GenWQE PCI support, health monitoring and recovery

Module initialization and PCIe setup. Card health monitoring and
recovery functionality. Character device creation and deletion are
controlled from here.

Signed-off-by: Frank Haverkamp <haver@linux.vnet.ibm.com>
Co-authors: Joerg-Stephan Vogt <jsvogt@de.ibm.com>,
            Michael Jung <MIJUNG@de.ibm.com>,
            Michael Ruettger <michael@ibmra.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

4 files changed, 2335 insertions, 0 deletions

diff --git a/drivers/misc/genwqe/card_base.c b/drivers/misc/genwqe/card_base.c
new file mode 100644
index 000000000000..74d51c9bb858
--- /dev/null
+++ b/drivers/misc/genwqe/card_base.c
@@ -0,0 +1,1205 @@
+/**
+ * IBM Accelerator Family 'GenWQE'
+ *
+ * (C) Copyright IBM Corp. 2013
+ *
+ * Author: Frank Haverkamp <haver@linux.vnet.ibm.com>
+ * Author: Joerg-Stephan Vogt <jsvogt@de.ibm.com>
+ * Author: Michael Jung <mijung@de.ibm.com>
+ * Author: Michael Ruettger <michael@ibmra.de>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+/*
+ * Module initialization and PCIe setup. Card health monitoring and
+ * recovery functionality. Character device creation and deletion are
+ * controlled from here.
+ */
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/pci.h>
+#include <linux/err.h>
+#include <linux/aer.h>
+#include <linux/string.h>
+#include <linux/sched.h>
+#include <linux/wait.h>
+#include <linux/delay.h>
+#include <linux/dma-mapping.h>
+#include <linux/module.h>
+#include <linux/notifier.h>
+#include <linux/device.h>
+#include <linux/log2.h>
+#include <linux/genwqe/genwqe_card.h>
+
+#include "card_base.h"
+#include "card_ddcb.h"
+
+MODULE_AUTHOR("Frank Haverkamp <haver@linux.vnet.ibm.com>");
+MODULE_AUTHOR("Michael Ruettger <michael@ibmra.de>");
+MODULE_AUTHOR("Joerg-Stephan Vogt <jsvogt@de.ibm.com>");
+MODULE_AUTHOR("Michal Jung <mijung@de.ibm.com>");
+
+MODULE_DESCRIPTION("GenWQE Card");
+MODULE_VERSION(DRV_VERS_STRING);
+MODULE_LICENSE("GPL");
+
+static char genwqe_driver_name[] = GENWQE_DEVNAME;
+static struct class *class_genwqe;
+static struct dentry *debugfs_genwqe;
+static struct genwqe_dev *genwqe_devices[GENWQE_CARD_NO_MAX];
+
+/* PCI structure for identifying device by PCI vendor and device ID */
+static DEFINE_PCI_DEVICE_TABLE(genwqe_device_table) = {
+	{ .vendor      = PCI_VENDOR_ID_IBM,
+	  .device      = PCI_DEVICE_GENWQE,
+	  .subvendor   = PCI_SUBVENDOR_ID_IBM,
+	  .subdevice   = PCI_SUBSYSTEM_ID_GENWQE5,
+	  .class       = (PCI_CLASSCODE_GENWQE5 << 8),
+	  .class_mask  = ~0,
+	  .driver_data = 0 },
+
+	/* Initial SR-IOV bring-up image */
+	{ .vendor      = PCI_VENDOR_ID_IBM,
+	  .device      = PCI_DEVICE_GENWQE,
+	  .subvendor   = PCI_SUBVENDOR_ID_IBM_SRIOV,
+	  .subdevice   = PCI_SUBSYSTEM_ID_GENWQE5_SRIOV,
+	  .class       = (PCI_CLASSCODE_GENWQE5_SRIOV << 8),
+	  .class_mask  = ~0,
+	  .driver_data = 0 },
+
+	{ .vendor      = PCI_VENDOR_ID_IBM,  /* VF Vendor ID */
+	  .device      = 0x0000,  /* VF Device ID */
+	  .subvendor   = PCI_SUBVENDOR_ID_IBM_SRIOV,
+	  .subdevice   = PCI_SUBSYSTEM_ID_GENWQE5_SRIOV,
+	  .class       = (PCI_CLASSCODE_GENWQE5_SRIOV << 8),
+	  .class_mask  = ~0,
+	  .driver_data = 0 },
+
+	/* Fixed up image */
+	{ .vendor      = PCI_VENDOR_ID_IBM,
+	  .device      = PCI_DEVICE_GENWQE,
+	  .subvendor   = PCI_SUBVENDOR_ID_IBM_SRIOV,
+	  .subdevice   = PCI_SUBSYSTEM_ID_GENWQE5,
+	  .class       = (PCI_CLASSCODE_GENWQE5_SRIOV << 8),
+	  .class_mask  = ~0,
+	  .driver_data = 0 },
+
+	{ .vendor      = PCI_VENDOR_ID_IBM,  /* VF Vendor ID */
+	  .device      = 0x0000,  /* VF Device ID */
+	  .subvendor   = PCI_SUBVENDOR_ID_IBM_SRIOV,
+	  .subdevice   = PCI_SUBSYSTEM_ID_GENWQE5,
+	  .class       = (PCI_CLASSCODE_GENWQE5_SRIOV << 8),
+	  .class_mask  = ~0,
+	  .driver_data = 0 },
+
+	/* Even one more ... */
+	{ .vendor      = PCI_VENDOR_ID_IBM,
+	  .device      = PCI_DEVICE_GENWQE,
+	  .subvendor   = PCI_SUBVENDOR_ID_IBM,
+	  .subdevice   = PCI_SUBSYSTEM_ID_GENWQE5_NEW,
+	  .class       = (PCI_CLASSCODE_GENWQE5 << 8),
+	  .class_mask  = ~0,
+	  .driver_data = 0 },
+
+	{ 0, }			/* 0 terminated list. */
+};
+
+MODULE_DEVICE_TABLE(pci, genwqe_device_table);
+
+/**
+ * genwqe_dev_alloc() - Create and prepare a new card descriptor
+ *
+ * Return: Pointer to card descriptor, or ERR_PTR(err) on error
+ */
+static struct genwqe_dev *genwqe_dev_alloc(void)
+{
+	unsigned int i = 0, j;
+	struct genwqe_dev *cd;
+
+	for (i = 0; i < GENWQE_CARD_NO_MAX; i++) {
+		if (genwqe_devices[i] == NULL)
+			break;
+	}
+	if (i >= GENWQE_CARD_NO_MAX)
+		return ERR_PTR(-ENODEV);
+
+	cd = kzalloc(sizeof(struct genwqe_dev), GFP_KERNEL);
+	if (!cd)
+		return ERR_PTR(-ENOMEM);
+
+	cd->card_idx = i;
+	cd->class_genwqe = class_genwqe;
+	cd->debugfs_genwqe = debugfs_genwqe;
+
+	init_waitqueue_head(&cd->queue_waitq);
+
+	spin_lock_init(&cd->file_lock);
+	INIT_LIST_HEAD(&cd->file_list);
+
+	cd->card_state = GENWQE_CARD_UNUSED;
+	spin_lock_init(&cd->print_lock);
+
+	cd->ddcb_software_timeout = genwqe_ddcb_software_timeout;
+	cd->kill_timeout = genwqe_kill_timeout;
+
+	for (j = 0; j < GENWQE_MAX_VFS; j++)
+		cd->vf_jobtimeout_msec[j] = genwqe_vf_jobtimeout_msec;
+
+	genwqe_devices[i] = cd;
+	return cd;
+}
+
+static void genwqe_dev_free(struct genwqe_dev *cd)
+{
+	if (!cd)
+		return;
+
+	genwqe_devices[cd->card_idx] = NULL;
+	kfree(cd);
+}
+
+/**
+ * genwqe_bus_reset() - Card recovery
+ *
+ * pci_reset_function() will recover the device and ensure that the
+ * registers are accessible again when it completes with success. If
+ * not, the card will stay dead and registers will be unaccessible
+ * still.
+ */
+static int genwqe_bus_reset(struct genwqe_dev *cd)
+{
+	int bars, rc = 0;
+	struct pci_dev *pci_dev = cd->pci_dev;
+	void __iomem *mmio;
+
+	if (cd->err_inject & GENWQE_INJECT_BUS_RESET_FAILURE)
+		return -EIO;
+
+	mmio = cd->mmio;
+	cd->mmio = NULL;
+	pci_iounmap(pci_dev, mmio);
+
+	bars = pci_select_bars(pci_dev, IORESOURCE_MEM);
+	pci_release_selected_regions(pci_dev, bars);
+
+	/*
+	 * Firmware/BIOS might change memory mapping during bus reset.
+	 * Settings like enable bus-mastering, ... are backuped and
+	 * restored by the pci_reset_function().
+	 */
+	dev_dbg(&pci_dev->dev, "[%s] pci_reset function ...\n", __func__);
+	rc = pci_reset_function(pci_dev);
+	if (rc) {
+		dev_err(&pci_dev->dev,
+			"[%s] err: failed reset func (rc %d)\n", __func__, rc);
+		return rc;
+	}
+	dev_dbg(&pci_dev->dev, "[%s] done with rc=%d\n", __func__, rc);
+
+	/*
+	 * Here is the right spot to clear the register read
+	 * failure. pci_bus_reset() does this job in real systems.
+	 */
+	cd->err_inject &= ~(GENWQE_INJECT_HARDWARE_FAILURE |
+			    GENWQE_INJECT_GFIR_FATAL |
+			    GENWQE_INJECT_GFIR_INFO);
+
+	rc = pci_request_selected_regions(pci_dev, bars, genwqe_driver_name);
+	if (rc) {
+		dev_err(&pci_dev->dev,
+			"[%s] err: request bars failed (%d)\n", __func__, rc);
+		return -EIO;
+	}
+
+	cd->mmio = pci_iomap(pci_dev, 0, 0);
+	if (cd->mmio == NULL) {
+		dev_err(&pci_dev->dev,
+			"[%s] err: mapping BAR0 failed\n", __func__);
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+/*
+ * Hardware circumvention section. Certain bitstreams in our test-lab
+ * had different kinds of problems. Here is where we adjust those
+ * bitstreams to function will with this version of our device driver.
+ *
+ * Thise circumventions are applied to the physical function only.
+ * The magical numbers below are identifying development/manufacturing
+ * versions of the bitstream used on the card.
+ *
+ * Turn off error reporting for old/manufacturing images.
+ */
+
+bool genwqe_need_err_masking(struct genwqe_dev *cd)
+{
+	return (cd->slu_unitcfg & 0xFFFF0ull) < 0x32170ull;
+}
+
+static void genwqe_tweak_hardware(struct genwqe_dev *cd)
+{
+	struct pci_dev *pci_dev = cd->pci_dev;
+
+	/* Mask FIRs for development images */
+	if (((cd->slu_unitcfg & 0xFFFF0ull) >= 0x32000ull) &&
+	    ((cd->slu_unitcfg & 0xFFFF0ull) <= 0x33250ull)) {
+		dev_warn(&pci_dev->dev,
+			 "FIRs masked due to bitstream %016llx.%016llx\n",
+			 cd->slu_unitcfg, cd->app_unitcfg);
+
+		__genwqe_writeq(cd, IO_APP_SEC_LEM_DEBUG_OVR,
+				0xFFFFFFFFFFFFFFFFull);
+
+		__genwqe_writeq(cd, IO_APP_ERR_ACT_MASK,
+				0x0000000000000000ull);
+	}
+}
+
+/**
+ * genwqe_recovery_on_fatal_gfir_required() - Version depended actions
+ *
+ * Bitstreams older than 2013-02-17 have a bug where fatal GFIRs must
+ * be ignored. This is e.g. true for the bitstream we gave to the card
+ * manufacturer, but also for some old bitstreams we released to our
+ * test-lab.
+ */
+int genwqe_recovery_on_fatal_gfir_required(struct genwqe_dev *cd)
+{
+	return (cd->slu_unitcfg & 0xFFFF0ull) >= 0x32170ull;
+}
+
+int genwqe_flash_readback_fails(struct genwqe_dev *cd)
+{
+	return (cd->slu_unitcfg & 0xFFFF0ull) < 0x32170ull;
+}
+
+/**
+ * genwqe_T_psec() - Calculate PF/VF timeout register content
+ *
+ * Note: From a design perspective it turned out to be a bad idea to
+ * use codes here to specifiy the frequency/speed values. An old
+ * driver cannot understand new codes and is therefore always a
+ * problem. Better is to measure out the value or put the
+ * speed/frequency directly into a register which is always a valid
+ * value for old as well as for new software.
+ */
+/* T = 1/f */
+static int genwqe_T_psec(struct genwqe_dev *cd)
+{
+	u16 speed;	/* 1/f -> 250,  200,  166,  175 */
+	static const int T[] = { 4000, 5000, 6000, 5714 };
+
+	speed = (u16)((cd->slu_unitcfg >> 28) & 0x0full);
+	if (speed >= ARRAY_SIZE(T))
+		return -1;	/* illegal value */
+
+	return T[speed];
+}
+
+/**
+ * genwqe_setup_pf_jtimer() - Setup PF hardware timeouts for DDCB execution
+ *
+ * Do this _after_ card_reset() is called. Otherwise the values will
+ * vanish. The settings need to be done when the queues are inactive.
+ *
+ * The max. timeout value is 2^(10+x) * T (6ns for 166MHz) * 15/16.
+ * The min. timeout value is 2^(10+x) * T (6ns for 166MHz) * 14/16.
+ */
+static bool genwqe_setup_pf_jtimer(struct genwqe_dev *cd)
+{
+	u32 T = genwqe_T_psec(cd);
+	u64 x;
+
+	if (genwqe_pf_jobtimeout_msec == 0)
+		return false;
+
+	/* PF: large value needed, flash update 2sec per block */
+	x = ilog2(genwqe_pf_jobtimeout_msec *
+		  16000000000uL/(T * 15)) - 10;
+
+	genwqe_write_vreg(cd, IO_SLC_VF_APPJOB_TIMEOUT,
+			  0xff00 | (x & 0xff), 0);
+	return true;
+}
+
+/**
+ * genwqe_setup_vf_jtimer() - Setup VF hardware timeouts for DDCB execution
+ */
+static bool genwqe_setup_vf_jtimer(struct genwqe_dev *cd)
+{
+	struct pci_dev *pci_dev = cd->pci_dev;
+	unsigned int vf;
+	u32 T = genwqe_T_psec(cd);
+	u64 x;
+
+	for (vf = 0; vf < pci_sriov_get_totalvfs(pci_dev); vf++) {
+
+		if (cd->vf_jobtimeout_msec[vf] == 0)
+			continue;
+
+		x = ilog2(cd->vf_jobtimeout_msec[vf] *
+			  16000000000uL/(T * 15)) - 10;
+
+		genwqe_write_vreg(cd, IO_SLC_VF_APPJOB_TIMEOUT,
+				  0xff00 | (x & 0xff), vf + 1);
+	}
+	return true;
+}
+
+static int genwqe_ffdc_buffs_alloc(struct genwqe_dev *cd)
+{
+	unsigned int type, e = 0;
+
+	for (type = 0; type < GENWQE_DBG_UNITS; type++) {
+		switch (type) {
+		case GENWQE_DBG_UNIT0:
+			e = genwqe_ffdc_buff_size(cd, 0);
+			break;
+		case GENWQE_DBG_UNIT1:
+			e = genwqe_ffdc_buff_size(cd, 1);
+			break;
+		case GENWQE_DBG_UNIT2:
+			e = genwqe_ffdc_buff_size(cd, 2);
+			break;
+		case GENWQE_DBG_REGS:
+			e = GENWQE_FFDC_REGS;
+			break;
+		}
+
+		/* currently support only the debug units mentioned here */
+		cd->ffdc[type].entries = e;
+		cd->ffdc[type].regs = kmalloc(e * sizeof(struct genwqe_reg),
+					      GFP_KERNEL);
+		/*
+		 * regs == NULL is ok, the using code treats this as no regs,
+		 * Printing warning is ok in this case.
+		 */
+	}
+	return 0;
+}
+
+static void genwqe_ffdc_buffs_free(struct genwqe_dev *cd)
+{
+	unsigned int type;
+
+	for (type = 0; type < GENWQE_DBG_UNITS; type++) {
+		kfree(cd->ffdc[type].regs);
+		cd->ffdc[type].regs = NULL;
+	}
+}
+
+static int genwqe_read_ids(struct genwqe_dev *cd)
+{
+	int err = 0;
+	int slu_id;
+	struct pci_dev *pci_dev = cd->pci_dev;
+
+	cd->slu_unitcfg = __genwqe_readq(cd, IO_SLU_UNITCFG);
+	if (cd->slu_unitcfg == IO_ILLEGAL_VALUE) {
+		dev_err(&pci_dev->dev,
+			"err: SLUID=%016llx\n", cd->slu_unitcfg);
+		err = -EIO;
+		goto out_err;
+	}
+
+	slu_id = genwqe_get_slu_id(cd);
+	if (slu_id < GENWQE_SLU_ARCH_REQ || slu_id == 0xff) {
+		dev_err(&pci_dev->dev,
+			"err: incompatible SLU Architecture %u\n", slu_id);
+		err = -ENOENT;
+		goto out_err;
+	}
+
+	cd->app_unitcfg = __genwqe_readq(cd, IO_APP_UNITCFG);
+	if (cd->app_unitcfg == IO_ILLEGAL_VALUE) {
+		dev_err(&pci_dev->dev,
+			"err: APPID=%016llx\n", cd->app_unitcfg);
+		err = -EIO;
+		goto out_err;
+	}
+	genwqe_read_app_id(cd, cd->app_name, sizeof(cd->app_name));
+
+	/*
+	 * Is access to all registers possible? If we are a VF the
+	 * answer is obvious. If we run fully virtualized, we need to
+	 * check if we can access all registers. If we do not have
+	 * full access we will cause an UR and some informational FIRs
+	 * in the PF, but that should not harm.
+	 */
+	if (pci_dev->is_virtfn)
+		cd->is_privileged = 0;
+	else
+		cd->is_privileged = (__genwqe_readq(cd, IO_SLU_BITSTREAM)
+				     != IO_ILLEGAL_VALUE);
+
+ out_err:
+	return err;
+}
+
+static int genwqe_start(struct genwqe_dev *cd)
+{
+	int err;
+	struct pci_dev *pci_dev = cd->pci_dev;
+
+	err = genwqe_read_ids(cd);
+	if (err)
+		return err;
+
+	if (genwqe_is_privileged(cd)) {
+		/* do this after the tweaks. alloc fail is acceptable */
+		genwqe_ffdc_buffs_alloc(cd);
+		genwqe_stop_traps(cd);
+
+		/* Collect registers e.g. FIRs, UNITIDs, traces ... */
+		genwqe_read_ffdc_regs(cd, cd->ffdc[GENWQE_DBG_REGS].regs,
+				      cd->ffdc[GENWQE_DBG_REGS].entries, 0);
+
+		genwqe_ffdc_buff_read(cd, GENWQE_DBG_UNIT0,
+				      cd->ffdc[GENWQE_DBG_UNIT0].regs,
+				      cd->ffdc[GENWQE_DBG_UNIT0].entries);
+
+		genwqe_ffdc_buff_read(cd, GENWQE_DBG_UNIT1,
+				      cd->ffdc[GENWQE_DBG_UNIT1].regs,
+				      cd->ffdc[GENWQE_DBG_UNIT1].entries);
+
+		genwqe_ffdc_buff_read(cd, GENWQE_DBG_UNIT2,
+				      cd->ffdc[GENWQE_DBG_UNIT2].regs,
+				      cd->ffdc[GENWQE_DBG_UNIT2].entries);
+
+		genwqe_start_traps(cd);
+
+		if (cd->card_state == GENWQE_CARD_FATAL_ERROR) {
+			dev_warn(&pci_dev->dev,
+				 "[%s] chip reload/recovery!\n", __func__);
+
+			/*
+			 * Stealth Mode: Reload chip on either hot
+			 * reset or PERST.
+			 */
+			cd->softreset = 0x7Cull;
+			__genwqe_writeq(cd, IO_SLC_CFGREG_SOFTRESET,
+				       cd->softreset);
+
+			err = genwqe_bus_reset(cd);
+			if (err != 0) {
+				dev_err(&pci_dev->dev,
+					"[%s] err: bus reset failed!\n",
+					__func__);
+				goto out;
+			}
+
+			/*
+			 * Re-read the IDs because
+			 * it could happen that the bitstream load
+			 * failed!
+			 */
+			err = genwqe_read_ids(cd);
+			if (err)
+				goto out;
+		}
+	}
+
+	err = genwqe_setup_service_layer(cd);  /* does a reset to the card */
+	if (err != 0) {
+		dev_err(&pci_dev->dev,
+			"[%s] err: could not setup servicelayer!\n", __func__);
+		err = -ENODEV;
+		goto out;
+	}
+
+	if (genwqe_is_privileged(cd)) {	 /* code is running _after_ reset */
+		genwqe_tweak_hardware(cd);
+
+		genwqe_setup_pf_jtimer(cd);
+		genwqe_setup_vf_jtimer(cd);
+	}
+
+	err = genwqe_device_create(cd);
+	if (err < 0) {
+		dev_err(&pci_dev->dev,
+			"err: chdev init failed! (err=%d)\n", err);
+		goto out_release_service_layer;
+	}
+	return 0;
+
+ out_release_service_layer:
+	genwqe_release_service_layer(cd);
+ out:
+	if (genwqe_is_privileged(cd))
+		genwqe_ffdc_buffs_free(cd);
+	return -EIO;
+}
+
+/**
+ * genwqe_stop() - Stop card operation
+ *
+ * Recovery notes:
+ *   As long as genwqe_thread runs we might access registers during
+ *   error data capture. Same is with the genwqe_health_thread.
+ *   When genwqe_bus_reset() fails this function might called two times:
+ *   first by the genwqe_health_thread() and later by genwqe_remove() to
+ *   unbind the device. We must be able to survive that.
+ *
+ * This function must be robust enough to be called twice.
+ */
+static int genwqe_stop(struct genwqe_dev *cd)
+{
+	genwqe_finish_queue(cd);	    /* no register access */
+	genwqe_device_remove(cd);	    /* device removed, procs killed */
+	genwqe_release_service_layer(cd);   /* here genwqe_thread is stopped */
+
+	if (genwqe_is_privileged(cd)) {
+		pci_disable_sriov(cd->pci_dev);	/* access pci config space */
+		genwqe_ffdc_buffs_free(cd);
+	}
+
+	return 0;
+}
+
+/**
+ * genwqe_recover_card() - Try to recover the card if it is possible
+ *
+ * If fatal_err is set no register access is possible anymore. It is
+ * likely that genwqe_start fails in that situation. Proper error
+ * handling is required in this case.
+ *
+ * genwqe_bus_reset() will cause the pci code to call genwqe_remove()
+ * and later genwqe_probe() for all virtual functions.
+ */
+static int genwqe_recover_card(struct genwqe_dev *cd, int fatal_err)
+{
+	int rc;
+	struct pci_dev *pci_dev = cd->pci_dev;
+
+	genwqe_stop(cd);
+
+	/*
+	 * Make sure chip is not reloaded to maintain FFDC. Write SLU
+	 * Reset Register, CPLDReset field to 0.
+	 */
+	if (!fatal_err) {
+		cd->softreset = 0x70ull;
+		__genwqe_writeq(cd, IO_SLC_CFGREG_SOFTRESET, cd->softreset);
+	}
+
+	rc = genwqe_bus_reset(cd);
+	if (rc != 0) {
+		dev_err(&pci_dev->dev,
+			"[%s] err: card recovery impossible!\n", __func__);
+		return rc;
+	}
+
+	rc = genwqe_start(cd);
+	if (rc < 0) {
+		dev_err(&pci_dev->dev,
+			"[%s] err: failed to launch device!\n", __func__);
+		return rc;
+	}
+	return 0;
+}
+
+static int genwqe_health_check_cond(struct genwqe_dev *cd, u64 *gfir)
+{
+	*gfir = __genwqe_readq(cd, IO_SLC_CFGREG_GFIR);
+	return (*gfir & GFIR_ERR_TRIGGER) &&
+		genwqe_recovery_on_fatal_gfir_required(cd);
+}
+
+/**
+ * genwqe_fir_checking() - Check the fault isolation registers of the card
+ *
+ * If this code works ok, can be tried out with help of the genwqe_poke tool:
+ *   sudo ./tools/genwqe_poke 0x8 0xfefefefefef
+ *
+ * Now the relevant FIRs/sFIRs should be printed out and the driver should
+ * invoke recovery (devices are removed and readded).
+ */
+static u64 genwqe_fir_checking(struct genwqe_dev *cd)
+{
+	int j, iterations = 0;
+	u64 mask, fir, fec, uid, gfir, gfir_masked, sfir, sfec;
+	u32 fir_addr, fir_clr_addr, fec_addr, sfir_addr, sfec_addr;
+	struct pci_dev *pci_dev = cd->pci_dev;
+
+ healthMonitor:
+	iterations++;
+	if (iterations > 16) {
+		dev_err(&pci_dev->dev, "* exit looping after %d times\n",
+			iterations);
+		goto fatal_error;
+	}
+
+	gfir = __genwqe_readq(cd, IO_SLC_CFGREG_GFIR);
+	if (gfir != 0x0)
+		dev_err(&pci_dev->dev, "* 0x%08x 0x%016llx\n",
+				    IO_SLC_CFGREG_GFIR, gfir);
+	if (gfir == IO_ILLEGAL_VALUE)
+		goto fatal_error;
+
+	/*
+	 * Avoid printing when to GFIR bit is on prevents contignous
+	 * printout e.g. for the following bug:
+	 *   FIR set without a 2ndary FIR/FIR cannot be cleared
+	 * Comment out the following if to get the prints:
+	 */
+	if (gfir == 0)
+		return 0;
+
+	gfir_masked = gfir & GFIR_ERR_TRIGGER;  /* fatal errors */
+
+	for (uid = 0; uid < GENWQE_MAX_UNITS; uid++) { /* 0..2 in zEDC */
+
+		/* read the primary FIR (pfir) */
+		fir_addr = (uid << 24) + 0x08;
+		fir = __genwqe_readq(cd, fir_addr);
+		if (fir == 0x0)
+			continue;  /* no error in this unit */
+
+		dev_err(&pci_dev->dev, "* 0x%08x 0x%016llx\n", fir_addr, fir);
+		if (fir == IO_ILLEGAL_VALUE)
+			goto fatal_error;
+
+		/* read primary FEC */
+		fec_addr = (uid << 24) + 0x18;
+		fec = __genwqe_readq(cd, fec_addr);
+
+		dev_err(&pci_dev->dev, "* 0x%08x 0x%016llx\n", fec_addr, fec);
+		if (fec == IO_ILLEGAL_VALUE)
+			goto fatal_error;
+
+		for (j = 0, mask = 1ULL; j < 64; j++, mask <<= 1) {
+
+			/* secondary fir empty, skip it */
+			if ((fir & mask) == 0x0)
+				continue;
+
+			sfir_addr = (uid << 24) + 0x100 + 0x08 * j;
+			sfir = __genwqe_readq(cd, sfir_addr);
+
+			if (sfir == IO_ILLEGAL_VALUE)
+				goto fatal_error;
+			dev_err(&pci_dev->dev,
+				"* 0x%08x 0x%016llx\n", sfir_addr, sfir);
+
+			sfec_addr = (uid << 24) + 0x300 + 0x08 * j;
+			sfec = __genwqe_readq(cd, sfec_addr);
+
+			if (sfec == IO_ILLEGAL_VALUE)
+				goto fatal_error;
+			dev_err(&pci_dev->dev,
+				"* 0x%08x 0x%016llx\n", sfec_addr, sfec);
+
+			gfir = __genwqe_readq(cd, IO_SLC_CFGREG_GFIR);
+			if (gfir == IO_ILLEGAL_VALUE)
+				goto fatal_error;
+
+			/* gfir turned on during routine! get out and
+			   start over. */
+			if ((gfir_masked == 0x0) &&
+			    (gfir & GFIR_ERR_TRIGGER)) {
+				goto healthMonitor;
+			}
+
+			/* do not clear if we entered with a fatal gfir */
+			if (gfir_masked == 0x0) {
+
+				/* NEW clear by mask the logged bits */
+				sfir_addr = (uid << 24) + 0x100 + 0x08 * j;
+				__genwqe_writeq(cd, sfir_addr, sfir);
+
+				dev_dbg(&pci_dev->dev,
+					"[HM] Clearing  2ndary FIR 0x%08x "
+					"with 0x%016llx\n", sfir_addr, sfir);
+
+				/*
+				 * note, these cannot be error-Firs
+				 * since gfir_masked is 0 after sfir
+				 * was read. Also, it is safe to do
+				 * this write if sfir=0. Still need to
+				 * clear the primary. This just means
+				 * there is no secondary FIR.
+				 */
+
+				/* clear by mask the logged bit. */
+				fir_clr_addr = (uid << 24) + 0x10;
+				__genwqe_writeq(cd, fir_clr_addr, mask);
+
+				dev_dbg(&pci_dev->dev,
+					"[HM] Clearing primary FIR 0x%08x "
+					"with 0x%016llx\n", fir_clr_addr,
+					mask);
+			}
+		}
+	}
+	gfir = __genwqe_readq(cd, IO_SLC_CFGREG_GFIR);
+	if (gfir == IO_ILLEGAL_VALUE)
+		goto fatal_error;
+
+	if ((gfir_masked == 0x0) && (gfir & GFIR_ERR_TRIGGER)) {
+		/*
+		 * Check once more that it didn't go on after all the
+		 * FIRS were cleared.
+		 */
+		dev_dbg(&pci_dev->dev, "ACK! Another FIR! Recursing %d!\n",
+			iterations);
+		goto healthMonitor;
+	}
+	return gfir_masked;
+
+ fatal_error:
+	return IO_ILLEGAL_VALUE;
+}
+
+/**
+ * genwqe_health_thread() - Health checking thread
+ *
+ * This thread is only started for the PF of the card.
+ *
+ * This thread monitors the health of the card. A critical situation
+ * is when we read registers which contain -1 (IO_ILLEGAL_VALUE). In
+ * this case we need to be recovered from outside. Writing to
+ * registers will very likely not work either.
+ *
+ * This thread must only exit if kthread_should_stop() becomes true.
+ *
+ * Condition for the health-thread to trigger:
+ *   a) when a kthread_stop() request comes in or
+ *   b) a critical GFIR occured
+ *
+ * Informational GFIRs are checked and potentially printed in
+ * health_check_interval seconds.
+ */
+static int genwqe_health_thread(void *data)
+{
+	int rc, should_stop = 0;
+	struct genwqe_dev *cd = data;
+	struct pci_dev *pci_dev = cd->pci_dev;
+	u64 gfir, gfir_masked, slu_unitcfg, app_unitcfg;
+
+	while (!kthread_should_stop()) {
+		rc = wait_event_interruptible_timeout(cd->health_waitq,
+			 (genwqe_health_check_cond(cd, &gfir) ||
+			  (should_stop = kthread_should_stop())),
+				genwqe_health_check_interval * HZ);
+
+		if (should_stop)
+			break;
+
+		if (gfir == IO_ILLEGAL_VALUE) {
+			dev_err(&pci_dev->dev,
+				"[%s] GFIR=%016llx\n", __func__, gfir);
+			goto fatal_error;
+		}
+
+		slu_unitcfg = __genwqe_readq(cd, IO_SLU_UNITCFG);
+		if (slu_unitcfg == IO_ILLEGAL_VALUE) {
+			dev_err(&pci_dev->dev,
+				"[%s] SLU_UNITCFG=%016llx\n",
+				__func__, slu_unitcfg);
+			goto fatal_error;
+		}
+
+		app_unitcfg = __genwqe_readq(cd, IO_APP_UNITCFG);
+		if (app_unitcfg == IO_ILLEGAL_VALUE) {
+			dev_err(&pci_dev->dev,
+				"[%s] APP_UNITCFG=%016llx\n",
+				__func__, app_unitcfg);
+			goto fatal_error;
+		}
+
+		gfir = __genwqe_readq(cd, IO_SLC_CFGREG_GFIR);
+		if (gfir == IO_ILLEGAL_VALUE) {
+			dev_err(&pci_dev->dev,
+				"[%s] %s: GFIR=%016llx\n", __func__,
+				(gfir & GFIR_ERR_TRIGGER) ? "err" : "info",
+				gfir);
+			goto fatal_error;
+		}
+
+		gfir_masked = genwqe_fir_checking(cd);
+		if (gfir_masked == IO_ILLEGAL_VALUE)
+			goto fatal_error;
+
+		/*
+		 * GFIR ErrorTrigger bits set => reset the card!
+		 * Never do this for old/manufacturing images!
+		 */
+		if ((gfir_masked) && !cd->skip_recovery &&
+		    genwqe_recovery_on_fatal_gfir_required(cd)) {
+
+			cd->card_state = GENWQE_CARD_FATAL_ERROR;
+
+			rc = genwqe_recover_card(cd, 0);
+			if (rc < 0) {
+				/* FIXME Card is unusable and needs unbind! */
+				goto fatal_error;
+			}
+		}
+
+		cd->last_gfir = gfir;
+		cond_resched();
+	}
+
+	return 0;
+
+ fatal_error:
+	dev_err(&pci_dev->dev,
+		"[%s] card unusable. Please trigger unbind!\n", __func__);
+
+	/* Bring down logical devices to inform user space via udev remove. */
+	cd->card_state = GENWQE_CARD_FATAL_ERROR;
+	genwqe_stop(cd);
+
+	/* genwqe_bus_reset failed(). Now wait for genwqe_remove(). */
+	while (!kthread_should_stop())
+		cond_resched();
+
+	return -EIO;
+}
+
+static int genwqe_health_check_start(struct genwqe_dev *cd)
+{
+	int rc;
+
+	if (genwqe_health_check_interval <= 0)
+		return 0;	/* valid for disabling the service */
+
+	/* moved before request_irq() */
+	/* init_waitqueue_head(&cd->health_waitq); */
+
+	cd->health_thread = kthread_run(genwqe_health_thread, cd,
+					GENWQE_DEVNAME "%d_health",
+					cd->card_idx);
+	if (IS_ERR(cd->health_thread)) {
+		rc = PTR_ERR(cd->health_thread);
+		cd->health_thread = NULL;
+		return rc;
+	}
+	return 0;
+}
+
+static int genwqe_health_thread_running(struct genwqe_dev *cd)
+{
+	return cd->health_thread != NULL;
+}
+
+static int genwqe_health_check_stop(struct genwqe_dev *cd)
+{
+	int rc;
+
+	if (!genwqe_health_thread_running(cd))
+		return -EIO;
+
+	rc = kthread_stop(cd->health_thread);
+	cd->health_thread = NULL;
+	return 0;
+}
+
+/**
+ * genwqe_pci_setup() - Allocate PCIe related resources for our card
+ */
+static int genwqe_pci_setup(struct genwqe_dev *cd)
+{
+	int err, bars;
+	struct pci_dev *pci_dev = cd->pci_dev;
+
+	bars = pci_select_bars(pci_dev, IORESOURCE_MEM);
+	err = pci_enable_device_mem(pci_dev);
+	if (err) {
+		dev_err(&pci_dev->dev,
+			"err: failed to enable pci memory (err=%d)\n", err);
+		goto err_out;
+	}
+
+	/* Reserve PCI I/O and memory resources */
+	err = pci_request_selected_regions(pci_dev, bars, genwqe_driver_name);
+	if (err) {
+		dev_err(&pci_dev->dev,
+			"[%s] err: request bars failed (%d)\n", __func__, err);
+		err = -EIO;
+		goto err_disable_device;
+	}
+
+	/* check for 64-bit DMA address supported (DAC) */
+	if (!pci_set_dma_mask(pci_dev, DMA_BIT_MASK(64))) {
+		err = pci_set_consistent_dma_mask(pci_dev, DMA_BIT_MASK(64));
+		if (err) {
+			dev_err(&pci_dev->dev,
+				"err: DMA64 consistent mask error\n");
+			err = -EIO;
+			goto out_release_resources;
+		}
+	/* check for 32-bit DMA address supported (SAC) */
+	} else if (!pci_set_dma_mask(pci_dev, DMA_BIT_MASK(32))) {
+		err = pci_set_consistent_dma_mask(pci_dev, DMA_BIT_MASK(32));
+		if (err) {
+			dev_err(&pci_dev->dev,
+				"err: DMA32 consistent mask error\n");
+			err = -EIO;
+			goto out_release_resources;
+		}
+	} else {
+		dev_err(&pci_dev->dev,
+			"err: neither DMA32 nor DMA64 supported\n");
+		err = -EIO;
+		goto out_release_resources;
+	}
+
+	pci_set_master(pci_dev);
+	pci_enable_pcie_error_reporting(pci_dev);
+
+	/* request complete BAR-0 space (length = 0) */
+	cd->mmio_len = pci_resource_len(pci_dev, 0);
+	cd->mmio = pci_iomap(pci_dev, 0, 0);
+	if (cd->mmio == NULL) {
+		dev_err(&pci_dev->dev,
+			"[%s] err: mapping BAR0 failed\n", __func__);
+		err = -ENOMEM;
+		goto out_release_resources;
+	}
+
+	cd->num_vfs = pci_sriov_get_totalvfs(pci_dev);
+
+	err = genwqe_read_ids(cd);
+	if (err)
+		goto out_iounmap;
+
+	return 0;
+
+ out_iounmap:
+	pci_iounmap(pci_dev, cd->mmio);
+ out_release_resources:
+	pci_release_selected_regions(pci_dev, bars);
+ err_disable_device:
+	pci_disable_device(pci_dev);
+ err_out:
+	return err;
+}
+
+/**
+ * genwqe_pci_remove() - Free PCIe related resources for our card
+ */
+static void genwqe_pci_remove(struct genwqe_dev *cd)
+{
+	int bars;
+	struct pci_dev *pci_dev = cd->pci_dev;
+
+	if (cd->mmio)
+		pci_iounmap(pci_dev, cd->mmio);
+
+	bars = pci_select_bars(pci_dev, IORESOURCE_MEM);
+	pci_release_selected_regions(pci_dev, bars);
+	pci_disable_device(pci_dev);
+}
+
+/**
+ * genwqe_probe() - Device initialization
+ * @pdev:	PCI device information struct
+ *
+ * Callable for multiple cards. This function is called on bind.
+ *
+ * Return: 0 if succeeded, < 0 when failed
+ */
+static int genwqe_probe(struct pci_dev *pci_dev,
+			const struct pci_device_id *id)
+{
+	int err;
+	struct genwqe_dev *cd;
+
+	genwqe_init_crc32();
+
+	cd = genwqe_dev_alloc();
+	if (IS_ERR(cd)) {
+		dev_err(&pci_dev->dev, "err: could not alloc mem (err=%d)!\n",
+			(int)PTR_ERR(cd));
+		return PTR_ERR(cd);
+	}
+
+	dev_set_drvdata(&pci_dev->dev, cd);
+	cd->pci_dev = pci_dev;
+
+	err = genwqe_pci_setup(cd);
+	if (err < 0) {
+		dev_err(&pci_dev->dev,
+			"err: problems with PCI setup (err=%d)\n", err);
+		goto out_free_dev;
+	}
+
+	err = genwqe_start(cd);
+	if (err < 0) {
+		dev_err(&pci_dev->dev,
+			"err: cannot start card services! (err=%d)\n", err);
+		goto out_pci_remove;
+	}
+
+	if (genwqe_is_privileged(cd)) {
+		err = genwqe_health_check_start(cd);
+		if (err < 0) {
+			dev_err(&pci_dev->dev,
+				"err: cannot start health checking! "
+				"(err=%d)\n", err);
+			goto out_stop_services;
+		}
+	}
+	return 0;
+
+ out_stop_services:
+	genwqe_stop(cd);
+ out_pci_remove:
+	genwqe_pci_remove(cd);
+ out_free_dev:
+	genwqe_dev_free(cd);
+	return err;
+}
+
+/**
+ * genwqe_remove() - Called when device is removed (hot-plugable)
+ *
+ * Or when driver is unloaded respecitively when unbind is done.
+ */
+static void genwqe_remove(struct pci_dev *pci_dev)
+{
+	struct genwqe_dev *cd = dev_get_drvdata(&pci_dev->dev);
+
+	genwqe_health_check_stop(cd);
+
+	/*
+	 * genwqe_stop() must survive if it is called twice
+	 * sequentially. This happens when the health thread calls it
+	 * and fails on genwqe_bus_reset().
+	 */
+	genwqe_stop(cd);
+	genwqe_pci_remove(cd);
+	genwqe_dev_free(cd);
+}
+
+/*
+ * genwqe_err_error_detected() - Error detection callback
+ *
+ * This callback is called by the PCI subsystem whenever a PCI bus
+ * error is detected.
+ */
+static pci_ers_result_t genwqe_err_error_detected(struct pci_dev *pci_dev,
+						 enum pci_channel_state state)
+{
+	struct genwqe_dev *cd;
+
+	dev_err(&pci_dev->dev, "[%s] state=%d\n", __func__, state);
+
+	if (pci_dev == NULL)
+		return PCI_ERS_RESULT_NEED_RESET;
+
+	cd = dev_get_drvdata(&pci_dev->dev);
+	if (cd == NULL)
+		return PCI_ERS_RESULT_NEED_RESET;
+
+	switch (state) {
+	case pci_channel_io_normal:
+		return PCI_ERS_RESULT_CAN_RECOVER;
+	case pci_channel_io_frozen:
+		return PCI_ERS_RESULT_NEED_RESET;
+	case pci_channel_io_perm_failure:
+		return PCI_ERS_RESULT_DISCONNECT;
+	}
+
+	return PCI_ERS_RESULT_NEED_RESET;
+}
+
+static pci_ers_result_t genwqe_err_result_none(struct pci_dev *dev)
+{
+	return PCI_ERS_RESULT_NONE;
+}
+
+static void genwqe_err_resume(struct pci_dev *dev)
+{
+}
+
+static int genwqe_sriov_configure(struct pci_dev *dev, int numvfs)
+{
+	struct genwqe_dev *cd = dev_get_drvdata(&dev->dev);
+
+	if (numvfs > 0) {
+		genwqe_setup_vf_jtimer(cd);
+		pci_enable_sriov(dev, numvfs);
+		return numvfs;
+	}
+	if (numvfs == 0) {
+		pci_disable_sriov(dev);
+		return 0;
+	}
+	return 0;
+}
+
+static struct pci_error_handlers genwqe_err_handler = {
+	.error_detected = genwqe_err_error_detected,
+	.mmio_enabled	= genwqe_err_result_none,
+	.link_reset	= genwqe_err_result_none,
+	.slot_reset	= genwqe_err_result_none,
+	.resume		= genwqe_err_resume,
+};
+
+static struct pci_driver genwqe_driver = {
+	.name	  = genwqe_driver_name,
+	.id_table = genwqe_device_table,
+	.probe	  = genwqe_probe,
+	.remove	  = genwqe_remove,
+	.sriov_configure = genwqe_sriov_configure,
+	.err_handler = &genwqe_err_handler,
+};
+
+/**
+ * genwqe_init_module() - Driver registration and initialization
+ */
+static int __init genwqe_init_module(void)
+{
+	int rc;
+
+	class_genwqe = class_create(THIS_MODULE, GENWQE_DEVNAME);
+	if (IS_ERR(class_genwqe)) {
+		pr_err("[%s] create class failed\n", __func__);
+		return -ENOMEM;
+	}
+
+	debugfs_genwqe = debugfs_create_dir(GENWQE_DEVNAME, NULL);
+	if (!debugfs_genwqe) {
+		rc = -ENOMEM;
+		goto err_out;
+	}
+
+	rc = pci_register_driver(&genwqe_driver);
+	if (rc != 0) {
+		pr_err("[%s] pci_reg_driver (rc=%d)\n", __func__, rc);
+		goto err_out0;
+	}
+
+	return rc;
+
+ err_out0:
+	debugfs_remove(debugfs_genwqe);
+ err_out:
+	class_destroy(class_genwqe);
+	return rc;
+}
+
+/**
+ * genwqe_exit_module() - Driver exit
+ */
+static void __exit genwqe_exit_module(void)
+{
+	pci_unregister_driver(&genwqe_driver);
+	debugfs_remove(debugfs_genwqe);
+	class_destroy(class_genwqe);
+}
+
+module_init(genwqe_init_module);
+module_exit(genwqe_exit_module);
diff --git a/drivers/misc/genwqe/card_base.h b/drivers/misc/genwqe/card_base.h
new file mode 100644
index 000000000000..41953e34d1a3
--- /dev/null
+++ b/drivers/misc/genwqe/card_base.h
@@ -0,0 +1,556 @@
+#ifndef __CARD_BASE_H__
+#define __CARD_BASE_H__
+
+/**
+ * IBM Accelerator Family 'GenWQE'
+ *
+ * (C) Copyright IBM Corp. 2013
+ *
+ * Author: Frank Haverkamp <haver@linux.vnet.ibm.com>
+ * Author: Joerg-Stephan Vogt <jsvogt@de.ibm.com>
+ * Author: Michael Jung <mijung@de.ibm.com>
+ * Author: Michael Ruettger <michael@ibmra.de>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+/*
+ * Interfaces within the GenWQE module. Defines genwqe_card and
+ * ddcb_queue as well as ddcb_requ.
+ */
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/cdev.h>
+#include <linux/stringify.h>
+#include <linux/pci.h>
+#include <linux/semaphore.h>
+#include <linux/uaccess.h>
+#include <linux/io.h>
+#include <linux/version.h>
+#include <linux/debugfs.h>
+
+#include <linux/genwqe/genwqe_card.h>
+#include "genwqe_driver.h"
+
+#define GENWQE_MSI_IRQS			4  /* Just one supported, no MSIx */
+#define GENWQE_FLAG_MSI_ENABLED		(1 << 0)
+
+#define GENWQE_MAX_VFS			15 /* maximum 15 VFs are possible */
+#define GENWQE_MAX_FUNCS		16 /* 1 PF and 15 VFs */
+#define GENWQE_CARD_NO_MAX		(16 * GENWQE_MAX_FUNCS)
+
+/* Compile parameters, some of them appear in debugfs for later adjustment */
+#define genwqe_ddcb_max			32 /* DDCBs on the work-queue */
+#define genwqe_polling_enabled		0  /* in case of irqs not working */
+#define genwqe_ddcb_software_timeout	10 /* timeout per DDCB in seconds */
+#define genwqe_kill_timeout		8  /* time until process gets killed */
+#define genwqe_vf_jobtimeout_msec	250  /* 250 msec */
+#define genwqe_pf_jobtimeout_msec	8000 /* 8 sec should be ok */
+#define genwqe_health_check_interval	4 /* <= 0: disabled */
+
+/* Sysfs attribute groups used when we create the genwqe device */
+extern const struct attribute_group *genwqe_attribute_groups[];
+
+/*
+ * Config space for Genwqe5 A7:
+ * 00:[14 10 4b 04]40 00 10 00[00 00 00 12]00 00 00 00
+ * 10: 0c 00 00 f0 07 3c 00 00 00 00 00 00 00 00 00 00
+ * 20: 00 00 00 00 00 00 00 00 00 00 00 00[14 10 4b 04]
+ * 30: 00 00 00 00 50 00 00 00 00 00 00 00 00 00 00 00
+ */
+#define PCI_DEVICE_GENWQE		0x044b /* Genwqe DeviceID */
+
+#define PCI_SUBSYSTEM_ID_GENWQE5	0x035f /* Genwqe A5 Subsystem-ID */
+#define PCI_SUBSYSTEM_ID_GENWQE5_NEW	0x044b /* Genwqe A5 Subsystem-ID */
+#define PCI_CLASSCODE_GENWQE5		0x1200 /* UNKNOWN */
+
+#define PCI_SUBVENDOR_ID_IBM_SRIOV	0x0000
+#define PCI_SUBSYSTEM_ID_GENWQE5_SRIOV	0x0000 /* Genwqe A5 Subsystem-ID */
+#define PCI_CLASSCODE_GENWQE5_SRIOV	0x1200 /* UNKNOWN */
+
+#define	GENWQE_SLU_ARCH_REQ		2 /* Required SLU architecture level */
+
+/**
+ * struct genwqe_reg - Genwqe data dump functionality
+ */
+struct genwqe_reg {
+	u32 addr;
+	u32 idx;
+	u64 val;
+};
+
+/*
+ * enum genwqe_dbg_type - Specify chip unit to dump/debug
+ */
+enum genwqe_dbg_type {
+	GENWQE_DBG_UNIT0 = 0,  /* captured before prev errs cleared */
+	GENWQE_DBG_UNIT1 = 1,
+	GENWQE_DBG_UNIT2 = 2,
+	GENWQE_DBG_UNIT3 = 3,
+	GENWQE_DBG_UNIT4 = 4,
+	GENWQE_DBG_UNIT5 = 5,
+	GENWQE_DBG_UNIT6 = 6,
+	GENWQE_DBG_UNIT7 = 7,
+	GENWQE_DBG_REGS  = 8,
+	GENWQE_DBG_DMA   = 9,
+	GENWQE_DBG_UNITS = 10, /* max number of possible debug units  */
+};
+
+/* Software error injection to simulate card failures */
+#define GENWQE_INJECT_HARDWARE_FAILURE	0x00000001 /* injects -1 reg reads */
+#define GENWQE_INJECT_BUS_RESET_FAILURE 0x00000002 /* pci_bus_reset fail */
+#define GENWQE_INJECT_GFIR_FATAL	0x00000004 /* GFIR = 0x0000ffff */
+#define GENWQE_INJECT_GFIR_INFO		0x00000008 /* GFIR = 0xffff0000 */
+
+/*
+ * Genwqe card description and management data.
+ *
+ * Error-handling in case of card malfunction
+ * ------------------------------------------
+ *
+ * If the card is detected to be defective the outside environment
+ * will cause the PCI layer to call deinit (the cleanup function for
+ * probe). This is the same effect like doing a unbind/bind operation
+ * on the card.
+ *
+ * The genwqe card driver implements a health checking thread which
+ * verifies the card function. If this detects a problem the cards
+ * device is being shutdown and restarted again, along with a reset of
+ * the card and queue.
+ *
+ * All functions accessing the card device return either -EIO or -ENODEV
+ * code to indicate the malfunction to the user. The user has to close
+ * the file descriptor and open a new one, once the card becomes
+ * available again.
+ *
+ * If the open file descriptor is setup to receive SIGIO, the signal is
+ * genereated for the application which has to provide a handler to
+ * react on it. If the application does not close the open
+ * file descriptor a SIGKILL is send to enforce freeing the cards
+ * resources.
+ *
+ * I did not find a different way to prevent kernel problems due to
+ * reference counters for the cards character devices getting out of
+ * sync. The character device deallocation does not block, even if
+ * there is still an open file descriptor pending. If this pending
+ * descriptor is closed, the data structures used by the character
+ * device is reinstantiated, which will lead to the reference counter
+ * dropping below the allowed values.
+ *
+ * Card recovery
+ * -------------
+ *
+ * To test the internal driver recovery the following command can be used:
+ *   sudo sh -c 'echo 0xfffff > /sys/class/genwqe/genwqe0_card/err_inject'
+ */
+
+
+/**
+ * struct dma_mapping_type - Mapping type definition
+ *
+ * To avoid memcpying data arround we use user memory directly. To do
+ * this we need to pin/swap-in the memory and request a DMA address
+ * for it.
+ */
+enum dma_mapping_type {
+	GENWQE_MAPPING_RAW = 0,		/* contignous memory buffer */
+	GENWQE_MAPPING_SGL_TEMP,	/* sglist dynamically used */
+	GENWQE_MAPPING_SGL_PINNED,	/* sglist used with pinning */
+};
+
+/**
+ * struct dma_mapping - Information about memory mappings done by the driver
+ */
+struct dma_mapping {
+	enum dma_mapping_type type;
+
+	void *u_vaddr;			/* user-space vaddr/non-aligned */
+	void *k_vaddr;			/* kernel-space vaddr/non-aligned */
+	dma_addr_t dma_addr;		/* physical DMA address */
+
+	struct page **page_list;	/* list of pages used by user buff */
+	dma_addr_t *dma_list;		/* list of dma addresses per page */
+	unsigned int nr_pages;		/* number of pages */
+	unsigned int size;		/* size in bytes */
+
+	struct list_head card_list;	/* list of usr_maps for card */
+	struct list_head pin_list;	/* list of pinned memory for dev */
+};
+
+static inline void genwqe_mapping_init(struct dma_mapping *m,
+				       enum dma_mapping_type type)
+{
+	memset(m, 0, sizeof(*m));
+	m->type = type;
+}
+
+/**
+ * struct ddcb_queue - DDCB queue data
+ * @ddcb_max:          Number of DDCBs on the queue
+ * @ddcb_next:         Next free DDCB
+ * @ddcb_act:          Next DDCB supposed to finish
+ * @ddcb_seq:          Sequence number of last DDCB
+ * @ddcbs_in_flight:   Currently enqueued DDCBs
+ * @ddcbs_completed:   Number of already completed DDCBs
+ * @busy:              Number of -EBUSY returns
+ * @ddcb_daddr:        DMA address of first DDCB in the queue
+ * @ddcb_vaddr:        Kernel virtual address of first DDCB in the queue
+ * @ddcb_req:          Associated requests (one per DDCB)
+ * @ddcb_waitqs:       Associated wait queues (one per DDCB)
+ * @ddcb_lock:         Lock to protect queuing operations
+ * @ddcb_waitq:        Wait on next DDCB finishing
+ */
+
+struct ddcb_queue {
+	int ddcb_max;			/* amount of DDCBs  */
+	int ddcb_next;			/* next available DDCB num */
+	int ddcb_act;			/* DDCB to be processed */
+	u16 ddcb_seq;			/* slc seq num */
+	unsigned int ddcbs_in_flight;	/* number of ddcbs in processing */
+	unsigned int ddcbs_completed;
+	unsigned int ddcbs_max_in_flight;
+	unsigned int busy;		/* how many times -EBUSY? */
+
+	dma_addr_t ddcb_daddr;		/* DMA address */
+	struct ddcb *ddcb_vaddr;	/* kernel virtual addr for DDCBs */
+	struct ddcb_requ **ddcb_req;	/* ddcb processing parameter */
+	wait_queue_head_t *ddcb_waitqs; /* waitqueue per ddcb */
+
+	spinlock_t ddcb_lock;		/* exclusive access to queue */
+	wait_queue_head_t ddcb_waitq;	/* wait for ddcb processing */
+
+	/* registers or the respective queue to be used */
+	u32 IO_QUEUE_CONFIG;
+	u32 IO_QUEUE_STATUS;
+	u32 IO_QUEUE_SEGMENT;
+	u32 IO_QUEUE_INITSQN;
+	u32 IO_QUEUE_WRAP;
+	u32 IO_QUEUE_OFFSET;
+	u32 IO_QUEUE_WTIME;
+	u32 IO_QUEUE_ERRCNTS;
+	u32 IO_QUEUE_LRW;
+};
+
+/*
+ * GFIR, SLU_UNITCFG, APP_UNITCFG
+ *   8 Units with FIR/FEC + 64 * 2ndary FIRS/FEC.
+ */
+#define GENWQE_FFDC_REGS	(3 + (8 * (2 + 2 * 64)))
+
+struct genwqe_ffdc {
+	unsigned int entries;
+	struct genwqe_reg *regs;
+};
+
+/**
+ * struct genwqe_dev - GenWQE device information
+ * @card_state:       Card operation state, see above
+ * @ffdc:             First Failure Data Capture buffers for each unit
+ * @card_thread:      Working thread to operate the DDCB queue
+ * @card_waitq:       Wait queue used in card_thread
+ * @queue:            DDCB queue
+ * @health_thread:    Card monitoring thread (only for PFs)
+ * @health_waitq:     Wait queue used in health_thread
+ * @pci_dev:          Associated PCI device (function)
+ * @mmio:             Base address of 64-bit register space
+ * @mmio_len:         Length of register area
+ * @file_lock:        Lock to protect access to file_list
+ * @file_list:        List of all processes with open GenWQE file descriptors
+ *
+ * This struct contains all information needed to communicate with a
+ * GenWQE card. It is initialized when a GenWQE device is found and
+ * destroyed when it goes away. It holds data to maintain the queue as
+ * well as data needed to feed the user interfaces.
+ */
+struct genwqe_dev {
+	enum genwqe_card_state card_state;
+	spinlock_t print_lock;
+
+	int card_idx;			/* card index 0..CARD_NO_MAX-1 */
+	u64 flags;			/* general flags */
+
+	/* FFDC data gathering */
+	struct genwqe_ffdc ffdc[GENWQE_DBG_UNITS];
+
+	/* DDCB workqueue */
+	struct task_struct *card_thread;
+	wait_queue_head_t queue_waitq;
+	struct ddcb_queue queue;	/* genwqe DDCB queue */
+	unsigned int irqs_processed;
+
+	/* Card health checking thread */
+	struct task_struct *health_thread;
+	wait_queue_head_t health_waitq;
+
+	/* char device */
+	dev_t  devnum_genwqe;		/* major/minor num card */
+	struct class *class_genwqe;	/* reference to class object */
+	struct device *dev;		/* for device creation */
+	struct cdev cdev_genwqe;	/* char device for card */
+
+	struct dentry *debugfs_root;	/* debugfs card root directory */
+	struct dentry *debugfs_genwqe;	/* debugfs driver root directory */
+
+	/* pci resources */
+	struct pci_dev *pci_dev;	/* PCI device */
+	void __iomem *mmio;		/* BAR-0 MMIO start */
+	unsigned long mmio_len;
+	u16 num_vfs;
+	u32 vf_jobtimeout_msec[GENWQE_MAX_VFS];
+	int is_privileged;		/* access to all regs possible */
+
+	/* config regs which we need often */
+	u64 slu_unitcfg;
+	u64 app_unitcfg;
+	u64 softreset;
+	u64 err_inject;
+	u64 last_gfir;
+	char app_name[5];
+
+	spinlock_t file_lock;		/* lock for open files */
+	struct list_head file_list;	/* list of open files */
+
+	/* debugfs parameters */
+	int ddcb_software_timeout;	/* wait until DDCB times out */
+	int skip_recovery;		/* circumvention if recovery fails */
+	int kill_timeout;		/* wait after sending SIGKILL */
+};
+
+/**
+ * enum genwqe_requ_state - State of a DDCB execution request
+ */
+enum genwqe_requ_state {
+	GENWQE_REQU_NEW      = 0,
+	GENWQE_REQU_ENQUEUED = 1,
+	GENWQE_REQU_TAPPED   = 2,
+	GENWQE_REQU_FINISHED = 3,
+	GENWQE_REQU_STATE_MAX,
+};
+
+/**
+ * struct ddcb_requ - Kernel internal representation of the DDCB request
+ * @cmd:          User space representation of the DDCB execution request
+ */
+struct ddcb_requ {
+	/* kernel specific content */
+	enum genwqe_requ_state req_state; /* request status */
+	int num;			  /* ddcb_no for this request */
+	struct ddcb_queue *queue;	  /* associated queue */
+
+	struct dma_mapping  dma_mappings[DDCB_FIXUPS];
+	struct sg_entry     *sgl[DDCB_FIXUPS];
+	dma_addr_t	    sgl_dma_addr[DDCB_FIXUPS];
+	size_t		    sgl_size[DDCB_FIXUPS];
+
+	/* kernel/user shared content */
+	struct genwqe_ddcb_cmd cmd;	/* ddcb_no for this request */
+	struct genwqe_debug_data debug_data;
+};
+
+/**
+ * struct genwqe_file - Information for open GenWQE devices
+ */
+struct genwqe_file {
+	struct genwqe_dev *cd;
+	struct genwqe_driver *client;
+	struct file *filp;
+
+	struct fasync_struct *async_queue;
+	struct task_struct *owner;
+	struct list_head list;		/* entry in list of open files */
+
+	spinlock_t map_lock;		/* lock for dma_mappings */
+	struct list_head map_list;	/* list of dma_mappings */
+
+	spinlock_t pin_lock;		/* lock for pinned memory */
+	struct list_head pin_list;	/* list of pinned memory */
+};
+
+int  genwqe_setup_service_layer(struct genwqe_dev *cd); /* for PF only */
+int  genwqe_finish_queue(struct genwqe_dev *cd);
+int  genwqe_release_service_layer(struct genwqe_dev *cd);
+
+/**
+ * genwqe_get_slu_id() - Read Service Layer Unit Id
+ * Return: 0x00: Development code
+ *         0x01: SLC1 (old)
+ *         0x02: SLC2 (sept2012)
+ *         0x03: SLC2 (feb2013, generic driver)
+ */
+static inline int genwqe_get_slu_id(struct genwqe_dev *cd)
+{
+	return (int)((cd->slu_unitcfg >> 32) & 0xff);
+}
+
+int  genwqe_ddcbs_in_flight(struct genwqe_dev *cd);
+
+u8   genwqe_card_type(struct genwqe_dev *cd);
+int  genwqe_card_reset(struct genwqe_dev *cd);
+int  genwqe_set_interrupt_capability(struct genwqe_dev *cd, int count);
+void genwqe_reset_interrupt_capability(struct genwqe_dev *cd);
+
+int  genwqe_device_create(struct genwqe_dev *cd);
+int  genwqe_device_remove(struct genwqe_dev *cd);
+
+/* debugfs */
+int  genwqe_init_debugfs(struct genwqe_dev *cd);
+void genqwe_exit_debugfs(struct genwqe_dev *cd);
+
+int  genwqe_read_softreset(struct genwqe_dev *cd);
+
+/* Hardware Circumventions */
+int  genwqe_recovery_on_fatal_gfir_required(struct genwqe_dev *cd);
+int  genwqe_flash_readback_fails(struct genwqe_dev *cd);
+
+/**
+ * genwqe_write_vreg() - Write register in VF window
+ * @cd:    genwqe device
+ * @reg:   register address
+ * @val:   value to write
+ * @func:  0: PF, 1: VF0, ..., 15: VF14
+ */
+int genwqe_write_vreg(struct genwqe_dev *cd, u32 reg, u64 val, int func);
+
+/**
+ * genwqe_read_vreg() - Read register in VF window
+ * @cd:    genwqe device
+ * @reg:   register address
+ * @func:  0: PF, 1: VF0, ..., 15: VF14
+ *
+ * Return: content of the register
+ */
+u64 genwqe_read_vreg(struct genwqe_dev *cd, u32 reg, int func);
+
+/* FFDC Buffer Management */
+int  genwqe_ffdc_buff_size(struct genwqe_dev *cd, int unit_id);
+int  genwqe_ffdc_buff_read(struct genwqe_dev *cd, int unit_id,
+			   struct genwqe_reg *regs, unsigned int max_regs);
+int  genwqe_read_ffdc_regs(struct genwqe_dev *cd, struct genwqe_reg *regs,
+			   unsigned int max_regs, int all);
+int  genwqe_ffdc_dump_dma(struct genwqe_dev *cd,
+			  struct genwqe_reg *regs, unsigned int max_regs);
+
+int  genwqe_init_debug_data(struct genwqe_dev *cd,
+			    struct genwqe_debug_data *d);
+
+void genwqe_init_crc32(void);
+int  genwqe_read_app_id(struct genwqe_dev *cd, char *app_name, int len);
+
+/* Memory allocation/deallocation; dma address handling */
+int  genwqe_user_vmap(struct genwqe_dev *cd, struct dma_mapping *m,
+		      void *uaddr, unsigned long size,
+		      struct ddcb_requ *req);
+
+int  genwqe_user_vunmap(struct genwqe_dev *cd, struct dma_mapping *m,
+			struct ddcb_requ *req);
+
+struct sg_entry *genwqe_alloc_sgl(struct genwqe_dev *cd, int num_pages,
+				 dma_addr_t *dma_addr, size_t *sgl_size);
+
+void genwqe_free_sgl(struct genwqe_dev *cd, struct sg_entry *sg_list,
+		    dma_addr_t dma_addr, size_t size);
+
+int genwqe_setup_sgl(struct genwqe_dev *cd,
+		    unsigned long offs,
+		    unsigned long size,
+		    struct sg_entry *sgl, /* genwqe sgl */
+		    dma_addr_t dma_addr, size_t sgl_size,
+		    dma_addr_t *dma_list, int page_offs, int num_pages);
+
+int genwqe_check_sgl(struct genwqe_dev *cd, struct sg_entry *sg_list,
+		     int size);
+
+static inline bool dma_mapping_used(struct dma_mapping *m)
+{
+	if (!m)
+		return 0;
+	return m->size != 0;
+}
+
+/**
+ * __genwqe_execute_ddcb() - Execute DDCB request with addr translation
+ *
+ * This function will do the address translation changes to the DDCBs
+ * according to the definitions required by the ATS field. It looks up
+ * the memory allocation buffer or does vmap/vunmap for the respective
+ * user-space buffers, inclusive page pinning and scatter gather list
+ * buildup and teardown.
+ */
+int  __genwqe_execute_ddcb(struct genwqe_dev *cd,
+			   struct genwqe_ddcb_cmd *cmd);
+
+/**
+ * __genwqe_execute_raw_ddcb() - Execute DDCB request without addr translation
+ *
+ * This version will not do address translation or any modifcation of
+ * the DDCB data. It is used e.g. for the MoveFlash DDCB which is
+ * entirely prepared by the driver itself. That means the appropriate
+ * DMA addresses are already in the DDCB and do not need any
+ * modification.
+ */
+int  __genwqe_execute_raw_ddcb(struct genwqe_dev *cd,
+			       struct genwqe_ddcb_cmd *cmd);
+
+int  __genwqe_enqueue_ddcb(struct genwqe_dev *cd, struct ddcb_requ *req);
+int  __genwqe_wait_ddcb(struct genwqe_dev *cd, struct ddcb_requ *req);
+int  __genwqe_purge_ddcb(struct genwqe_dev *cd, struct ddcb_requ *req);
+
+/* register access */
+int __genwqe_writeq(struct genwqe_dev *cd, u64 byte_offs, u64 val);
+u64 __genwqe_readq(struct genwqe_dev *cd, u64 byte_offs);
+int __genwqe_writel(struct genwqe_dev *cd, u64 byte_offs, u32 val);
+u32 __genwqe_readl(struct genwqe_dev *cd, u64 byte_offs);
+
+void *__genwqe_alloc_consistent(struct genwqe_dev *cd, size_t size,
+				 dma_addr_t *dma_handle);
+void __genwqe_free_consistent(struct genwqe_dev *cd, size_t size,
+			      void *vaddr, dma_addr_t dma_handle);
+
+/* Base clock frequency in MHz */
+int  genwqe_base_clock_frequency(struct genwqe_dev *cd);
+
+/* Before FFDC is captured the traps should be stopped. */
+void genwqe_stop_traps(struct genwqe_dev *cd);
+void genwqe_start_traps(struct genwqe_dev *cd);
+
+/* Hardware circumvention */
+bool genwqe_need_err_masking(struct genwqe_dev *cd);
+
+/**
+ * genwqe_is_privileged() - Determine operation mode for PCI function
+ *
+ * On Intel with SRIOV support we see:
+ *   PF: is_physfn = 1 is_virtfn = 0
+ *   VF: is_physfn = 0 is_virtfn = 1
+ *
+ * On Systems with no SRIOV support _and_ virtualized systems we get:
+ *       is_physfn = 0 is_virtfn = 0
+ *
+ * Other vendors have individual pci device ids to distinguish between
+ * virtual function drivers and physical function drivers. GenWQE
+ * unfortunately has just on pci device id for both, VFs and PF.
+ *
+ * The following code is used to distinguish if the card is running in
+ * privileged mode, either as true PF or in a virtualized system with
+ * full register access e.g. currently on PowerPC.
+ *
+ * if (pci_dev->is_virtfn)
+ *          cd->is_privileged = 0;
+ *  else
+ *          cd->is_privileged = (__genwqe_readq(cd, IO_SLU_BITSTREAM)
+ *				 != IO_ILLEGAL_VALUE);
+ */
+static inline int genwqe_is_privileged(struct genwqe_dev *cd)
+{
+	return cd->is_privileged;
+}
+
+#endif	/* __CARD_BASE_H__ */
diff --git a/drivers/misc/genwqe/genwqe_driver.h b/drivers/misc/genwqe/genwqe_driver.h
new file mode 100644
index 000000000000..a1572037c0f9
--- /dev/null
+++ b/drivers/misc/genwqe/genwqe_driver.h
@@ -0,0 +1,74 @@
+#ifndef __GENWQE_DRIVER_H__
+#define __GENWQE_DRIVER_H__
+
+/**
+ * IBM Accelerator Family 'GenWQE'
+ *
+ * (C) Copyright IBM Corp. 2013
+ *
+ * Author: Frank Haverkamp <haver@linux.vnet.ibm.com>
+ * Author: Joerg-Stephan Vogt <jsvogt@de.ibm.com>
+ * Author: Michael Jung <mijung@de.ibm.com>
+ * Author: Michael Ruettger <michael@ibmra.de>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/types.h>
+#include <linux/stddef.h>
+#include <linux/cdev.h>
+#include <linux/list.h>
+#include <linux/kthread.h>
+#include <linux/scatterlist.h>
+#include <linux/iommu.h>
+#include <linux/spinlock.h>
+#include <linux/mutex.h>
+#include <linux/platform_device.h>
+#include <asm/byteorder.h>
+
+#include <linux/genwqe/genwqe_card.h>
+
+#define DRV_VERS_STRING		"2.0.0"
+
+/*
+ * Static minor number assignement, until we decide/implement
+ * something dynamic.
+ */
+#define GENWQE_MAX_MINOR	128 /* up to 128 possible genwqe devices */
+
+/**
+ * genwqe_requ_alloc() - Allocate a new DDCB execution request
+ *
+ * This data structure contains the user visiable fields of the DDCB
+ * to be executed.
+ *
+ * Return: ptr to genwqe_ddcb_cmd data structure
+ */
+struct genwqe_ddcb_cmd *ddcb_requ_alloc(void);
+
+/**
+ * ddcb_requ_free() - Free DDCB execution request.
+ * @req:       ptr to genwqe_ddcb_cmd data structure.
+ */
+void ddcb_requ_free(struct genwqe_ddcb_cmd *req);
+
+u32  genwqe_crc32(u8 *buff, size_t len, u32 init);
+
+static inline void genwqe_hexdump(struct pci_dev *pci_dev,
+				  const void *buff, unsigned int size)
+{
+	char prefix[32];
+
+	scnprintf(prefix, sizeof(prefix), "%s %s: ",
+		  GENWQE_DEVNAME, pci_name(pci_dev));
+	dynamic_hex_dump(prefix, DUMP_PREFIX_OFFSET, 16, 1, buff, size, true);
+}
+
+#endif	/* __GENWQE_DRIVER_H__ */
diff --git a/include/uapi/linux/genwqe/genwqe_card.h b/include/uapi/linux/genwqe/genwqe_card.h
new file mode 100644
index 000000000000..795e957bb840
--- /dev/null
+++ b/include/uapi/linux/genwqe/genwqe_card.h
@@ -0,0 +1,500 @@
+#ifndef __GENWQE_CARD_H__
+#define __GENWQE_CARD_H__
+
+/**
+ * IBM Accelerator Family 'GenWQE'
+ *
+ * (C) Copyright IBM Corp. 2013
+ *
+ * Author: Frank Haverkamp <haver@linux.vnet.ibm.com>
+ * Author: Joerg-Stephan Vogt <jsvogt@de.ibm.com>
+ * Author: Michael Jung <mijung@de.ibm.com>
+ * Author: Michael Ruettger <michael@ibmra.de>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+/*
+ * User-space API for the GenWQE card. For debugging and test purposes
+ * the register addresses are included here too.
+ */
+
+#include <linux/types.h>
+#include <linux/ioctl.h>
+
+/* Basename of sysfs, debugfs and /dev interfaces */
+#define GENWQE_DEVNAME			"genwqe"
+
+#define GENWQE_TYPE_ALTERA_230		0x00 /* GenWQE4 Stratix-IV-230 */
+#define GENWQE_TYPE_ALTERA_530		0x01 /* GenWQE4 Stratix-IV-530 */
+#define GENWQE_TYPE_ALTERA_A4		0x02 /* GenWQE5 A4 Stratix-V-A4 */
+#define GENWQE_TYPE_ALTERA_A7		0x03 /* GenWQE5 A7 Stratix-V-A7 */
+
+/* MMIO Unit offsets: Each UnitID occupies a defined address range */
+#define GENWQE_UID_OFFS(uid)		((uid) << 24)
+#define GENWQE_SLU_OFFS			GENWQE_UID_OFFS(0)
+#define GENWQE_HSU_OFFS			GENWQE_UID_OFFS(1)
+#define GENWQE_APP_OFFS			GENWQE_UID_OFFS(2)
+#define GENWQE_MAX_UNITS		3
+
+/* Common offsets per UnitID */
+#define IO_EXTENDED_ERROR_POINTER	0x00000048
+#define IO_ERROR_INJECT_SELECTOR	0x00000060
+#define IO_EXTENDED_DIAG_SELECTOR	0x00000070
+#define IO_EXTENDED_DIAG_READ_MBX	0x00000078
+#define IO_EXTENDED_DIAG_MAP(ring)	(0x00000500 | ((ring) << 3))
+
+#define GENWQE_EXTENDED_DIAG_SELECTOR(ring, trace) (((ring) << 8) | (trace))
+
+/* UnitID 0: Service Layer Unit (SLU) */
+
+/* SLU: Unit Configuration Register */
+#define IO_SLU_UNITCFG			0x00000000
+#define IO_SLU_UNITCFG_TYPE_MASK	0x000000000ff00000 /* 27:20 */
+
+/* SLU: Fault Isolation Register (FIR) (ac_slu_fir) */
+#define IO_SLU_FIR			0x00000008 /* read only, wr direct */
+#define IO_SLU_FIR_CLR			0x00000010 /* read and clear */
+
+/* SLU: First Error Capture Register (FEC/WOF) */
+#define IO_SLU_FEC			0x00000018
+
+#define IO_SLU_ERR_ACT_MASK		0x00000020
+#define IO_SLU_ERR_ATTN_MASK		0x00000028
+#define IO_SLU_FIRX1_ACT_MASK		0x00000030
+#define IO_SLU_FIRX0_ACT_MASK		0x00000038
+#define IO_SLU_SEC_LEM_DEBUG_OVR	0x00000040
+#define IO_SLU_EXTENDED_ERR_PTR		0x00000048
+#define IO_SLU_COMMON_CONFIG		0x00000060
+
+#define IO_SLU_FLASH_FIR		0x00000108
+#define IO_SLU_SLC_FIR			0x00000110
+#define IO_SLU_RIU_TRAP			0x00000280
+#define IO_SLU_FLASH_FEC		0x00000308
+#define IO_SLU_SLC_FEC			0x00000310
+
+/*
+ * The  Virtual Function's Access is from offset 0x00010000
+ * The Physical Function's Access is from offset 0x00050000
+ * Single Shared Registers exists only at offset 0x00060000
+ *
+ * SLC: Queue Virtual Window Window for accessing into a specific VF
+ * queue. When accessing the 0x10000 space using the 0x50000 address
+ * segment, the value indicated here is used to specify which VF
+ * register is decoded. This register, and the 0x50000 register space
+ * can only be accessed by the PF. Example, if this register is set to
+ * 0x2, then a read from 0x50000 is the same as a read from 0x10000
+ * from VF=2.
+ */
+
+/* SLC: Queue Segment */
+#define IO_SLC_QUEUE_SEGMENT		0x00010000
+#define IO_SLC_VF_QUEUE_SEGMENT		0x00050000
+
+/* SLC: Queue Offset */
+#define IO_SLC_QUEUE_OFFSET		0x00010008
+#define IO_SLC_VF_QUEUE_OFFSET		0x00050008
+
+/* SLC: Queue Configuration */
+#define IO_SLC_QUEUE_CONFIG		0x00010010
+#define IO_SLC_VF_QUEUE_CONFIG		0x00050010
+
+/* SLC: Job Timout/Only accessible for the PF */
+#define IO_SLC_APPJOB_TIMEOUT		0x00010018
+#define IO_SLC_VF_APPJOB_TIMEOUT	0x00050018
+#define TIMEOUT_250MS			0x0000000f
+#define HEARTBEAT_DISABLE		0x0000ff00
+
+/* SLC: Queue InitSequence Register */
+#define	IO_SLC_QUEUE_INITSQN		0x00010020
+#define	IO_SLC_VF_QUEUE_INITSQN		0x00050020
+
+/* SLC: Queue Wrap */
+#define IO_SLC_QUEUE_WRAP		0x00010028
+#define IO_SLC_VF_QUEUE_WRAP		0x00050028
+
+/* SLC: Queue Status */
+#define IO_SLC_QUEUE_STATUS		0x00010100
+#define IO_SLC_VF_QUEUE_STATUS		0x00050100
+
+/* SLC: Queue Working Time */
+#define IO_SLC_QUEUE_WTIME		0x00010030
+#define IO_SLC_VF_QUEUE_WTIME		0x00050030
+
+/* SLC: Queue Error Counts */
+#define IO_SLC_QUEUE_ERRCNTS		0x00010038
+#define IO_SLC_VF_QUEUE_ERRCNTS		0x00050038
+
+/* SLC: Queue Loast Response Word */
+#define IO_SLC_QUEUE_LRW		0x00010040
+#define IO_SLC_VF_QUEUE_LRW		0x00050040
+
+/* SLC: Freerunning Timer */
+#define IO_SLC_FREE_RUNNING_TIMER	0x00010108
+#define IO_SLC_VF_FREE_RUNNING_TIMER	0x00050108
+
+/* SLC: Queue Virtual Access Region */
+#define IO_PF_SLC_VIRTUAL_REGION	0x00050000
+
+/* SLC: Queue Virtual Window */
+#define IO_PF_SLC_VIRTUAL_WINDOW	0x00060000
+
+/* SLC: DDCB Application Job Pending [n] (n=0:63) */
+#define IO_PF_SLC_JOBPEND(n)		(0x00061000 + 8*(n))
+#define IO_SLC_JOBPEND(n)		IO_PF_SLC_JOBPEND(n)
+
+/* SLC: Parser Trap RAM [n] (n=0:31) */
+#define IO_SLU_SLC_PARSE_TRAP(n)	(0x00011000 + 8*(n))
+
+/* SLC: Dispatcher Trap RAM [n] (n=0:31) */
+#define IO_SLU_SLC_DISP_TRAP(n)	(0x00011200 + 8*(n))
+
+/* Global Fault Isolation Register (GFIR) */
+#define IO_SLC_CFGREG_GFIR		0x00020000
+#define GFIR_ERR_TRIGGER		0x0000ffff
+
+/* SLU: Soft Reset Register */
+#define IO_SLC_CFGREG_SOFTRESET		0x00020018
+
+/* SLU: Misc Debug Register */
+#define IO_SLC_MISC_DEBUG		0x00020060
+#define IO_SLC_MISC_DEBUG_CLR		0x00020068
+#define IO_SLC_MISC_DEBUG_SET		0x00020070
+
+/* Temperature Sensor Reading */
+#define IO_SLU_TEMPERATURE_SENSOR	0x00030000
+#define IO_SLU_TEMPERATURE_CONFIG	0x00030008
+
+/* Voltage Margining Control */
+#define IO_SLU_VOLTAGE_CONTROL		0x00030080
+#define IO_SLU_VOLTAGE_NOMINAL		0x00000000
+#define IO_SLU_VOLTAGE_DOWN5		0x00000006
+#define IO_SLU_VOLTAGE_UP5		0x00000007
+
+/* Direct LED Control Register */
+#define IO_SLU_LEDCONTROL		0x00030100
+
+/* SLU: Flashbus Direct Access -A5 */
+#define IO_SLU_FLASH_DIRECTACCESS	0x00040010
+
+/* SLU: Flashbus Direct Access2 -A5 */
+#define IO_SLU_FLASH_DIRECTACCESS2	0x00040020
+
+/* SLU: Flashbus Command Interface -A5 */
+#define IO_SLU_FLASH_CMDINTF		0x00040030
+
+/* SLU: BitStream Loaded */
+#define IO_SLU_BITSTREAM		0x00040040
+
+/* This Register has a switch which will change the CAs to UR */
+#define IO_HSU_ERR_BEHAVIOR		0x01001010
+
+#define IO_SLC2_SQB_TRAP		0x00062000
+#define IO_SLC2_QUEUE_MANAGER_TRAP	0x00062008
+#define IO_SLC2_FLS_MASTER_TRAP		0x00062010
+
+/* UnitID 1: HSU Registers */
+#define IO_HSU_UNITCFG			0x01000000
+#define IO_HSU_FIR			0x01000008
+#define IO_HSU_FIR_CLR			0x01000010
+#define IO_HSU_FEC			0x01000018
+#define IO_HSU_ERR_ACT_MASK		0x01000020
+#define IO_HSU_ERR_ATTN_MASK		0x01000028
+#define IO_HSU_FIRX1_ACT_MASK		0x01000030
+#define IO_HSU_FIRX0_ACT_MASK		0x01000038
+#define IO_HSU_SEC_LEM_DEBUG_OVR	0x01000040
+#define IO_HSU_EXTENDED_ERR_PTR		0x01000048
+#define IO_HSU_COMMON_CONFIG		0x01000060
+
+/* UnitID 2: Application Unit (APP) */
+#define IO_APP_UNITCFG			0x02000000
+#define IO_APP_FIR			0x02000008
+#define IO_APP_FIR_CLR			0x02000010
+#define IO_APP_FEC			0x02000018
+#define IO_APP_ERR_ACT_MASK		0x02000020
+#define IO_APP_ERR_ATTN_MASK		0x02000028
+#define IO_APP_FIRX1_ACT_MASK		0x02000030
+#define IO_APP_FIRX0_ACT_MASK		0x02000038
+#define IO_APP_SEC_LEM_DEBUG_OVR	0x02000040
+#define IO_APP_EXTENDED_ERR_PTR		0x02000048
+#define IO_APP_COMMON_CONFIG		0x02000060
+
+#define IO_APP_DEBUG_REG_01		0x02010000
+#define IO_APP_DEBUG_REG_02		0x02010008
+#define IO_APP_DEBUG_REG_03		0x02010010
+#define IO_APP_DEBUG_REG_04		0x02010018
+#define IO_APP_DEBUG_REG_05		0x02010020
+#define IO_APP_DEBUG_REG_06		0x02010028
+#define IO_APP_DEBUG_REG_07		0x02010030
+#define IO_APP_DEBUG_REG_08		0x02010038
+#define IO_APP_DEBUG_REG_09		0x02010040
+#define IO_APP_DEBUG_REG_10		0x02010048
+#define IO_APP_DEBUG_REG_11		0x02010050
+#define IO_APP_DEBUG_REG_12		0x02010058
+#define IO_APP_DEBUG_REG_13		0x02010060
+#define IO_APP_DEBUG_REG_14		0x02010068
+#define IO_APP_DEBUG_REG_15		0x02010070
+#define IO_APP_DEBUG_REG_16		0x02010078
+#define IO_APP_DEBUG_REG_17		0x02010080
+#define IO_APP_DEBUG_REG_18		0x02010088
+
+/* Read/write from/to registers */
+struct genwqe_reg_io {
+	__u64 num;		/* register offset/address */
+	__u64 val64;
+};
+
+/*
+ * All registers of our card will return values not equal this values.
+ * If we see IO_ILLEGAL_VALUE on any of our MMIO register reads, the
+ * card can be considered as unusable. It will need recovery.
+ */
+#define IO_ILLEGAL_VALUE		0xffffffffffffffffull
+
+/*
+ * Generic DDCB execution interface.
+ *
+ * This interface is a first prototype resulting from discussions we
+ * had with other teams which wanted to use the Genwqe card. It allows
+ * to issue a DDCB request in a generic way. The request will block
+ * until it finishes or time out with error.
+ *
+ * Some DDCBs require DMA addresses to be specified in the ASIV
+ * block. The interface provies the capability to let the kernel
+ * driver know where those addresses are by specifying the ATS field,
+ * such that it can replace the user-space addresses with appropriate
+ * DMA addresses or DMA addresses of a scatter gather list which is
+ * dynamically created.
+ *
+ * Our hardware will refuse DDCB execution if the ATS field is not as
+ * expected. That means the DDCB execution engine in the chip knows
+ * where it expects DMA addresses within the ASIV part of the DDCB and
+ * will check that against the ATS field definition. Any invalid or
+ * unknown ATS content will lead to DDCB refusal.
+ */
+
+/* Genwqe chip Units */
+#define DDCB_ACFUNC_SLU			0x00  /* chip service layer unit */
+#define DDCB_ACFUNC_APP			0x01  /* chip application */
+
+/* DDCB return codes (RETC) */
+#define DDCB_RETC_IDLE			0x0000 /* Unexecuted/DDCB created */
+#define DDCB_RETC_PENDING		0x0101 /* Pending Execution */
+#define DDCB_RETC_COMPLETE		0x0102 /* Cmd complete. No error */
+#define DDCB_RETC_FAULT			0x0104 /* App Err, recoverable */
+#define DDCB_RETC_ERROR			0x0108 /* App Err, non-recoverable */
+#define DDCB_RETC_FORCED_ERROR		0x01ff /* overwritten by driver  */
+
+#define DDCB_RETC_UNEXEC		0x0110 /* Unexe/Removed from queue */
+#define DDCB_RETC_TERM			0x0120 /* Terminated */
+#define DDCB_RETC_RES0			0x0140 /* Reserved */
+#define DDCB_RETC_RES1			0x0180 /* Reserved */
+
+/* DDCB Command Options (CMDOPT) */
+#define DDCB_OPT_ECHO_FORCE_NO		0x0000 /* ECHO DDCB */
+#define DDCB_OPT_ECHO_FORCE_102		0x0001 /* force return code */
+#define DDCB_OPT_ECHO_FORCE_104		0x0002
+#define DDCB_OPT_ECHO_FORCE_108		0x0003
+
+#define DDCB_OPT_ECHO_FORCE_110		0x0004 /* only on PF ! */
+#define DDCB_OPT_ECHO_FORCE_120		0x0005
+#define DDCB_OPT_ECHO_FORCE_140		0x0006
+#define DDCB_OPT_ECHO_FORCE_180		0x0007
+
+#define DDCB_OPT_ECHO_COPY_NONE		(0 << 5)
+#define DDCB_OPT_ECHO_COPY_ALL		(1 << 5)
+
+/* Definitions of Service Layer Commands */
+#define SLCMD_ECHO_SYNC			0x00 /* PF/VF */
+#define SLCMD_MOVE_FLASH		0x06 /* PF only */
+#define SLCMD_MOVE_FLASH_FLAGS_MODE	0x03 /* bit 0 and 1 used for mode */
+#define SLCMD_MOVE_FLASH_FLAGS_DLOAD	0	/* mode: download  */
+#define SLCMD_MOVE_FLASH_FLAGS_EMUL	1	/* mode: emulation */
+#define SLCMD_MOVE_FLASH_FLAGS_UPLOAD	2	/* mode: upload	   */
+#define SLCMD_MOVE_FLASH_FLAGS_VERIFY	3	/* mode: verify	   */
+#define SLCMD_MOVE_FLASH_FLAG_NOTAP	(1 << 2)/* just dump DDCB and exit */
+#define SLCMD_MOVE_FLASH_FLAG_POLL	(1 << 3)/* wait for RETC >= 0102   */
+#define SLCMD_MOVE_FLASH_FLAG_PARTITION	(1 << 4)
+#define SLCMD_MOVE_FLASH_FLAG_ERASE	(1 << 5)
+
+enum genwqe_card_state {
+	GENWQE_CARD_UNUSED = 0,
+	GENWQE_CARD_USED = 1,
+	GENWQE_CARD_FATAL_ERROR = 2,
+	GENWQE_CARD_STATE_MAX,
+};
+
+/* common struct for chip image exchange */
+struct genwqe_bitstream {
+	__u64 data_addr;		/* pointer to image data */
+	__u32 size;			/* size of image file */
+	__u32 crc;			/* crc of this image */
+	__u64 target_addr;		/* starting address in Flash */
+	__u32 partition;		/* '0', '1', or 'v' */
+	__u32 uid;			/* 1=host/x=dram */
+
+	__u64 slu_id;			/* informational/sim: SluID */
+	__u64 app_id;			/* informational/sim: AppID */
+
+	__u16 retc;			/* returned from processing */
+	__u16 attn;			/* attention code from processing */
+	__u32 progress;			/* progress code from processing */
+};
+
+/* Issuing a specific DDCB command */
+#define DDCB_LENGTH			256 /* for debug data */
+#define DDCB_ASIV_LENGTH		104 /* len of the DDCB ASIV array */
+#define DDCB_ASIV_LENGTH_ATS		96  /* ASIV in ATS architecture */
+#define DDCB_ASV_LENGTH			64  /* len of the DDCB ASV array  */
+#define DDCB_FIXUPS			12  /* maximum number of fixups */
+
+struct genwqe_debug_data {
+	char driver_version[64];
+	__u64 slu_unitcfg;
+	__u64 app_unitcfg;
+
+	__u8  ddcb_before[DDCB_LENGTH];
+	__u8  ddcb_prev[DDCB_LENGTH];
+	__u8  ddcb_finished[DDCB_LENGTH];
+};
+
+/*
+ * Address Translation Specification (ATS) definitions
+ *
+ * Each 4 bit within the ATS 64-bit word specify the required address
+ * translation at the defined offset.
+ *
+ * 63 LSB
+ *         6666.5555.5555.5544.4444.4443.3333.3333 ... 11
+ *         3210.9876.5432.1098.7654.3210.9876.5432 ... 1098.7654.3210
+ *
+ * offset: 0x00 0x08 0x10 0x18 0x20 0x28 0x30 0x38 ... 0x68 0x70 0x78
+ *         res  res  res  res  ASIV ...
+ * The first 4 entries in the ATS word are reserved. The following nibbles
+ * each describe at an 8 byte offset the format of the required data.
+ */
+#define ATS_TYPE_DATA			0x0ull /* data  */
+#define ATS_TYPE_FLAT_RD		0x4ull /* flat buffer read only */
+#define ATS_TYPE_FLAT_RDWR		0x5ull /* flat buffer read/write */
+#define ATS_TYPE_SGL_RD			0x6ull /* sgl read only */
+#define ATS_TYPE_SGL_RDWR		0x7ull /* sgl read/write */
+
+#define ATS_SET_FLAGS(_struct, _field, _flags)				\
+	(((_flags) & 0xf) << (44 - (4 * (offsetof(_struct, _field) / 8))))
+
+#define ATS_GET_FLAGS(_ats, _byte_offs)					\
+	(((_ats)	  >> (44 - (4 * ((_byte_offs) / 8)))) & 0xf)
+
+/**
+ * struct genwqe_ddcb_cmd - User parameter for generic DDCB commands
+ *
+ * On the way into the kernel the driver will read the whole data
+ * structure. On the way out the driver will not copy the ASIV data
+ * back to user-space.
+ */
+struct genwqe_ddcb_cmd {
+	/* START of data copied to/from driver */
+	__u64 next_addr;		/* chaining genwqe_ddcb_cmd */
+	__u64 flags;			/* reserved */
+
+	__u8  acfunc;			/* accelerators functional unit */
+	__u8  cmd;			/* command to execute */
+	__u8  asiv_length;		/* used parameter length */
+	__u8  asv_length;		/* length of valid return values  */
+	__u16 cmdopts;			/* command options */
+	__u16 retc;			/* return code from processing    */
+
+	__u16 attn;			/* attention code from processing */
+	__u16 vcrc;			/* variant crc16 */
+	__u32 progress;			/* progress code from processing  */
+
+	__u64 deque_ts;			/* dequeue time stamp */
+	__u64 cmplt_ts;			/* completion time stamp */
+	__u64 disp_ts;			/* SW processing start */
+
+	/* move to end and avoid copy-back */
+	__u64 ddata_addr;		/* collect debug data */
+
+	/* command specific values */
+	__u8  asv[DDCB_ASV_LENGTH];
+
+	/* END of data copied from driver */
+	union {
+		struct {
+			__u64 ats;
+			__u8  asiv[DDCB_ASIV_LENGTH_ATS];
+		};
+		/* used for flash update to keep it backward compatible */
+		__u8 __asiv[DDCB_ASIV_LENGTH];
+	};
+	/* END of data copied to driver */
+};
+
+#define GENWQE_IOC_CODE	    0xa5
+
+/* Access functions */
+#define GENWQE_READ_REG64   _IOR(GENWQE_IOC_CODE, 30, struct genwqe_reg_io)
+#define GENWQE_WRITE_REG64  _IOW(GENWQE_IOC_CODE, 31, struct genwqe_reg_io)
+#define GENWQE_READ_REG32   _IOR(GENWQE_IOC_CODE, 32, struct genwqe_reg_io)
+#define GENWQE_WRITE_REG32  _IOW(GENWQE_IOC_CODE, 33, struct genwqe_reg_io)
+#define GENWQE_READ_REG16   _IOR(GENWQE_IOC_CODE, 34, struct genwqe_reg_io)
+#define GENWQE_WRITE_REG16  _IOW(GENWQE_IOC_CODE, 35, struct genwqe_reg_io)
+
+#define GENWQE_GET_CARD_STATE _IOR(GENWQE_IOC_CODE, 36,	enum genwqe_card_state)
+
+/**
+ * struct genwqe_mem - Memory pinning/unpinning information
+ * @addr:          virtual user space address
+ * @size:          size of the area pin/dma-map/unmap
+ * direction:      0: read/1: read and write
+ *
+ * Avoid pinning and unpinning of memory pages dynamically. Instead
+ * the idea is to pin the whole buffer space required for DDCB
+ * opertionas in advance. The driver will reuse this pinning and the
+ * memory associated with it to setup the sglists for the DDCB
+ * requests without the need to allocate and free memory or map and
+ * unmap to get the DMA addresses.
+ *
+ * The inverse operation needs to be called after the pinning is not
+ * needed anymore. The pinnings else the pinnings will get removed
+ * after the device is closed. Note that pinnings will required
+ * memory.
+ */
+struct genwqe_mem {
+	__u64 addr;
+	__u64 size;
+	__u64 direction;
+	__u64 flags;
+};
+
+#define GENWQE_PIN_MEM	      _IOWR(GENWQE_IOC_CODE, 40, struct genwqe_mem)
+#define GENWQE_UNPIN_MEM      _IOWR(GENWQE_IOC_CODE, 41, struct genwqe_mem)
+
+/*
+ * Generic synchronous DDCB execution interface.
+ * Synchronously execute a DDCB.
+ *
+ * Return: 0 on success or negative error code.
+ *         -EINVAL: Invalid parameters (ASIV_LEN, ASV_LEN, illegal fixups
+ *                  no mappings found/could not create mappings
+ *         -EFAULT: illegal addresses in fixups, purging failed
+ *         -EBADMSG: enqueing failed, retc != DDCB_RETC_COMPLETE
+ */
+#define GENWQE_EXECUTE_DDCB					\
+	_IOWR(GENWQE_IOC_CODE, 50, struct genwqe_ddcb_cmd)
+
+#define GENWQE_EXECUTE_RAW_DDCB					\
+	_IOWR(GENWQE_IOC_CODE, 51, struct genwqe_ddcb_cmd)
+
+/* Service Layer functions (PF only) */
+#define GENWQE_SLU_UPDATE  _IOWR(GENWQE_IOC_CODE, 80, struct genwqe_bitstream)
+#define GENWQE_SLU_READ	   _IOWR(GENWQE_IOC_CODE, 81, struct genwqe_bitstream)
+
+#endif	/* __GENWQE_CARD_H__ */