_unlock_irqrestore(&bufferlock, flags);
+	dasd_eer_free_buffer_pages(eerb->buffer, eerb->buffer_page_count);
+	kfree(eerb->buffer);
+	kfree(eerb);
+
+	return 0;
+}
+
+static ssize_t dasd_eer_read(struct file *filp, char __user *buf,
+			     size_t count, loff_t *ppos)
+{
+	int tc,rc;
+	int tailcount,effective_count;
+        unsigned long flags;
+	struct eerbuffer *eerb;
+
+	eerb = (struct eerbuffer *) filp->private_data;
+	if (mutex_lock_interruptible(&readbuffer_mutex))
+		return -ERESTARTSYS;
+
+	spin_lock_irqsave(&bufferlock, flags);
+
+	if (eerb->residual < 0) { /* the remainder of this record */
+		                  /* has been deleted             */
+		eerb->residual = 0;
+		spin_unlock_irqrestore(&bufferlock, flags);
+		mutex_unlock(&readbuffer_mutex);
+		return -EIO;
+	} else if (eerb->residual > 0) {
+		/* OK we still have a second half of a record to deliver */
+		effective_count = min(eerb->residual, (int) count);
+		eerb->residual -= effective_count;
+	} else {
+		tc = 0;
+		while (!tc) {
+			tc = dasd_eer_read_buffer(eerb, (char *) &tailcount,
+						  sizeof(tailcount));
+			if (!tc) {
+				/* no data available */
+				spin_unlock_irqrestore(&bufferlock, flags);
+				mutex_unlock(&readbuffer_mutex);
+				if (filp->f_flags & O_NONBLOCK)
+					return -EAGAIN;
+				rc = wait_event_interruptible(
+					dasd_eer_read_wait_queue,
+					eerb->head != eerb->tail);
+				if (rc)
+					return rc;
+				if (mutex_lock_interruptible(&readbuffer_mutex))
+					return -ERESTARTSYS;
+				spin_lock_irqsave(&bufferlock, flags);
+			}
+		}
+		WARN_ON(tc != sizeof(tailcount));
+		effective_count = min(tailcount,(int)count);
+		eerb->residual = tailcount - effective_count;
+	}
+
+	tc = dasd_eer_read_buffer(eerb, readbuffer, effective_count);
+	WARN_ON(tc != effective_count);
+
+	spin_unlock_irqrestore(&bufferlock, flags);
+
+	if (copy_to_user(buf, readbuffer, effective_count)) {
+		mutex_unlock(&readbuffer_mutex);
+		return -EFAULT;
+	}
+
+	mutex_unlock(&readbuffer_mutex);
+	return effective_count;
+}
+
+static __poll_t dasd_eer_poll(struct file *filp, poll_table *ptable)
+{
+	__poll_t mask;
+	unsigned long flags;
+	struct eerbuffer *eerb;
+
+	eerb = (struct eerbuffer *) filp->private_data;
+	poll_wait(filp, &dasd_eer_read_wait_queue, ptable);
+	spin_lock_irqsave(&bufferlock, flags);
+	if (eerb->head != eerb->tail)
+		mask = EPOLLIN | EPOLLRDNORM ;
+	else
+		mask = 0;
+	spin_unlock_irqrestore(&bufferlock, flags);
+	return mask;
+}
+
+static const struct file_operations dasd_eer_fops = {
+	.open		= &dasd_eer_open,
+	.release	= &dasd_eer_close,
+	.read		= &dasd_eer_read,
+	.poll		= &dasd_eer_poll,
+	.owner		= THIS_MODULE,
+	.llseek		= noop_llseek,
+};
+
+static struct miscdevice *dasd_eer_dev = NULL;
+
+int __init dasd_eer_init(void)
+{
+	int rc;
+
+	dasd_eer_dev = kzalloc(sizeof(*dasd_eer_dev), GFP_KERNEL);
+	if (!dasd_eer_dev)
+		return -ENOMEM;
+
+	dasd_eer_dev->minor = MISC_DYNAMIC_MINOR;
+	dasd_eer_dev->name  = "dasd_eer";
+	dasd_eer_dev->fops  = &dasd_eer_fops;
+
+	rc = misc_register(dasd_eer_dev);
+	if (rc) {
+		kfree(dasd_eer_dev);
+		dasd_eer_dev = NULL;
+		DBF_EVENT(DBF_ERR, "%s", "dasd_eer_init could not "
+		       "register misc device");
+		return rc;
+	}
+
+	return 0;
+}
+
+void dasd_eer_exit(void)
+{
+	if (dasd_eer_dev) {
+		misc_deregister(dasd_eer_dev);
+		kfree(dasd_eer_dev);
+		dasd_eer_dev = NULL;
+	}
+}