@@ -345,6 +345,7 @@ source "drivers/scsi/cxgbi/Kconfig"
source "drivers/scsi/bnx2i/Kconfig"
source "drivers/scsi/bnx2fc/Kconfig"
source "drivers/scsi/be2iscsi/Kconfig"
+source "drivers/scsi/cxlflash/Kconfig"
config SGIWD93_SCSI
tristate "SGI WD93C93 SCSI Driver"
@@ -101,6 +101,7 @@ obj-$(CONFIG_SCSI_7000FASST) += wd7000.o
obj-$(CONFIG_SCSI_EATA) += eata.o
obj-$(CONFIG_SCSI_DC395x) += dc395x.o
obj-$(CONFIG_SCSI_AM53C974) += esp_scsi.o am53c974.o
+obj-$(CONFIG_CXLFLASH) += cxlflash/
obj-$(CONFIG_MEGARAID_LEGACY) += megaraid.o
obj-$(CONFIG_MEGARAID_NEWGEN) += megaraid/
obj-$(CONFIG_MEGARAID_SAS) += megaraid/
new file mode 100644
@@ -0,0 +1,11 @@
+#
+# IBM CXL-attached Flash Accelerator SCSI Driver
+#
+
+config CXLFLASH
+ tristate "Support for IBM CAPI Flash"
+ depends on PCI && SCSI && CXL
+ default m
+ help
+ Allows CAPI Accelerated IO to Flash
+ If unsure, say N.
new file mode 100644
@@ -0,0 +1,2 @@
+obj-$(CONFIG_CXLFLASH) += cxlflash.o
+cxlflash-y += main.o
new file mode 100644
@@ -0,0 +1,181 @@
+/*
+ * CXL Flash Device Driver
+ *
+ * Written by: Manoj N. Kumar <manoj@linux.vnet.ibm.com>, IBM Corporation
+ * Matthew R. Ochs <mrochs@linux.vnet.ibm.com>, IBM Corporation
+ *
+ * Copyright (C) 2015 IBM Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _CXLFLASH_COMMON_H
+#define _CXLFLASH_COMMON_H
+
+#include <linux/list.h>
+#include <linux/types.h>
+#include <scsi/scsi.h>
+#include <scsi/scsi_device.h>
+
+
+#define MAX_CONTEXT CXLFLASH_MAX_CONTEXT /* num contexts per afu */
+
+#define CXLFLASH_BLOCK_SIZE 4096 /* 4K blocks */
+#define CXLFLASH_MAX_XFER_SIZE 16777216 /* 16MB transfer */
+#define CXLFLASH_MAX_SECTORS (CXLFLASH_MAX_XFER_SIZE/512) /* SCSI wants
+ max_sectors
+ in units of
+ 512 byte
+ sectors
+ */
+
+#define NUM_RRQ_ENTRY 16 /* for master issued cmds */
+#define MAX_RHT_PER_CONTEXT (PAGE_SIZE / sizeof(struct sisl_rht_entry))
+
+/* AFU command retry limit */
+#define MC_RETRY_CNT 5 /* sufficient for SCSI check and
+ certain AFU errors */
+
+/* Command management definitions */
+#define CXLFLASH_NUM_CMDS (2 * CXLFLASH_MAX_CMDS) /* Must be a pow2 for
+ alignment and more
+ efficient array
+ index derivation
+ */
+
+#define CXLFLASH_MAX_CMDS 16
+#define CXLFLASH_MAX_CMDS_PER_LUN CXLFLASH_MAX_CMDS
+
+
+static inline void check_sizes(void)
+{
+ BUILD_BUG_ON_NOT_POWER_OF_2(CXLFLASH_NUM_CMDS);
+}
+
+/* AFU defines a fixed size of 4K for command buffers (borrow 4K page define) */
+#define CMD_BUFSIZE SIZE_4K
+
+/* flags in IOA status area for host use */
+#define B_DONE 0x01
+#define B_ERROR 0x02 /* set with B_DONE */
+#define B_TIMEOUT 0x04 /* set with B_DONE & B_ERROR */
+
+enum cxlflash_lr_state {
+ LINK_RESET_INVALID,
+ LINK_RESET_REQUIRED,
+ LINK_RESET_COMPLETE
+};
+
+enum cxlflash_init_state {
+ INIT_STATE_NONE,
+ INIT_STATE_PCI,
+ INIT_STATE_AFU,
+ INIT_STATE_SCSI
+};
+
+/*
+ * Each context has its own set of resource handles that is visible
+ * only from that context.
+ */
+
+struct cxlflash_cfg {
+ struct afu *afu;
+ struct cxl_context *mcctx;
+
+ struct pci_dev *dev;
+ struct pci_device_id *dev_id;
+ struct Scsi_Host *host;
+
+ ulong cxlflash_regs_pci;
+
+ wait_queue_head_t eeh_waitq;
+
+ struct work_struct work_q;
+ enum cxlflash_init_state init_state;
+ enum cxlflash_lr_state lr_state;
+ int lr_port;
+
+ struct cxl_afu *cxl_afu;
+
+ struct pci_pool *cxlflash_cmd_pool;
+ struct pci_dev *parent_dev;
+
+ wait_queue_head_t tmf_waitq;
+ bool tmf_active;
+ u8 err_recovery_active:1;
+};
+
+struct afu_cmd {
+ struct sisl_ioarcb rcb; /* IOARCB (cache line aligned) */
+ struct sisl_ioasa sa; /* IOASA must follow IOARCB */
+ spinlock_t slock;
+ struct completion cevent;
+ char *buf; /* per command buffer */
+ struct afu *parent;
+ int slot;
+ atomic_t free;
+
+ u8 cmd_tmf:1;
+
+ /* As per the SISLITE spec the IOARCB EA has to be 16-byte aligned.
+ * However for performance reasons the IOARCB/IOASA should be
+ * cache line aligned.
+ */
+} __aligned(cache_line_size());
+
+struct afu {
+ /* Stuff requiring alignment go first. */
+
+ u64 rrq_entry[NUM_RRQ_ENTRY]; /* 128B RRQ */
+ /*
+ * Command & data for AFU commands.
+ */
+ struct afu_cmd cmd[CXLFLASH_NUM_CMDS];
+
+ /* Beware of alignment till here. Preferably introduce new
+ * fields after this point
+ */
+
+ /* AFU HW */
+ struct cxl_ioctl_start_work work;
+ struct cxlflash_afu_map *afu_map; /* entire MMIO map */
+ struct sisl_host_map *host_map; /* MC host map */
+ struct sisl_ctrl_map *ctrl_map; /* MC control map */
+
+ ctx_hndl_t ctx_hndl; /* master's context handle */
+ u64 *hrrq_start;
+ u64 *hrrq_end;
+ u64 *hrrq_curr;
+ bool toggle;
+ bool read_room;
+ atomic64_t room;
+ u64 hb;
+ u32 cmd_couts; /* Number of command checkouts */
+ u32 internal_lun; /* User-desired LUN mode for this AFU */
+
+ char version[8];
+ u64 interface_version;
+
+ struct cxlflash_cfg *parent; /* Pointer back to parent cxlflash_cfg */
+
+};
+
+static inline u64 lun_to_lunid(u64 lun)
+{
+ u64 lun_id;
+
+ int_to_scsilun(lun, (struct scsi_lun *)&lun_id);
+ return swab64(lun_id);
+}
+
+int cxlflash_send_cmd(struct afu *, struct afu_cmd *);
+void cxlflash_wait_resp(struct afu *, struct afu_cmd *);
+int cxlflash_afu_reset(struct cxlflash_cfg *);
+struct afu_cmd *cxlflash_cmd_checkout(struct afu *);
+void cxlflash_cmd_checkin(struct afu_cmd *);
+int cxlflash_afu_sync(struct afu *, ctx_hndl_t, res_hndl_t, u8);
+#endif /* ifndef _CXLFLASH_COMMON_H */
+
new file mode 100644
@@ -0,0 +1,2294 @@
+/*
+ * CXL Flash Device Driver
+ *
+ * Written by: Manoj N. Kumar <manoj@linux.vnet.ibm.com>, IBM Corporation
+ * Matthew R. Ochs <mrochs@linux.vnet.ibm.com>, IBM Corporation
+ *
+ * Copyright (C) 2015 IBM Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/delay.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+
+#include <asm/unaligned.h>
+
+#include <misc/cxl.h>
+
+#include <scsi/scsi_cmnd.h>
+#include <scsi/scsi_host.h>
+
+#include "main.h"
+#include "sislite.h"
+#include "common.h"
+
+MODULE_DESCRIPTION(CXLFLASH_ADAPTER_NAME);
+MODULE_AUTHOR("Manoj N. Kumar <manoj@linux.vnet.ibm.com>");
+MODULE_AUTHOR("Matthew R. Ochs <mrochs@linux.vnet.ibm.com>");
+MODULE_LICENSE("GPL");
+
+
+/**
+ * cxlflash_cmd_checkout() - checks out an AFU command
+ * @afu: AFU to checkout from.
+ *
+ * Commands are checked out in a round-robin fashion. Note that since
+ * the command pool is larger than the hardware queue, the majority of
+ * times we will only loop once or twice before getting a command. The
+ * buffer and CDB within the command are initialized (zeroed) prior to
+ * returning.
+ *
+ * Return: The checked out command or NULL when command pool is empty.
+ */
+struct afu_cmd *cxlflash_cmd_checkout(struct afu *afu)
+{
+ int k, dec = CXLFLASH_NUM_CMDS;
+ struct afu_cmd *cmd;
+
+ while (dec--) {
+ k = (afu->cmd_couts++ & (CXLFLASH_NUM_CMDS - 1));
+
+ cmd = &afu->cmd[k];
+
+ if (!atomic_dec_if_positive(&cmd->free)) {
+ pr_debug("%s: returning found index=%d\n",
+ __func__, cmd->slot);
+ memset(cmd->buf, 0, CMD_BUFSIZE);
+ memset(cmd->rcb.cdb, 0, sizeof(cmd->rcb.cdb));
+ return cmd;
+ }
+ }
+
+ return NULL;
+}
+
+/**
+ * cxlflash_cmd_checkin() - checks in an AFU command
+ * @cmd: AFU command to checkin.
+ *
+ * Safe to pass commands that have already been checked in. Several
+ * internal tracking fields are reset as part of the checkin. Note
+ * that these are intentionally reset prior to toggling the free bit
+ * to avoid clobbering values in the event that the command is checked
+ * out right away.
+ */
+void cxlflash_cmd_checkin(struct afu_cmd *cmd)
+{
+ cmd->rcb.scp = NULL;
+ cmd->rcb.timeout = 0;
+ cmd->sa.ioasc = 0;
+ cmd->cmd_tmf = false;
+ cmd->sa.host_use[0] = 0; /* clears both completion and retry bytes */
+
+ if (unlikely(atomic_inc_return(&cmd->free) != 1)) {
+ pr_err("%s: Freeing cmd (%d) that is not in use!\n",
+ __func__, cmd->slot);
+ return;
+ }
+
+ pr_debug("%s: released cmd %p index=%d\n", __func__, cmd, cmd->slot);
+}
+
+/**
+ * process_cmd_err() - command error handler
+ * @cmd: AFU command that experienced the error.
+ * @scp: SCSI command associated with the AFU command in error.
+ *
+ * Translates error bits from AFU command to SCSI command results.
+ */
+static void process_cmd_err(struct afu_cmd *cmd, struct scsi_cmnd *scp)
+{
+ struct sisl_ioarcb *ioarcb;
+ struct sisl_ioasa *ioasa;
+
+ if (unlikely(!cmd))
+ return;
+
+ ioarcb = &(cmd->rcb);
+ ioasa = &(cmd->sa);
+
+ if (ioasa->rc.flags & SISL_RC_FLAGS_UNDERRUN) {
+ pr_debug("%s: cmd underrun cmd = %p scp = %p\n",
+ __func__, cmd, scp);
+ scp->result = (DID_ERROR << 16);
+ }
+
+ if (ioasa->rc.flags & SISL_RC_FLAGS_OVERRUN) {
+ pr_debug("%s: cmd underrun cmd = %p scp = %p\n",
+ __func__, cmd, scp);
+ scp->result = (DID_ERROR << 16);
+ }
+
+ pr_debug("%s: cmd failed afu_rc=%d scsi_rc=%d fc_rc=%d "
+ "afu_extra=0x%X, scsi_entra=0x%X, fc_extra=0x%X\n",
+ __func__, ioasa->rc.afu_rc, ioasa->rc.scsi_rc,
+ ioasa->rc.fc_rc, ioasa->afu_extra, ioasa->scsi_extra,
+ ioasa->fc_extra);
+
+ if (ioasa->rc.scsi_rc) {
+ /* We have a SCSI status */
+ if (ioasa->rc.flags & SISL_RC_FLAGS_SENSE_VALID) {
+ memcpy(scp->sense_buffer, ioasa->sense_data,
+ SISL_SENSE_DATA_LEN);
+ scp->result = ioasa->rc.scsi_rc;
+ } else
+ scp->result = ioasa->rc.scsi_rc | (DID_ERROR << 16);
+ }
+
+ /*
+ * We encountered an error. Set scp->result based on nature
+ * of error.
+ */
+ if (ioasa->rc.fc_rc) {
+ /* We have an FC status */
+ switch (ioasa->rc.fc_rc) {
+ case SISL_FC_RC_LINKDOWN:
+ scp->result = (DID_REQUEUE << 16);
+ break;
+ case SISL_FC_RC_RESID:
+ /* This indicates an FCP resid underrun */
+ if (!(ioasa->rc.flags & SISL_RC_FLAGS_OVERRUN)) {
+ /* If the SISL_RC_FLAGS_OVERRUN flag was set,
+ * then we will handle this error else where.
+ * If not then we must handle it here.
+ * This is probably an AFU bug. We will
+ * attempt a retry to see if that resolves it.
+ */
+ scp->result = (DID_ERROR << 16);
+ }
+ break;
+ case SISL_FC_RC_RESIDERR:
+ /* Resid mismatch between adapter and device */
+ case SISL_FC_RC_TGTABORT:
+ case SISL_FC_RC_ABORTOK:
+ case SISL_FC_RC_ABORTFAIL:
+ case SISL_FC_RC_NOLOGI:
+ case SISL_FC_RC_ABORTPEND:
+ case SISL_FC_RC_WRABORTPEND:
+ case SISL_FC_RC_NOEXP:
+ case SISL_FC_RC_INUSE:
+ scp->result = (DID_ERROR << 16);
+ break;
+ }
+ }
+
+ if (ioasa->rc.afu_rc) {
+ /* We have an AFU error */
+ switch (ioasa->rc.afu_rc) {
+ case SISL_AFU_RC_NO_CHANNELS:
+ scp->result = (DID_MEDIUM_ERROR << 16);
+ break;
+ case SISL_AFU_RC_DATA_DMA_ERR:
+ switch (ioasa->afu_extra) {
+ case SISL_AFU_DMA_ERR_PAGE_IN:
+ /* Retry */
+ scp->result = (DID_IMM_RETRY << 16);
+ break;
+ case SISL_AFU_DMA_ERR_INVALID_EA:
+ default:
+ scp->result = (DID_ERROR << 16);
+ }
+ break;
+ case SISL_AFU_RC_OUT_OF_DATA_BUFS:
+ /* Retry */
+ scp->result = (DID_ALLOC_FAILURE << 16);
+ break;
+ default:
+ scp->result = (DID_ERROR << 16);
+ }
+ }
+}
+
+/**
+ * cmd_complete() - command completion handler
+ * @cmd: AFU command that has completed.
+ *
+ * Prepares and submits command that has either completed or timed out to
+ * the SCSI stack. Checks AFU command back into command pool for non-internal
+ * (rcb.scp populated) commands.
+ */
+static void cmd_complete(struct afu_cmd *cmd)
+{
+ struct scsi_cmnd *scp;
+ u32 resid;
+ ulong lock_flags;
+ struct afu *afu = cmd->parent;
+ struct cxlflash_cfg *cfg = afu->parent;
+ bool cmd_is_tmf;
+
+ spin_lock_irqsave(&cmd->slock, lock_flags);
+ cmd->sa.host_use_b[0] |= B_DONE;
+ spin_unlock_irqrestore(&cmd->slock, lock_flags);
+
+ if (cmd->rcb.scp) {
+ scp = cmd->rcb.scp;
+ if (unlikely(cmd->sa.rc.afu_rc ||
+ cmd->sa.rc.scsi_rc ||
+ cmd->sa.rc.fc_rc))
+ process_cmd_err(cmd, scp);
+ else
+ scp->result = (DID_OK << 16);
+
+ resid = cmd->sa.resid;
+ cmd_is_tmf = cmd->cmd_tmf;
+ cxlflash_cmd_checkin(cmd); /* Don't use cmd after here */
+
+ pr_debug("%s: calling scsi_set_resid, scp=%p "
+ "result=%X resid=%d\n", __func__,
+ scp, scp->result, resid);
+
+ scsi_set_resid(scp, resid);
+ scsi_dma_unmap(scp);
+ scp->scsi_done(scp);
+
+ if (cmd_is_tmf) {
+ spin_lock_irqsave(&cfg->tmf_waitq.lock, lock_flags);
+ cfg->tmf_active = false;
+ wake_up_all_locked(&cfg->tmf_waitq);
+ spin_unlock_irqrestore(&cfg->tmf_waitq.lock,
+ lock_flags);
+ }
+ } else
+ complete(&cmd->cevent);
+}
+
+/**
+ * send_tmf() - sends a Task Management Function (TMF)
+ * @afu: AFU to checkout from.
+ * @scp: SCSI command from stack.
+ * @tmfcmd: TMF command to send.
+ *
+ * Return:
+ * 0 on success
+ * SCSI_MLQUEUE_HOST_BUSY when host is busy
+ */
+static int send_tmf(struct afu *afu, struct scsi_cmnd *scp, u64 tmfcmd)
+{
+ struct afu_cmd *cmd;
+
+ u32 port_sel = scp->device->channel + 1;
+ short lflag = 0;
+ struct Scsi_Host *host = scp->device->host;
+ struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)host->hostdata;
+ ulong lock_flags;
+ int rc = 0;
+
+ cmd = cxlflash_cmd_checkout(afu);
+ if (unlikely(!cmd)) {
+ pr_err("%s: could not get a free command\n", __func__);
+ rc = SCSI_MLQUEUE_HOST_BUSY;
+ goto out;
+ }
+
+ /* If a Task Management Function is active, do not send one more.
+ */
+ spin_lock_irqsave(&cfg->tmf_waitq.lock, lock_flags);
+ if (cfg->tmf_active)
+ wait_event_interruptible_locked_irq(cfg->tmf_waitq,
+ !cfg->tmf_active);
+ cfg->tmf_active = true;
+ cmd->cmd_tmf = true;
+ spin_unlock_irqrestore(&cfg->tmf_waitq.lock, lock_flags);
+
+ cmd->rcb.ctx_id = afu->ctx_hndl;
+ cmd->rcb.port_sel = port_sel;
+ cmd->rcb.lun_id = lun_to_lunid(scp->device->lun);
+
+ lflag = SISL_REQ_FLAGS_TMF_CMD;
+
+ cmd->rcb.req_flags = (SISL_REQ_FLAGS_PORT_LUN_ID |
+ SISL_REQ_FLAGS_SUP_UNDERRUN | lflag);
+
+ /* Stash the scp in the reserved field, for reuse during interrupt */
+ cmd->rcb.scp = scp;
+
+ /* Copy the CDB from the cmd passed in */
+ memcpy(cmd->rcb.cdb, &tmfcmd, sizeof(tmfcmd));
+
+ /* Send the command */
+ rc = cxlflash_send_cmd(afu, cmd);
+ if (unlikely(rc)) {
+ cxlflash_cmd_checkin(cmd);
+ spin_lock_irqsave(&cfg->tmf_waitq.lock, lock_flags);
+ cfg->tmf_active = false;
+ spin_unlock_irqrestore(&cfg->tmf_waitq.lock, lock_flags);
+ goto out;
+ }
+
+ spin_lock_irqsave(&cfg->tmf_waitq.lock, lock_flags);
+ wait_event_interruptible_locked_irq(cfg->tmf_waitq, !cfg->tmf_active);
+ spin_unlock_irqrestore(&cfg->tmf_waitq.lock, lock_flags);
+out:
+ return rc;
+}
+
+/**
+ * cxlflash_driver_info() - information handler for this host driver
+ * @host: SCSI host associated with device.
+ *
+ * Return: A string describing the device.
+ */
+static const char *cxlflash_driver_info(struct Scsi_Host *host)
+{
+ return CXLFLASH_ADAPTER_NAME;
+}
+
+/**
+ * cxlflash_queuecommand() - sends a mid-layer request
+ * @host: SCSI host associated with device.
+ * @scp: SCSI command to send.
+ *
+ * Return:
+ * 0 on success
+ * SCSI_MLQUEUE_HOST_BUSY when host is busy
+ */
+static int cxlflash_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scp)
+{
+ struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)host->hostdata;
+ struct afu *afu = cfg->afu;
+ struct pci_dev *pdev = cfg->dev;
+ struct afu_cmd *cmd;
+ u32 port_sel = scp->device->channel + 1;
+ int nseg, i, ncount;
+ struct scatterlist *sg;
+ ulong lock_flags;
+ short lflag = 0;
+ int rc = 0;
+
+ pr_debug("%s: (scp=%p) %d/%d/%d/%llu cdb=(%08X-%08X-%08X-%08X)\n",
+ __func__, scp, host->host_no, scp->device->channel,
+ scp->device->id, scp->device->lun,
+ get_unaligned_be32(&((u32 *)scp->cmnd)[0]),
+ get_unaligned_be32(&((u32 *)scp->cmnd)[1]),
+ get_unaligned_be32(&((u32 *)scp->cmnd)[2]),
+ get_unaligned_be32(&((u32 *)scp->cmnd)[3]));
+
+ /* If a Task Management Function is active, wait for it to complete
+ * before continuing with regular commands.
+ */
+ spin_lock_irqsave(&cfg->tmf_waitq.lock, lock_flags);
+ if (cfg->tmf_active) {
+ spin_unlock_irqrestore(&cfg->tmf_waitq.lock, lock_flags);
+ rc = SCSI_MLQUEUE_HOST_BUSY;
+ goto out;
+ }
+ spin_unlock_irqrestore(&cfg->tmf_waitq.lock, lock_flags);
+
+ cmd = cxlflash_cmd_checkout(afu);
+ if (unlikely(!cmd)) {
+ pr_err("%s: could not get a free command\n", __func__);
+ rc = SCSI_MLQUEUE_HOST_BUSY;
+ goto out;
+ }
+
+ cmd->rcb.ctx_id = afu->ctx_hndl;
+ cmd->rcb.port_sel = port_sel;
+ cmd->rcb.lun_id = lun_to_lunid(scp->device->lun);
+
+ if (scp->sc_data_direction == DMA_TO_DEVICE)
+ lflag = SISL_REQ_FLAGS_HOST_WRITE;
+ else
+ lflag = SISL_REQ_FLAGS_HOST_READ;
+
+ cmd->rcb.req_flags = (SISL_REQ_FLAGS_PORT_LUN_ID |
+ SISL_REQ_FLAGS_SUP_UNDERRUN | lflag);
+
+ /* Stash the scp in the reserved field, for reuse during interrupt */
+ cmd->rcb.scp = scp;
+
+ nseg = scsi_dma_map(scp);
+ if (unlikely(nseg < 0)) {
+ dev_err(&pdev->dev, "%s: Fail DMA map! nseg=%d\n",
+ __func__, nseg);
+ rc = SCSI_MLQUEUE_HOST_BUSY;
+ goto out;
+ }
+
+ ncount = scsi_sg_count(scp);
+ scsi_for_each_sg(scp, sg, ncount, i) {
+ cmd->rcb.data_len = sg_dma_len(sg);
+ cmd->rcb.data_ea = sg_dma_address(sg);
+ }
+
+ /* Copy the CDB from the scsi_cmnd passed in */
+ memcpy(cmd->rcb.cdb, scp->cmnd, sizeof(cmd->rcb.cdb));
+
+ /* Send the command */
+ rc = cxlflash_send_cmd(afu, cmd);
+ if (unlikely(rc)) {
+ cxlflash_cmd_checkin(cmd);
+ scsi_dma_unmap(scp);
+ }
+
+out:
+ return rc;
+}
+
+/**
+ * cxlflash_eh_device_reset_handler() - reset a single LUN
+ * @scp: SCSI command to send.
+ *
+ * Return:
+ * SUCCESS as defined in scsi/scsi.h
+ * FAILED as defined in scsi/scsi.h
+ */
+static int cxlflash_eh_device_reset_handler(struct scsi_cmnd *scp)
+{
+ int rc = SUCCESS;
+ struct Scsi_Host *host = scp->device->host;
+ struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)host->hostdata;
+ struct afu *afu = cfg->afu;
+ int rcr = 0;
+
+ pr_debug("%s: (scp=%p) %d/%d/%d/%llu "
+ "cdb=(%08X-%08X-%08X-%08X)\n", __func__, scp,
+ host->host_no, scp->device->channel,
+ scp->device->id, scp->device->lun,
+ get_unaligned_be32(&((u32 *)scp->cmnd)[0]),
+ get_unaligned_be32(&((u32 *)scp->cmnd)[1]),
+ get_unaligned_be32(&((u32 *)scp->cmnd)[2]),
+ get_unaligned_be32(&((u32 *)scp->cmnd)[3]));
+
+ rcr = send_tmf(afu, scp, TMF_LUN_RESET);
+ if (unlikely(rcr))
+ rc = FAILED;
+
+ pr_debug("%s: returning rc=%d\n", __func__, rc);
+ return rc;
+}
+
+/**
+ * cxlflash_eh_host_reset_handler() - reset the host adapter
+ * @scp: SCSI command from stack identifying host.
+ *
+ * Return:
+ * SUCCESS as defined in scsi/scsi.h
+ * FAILED as defined in scsi/scsi.h
+ */
+static int cxlflash_eh_host_reset_handler(struct scsi_cmnd *scp)
+{
+ int rc = SUCCESS;
+ int rcr = 0;
+ struct Scsi_Host *host = scp->device->host;
+ struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)host->hostdata;
+
+ pr_debug("%s: (scp=%p) %d/%d/%d/%llu "
+ "cdb=(%08X-%08X-%08X-%08X)\n", __func__, scp,
+ host->host_no, scp->device->channel,
+ scp->device->id, scp->device->lun,
+ get_unaligned_be32(&((u32 *)scp->cmnd)[0]),
+ get_unaligned_be32(&((u32 *)scp->cmnd)[1]),
+ get_unaligned_be32(&((u32 *)scp->cmnd)[2]),
+ get_unaligned_be32(&((u32 *)scp->cmnd)[3]));
+
+ rcr = cxlflash_afu_reset(cfg);
+ if (rcr == 0)
+ rc = SUCCESS;
+ else
+ rc = FAILED;
+
+ pr_debug("%s: returning rc=%d\n", __func__, rc);
+ return rc;
+}
+
+/**
+ * cxlflash_change_queue_depth() - change the queue depth for the device
+ * @sdev: SCSI device destined for queue depth change.
+ * @qdepth: Requested queue depth value to set.
+ *
+ * The requested queue depth is capped to the maximum supported value.
+ *
+ * Return: The actual queue depth set.
+ */
+static int cxlflash_change_queue_depth(struct scsi_device *sdev, int qdepth)
+{
+
+ if (qdepth > CXLFLASH_MAX_CMDS_PER_LUN)
+ qdepth = CXLFLASH_MAX_CMDS_PER_LUN;
+
+ scsi_change_queue_depth(sdev, qdepth);
+ return sdev->queue_depth;
+}
+
+/**
+ * cxlflash_show_port_status() - queries and presents the current port status
+ * @dev: Generic device associated with the host owning the port.
+ * @attr: Device attribute representing the port.
+ * @buf: Buffer of length PAGE_SIZE to report back port status in ASCII.
+ *
+ * Return: The size of the ASCII string returned in @buf.
+ */
+static ssize_t cxlflash_show_port_status(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct Scsi_Host *shost = class_to_shost(dev);
+ struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)shost->hostdata;
+ struct afu *afu = cfg->afu;
+
+ char *disp_status;
+ int rc;
+ u32 port;
+ u64 status;
+ u64 *fc_regs;
+
+ rc = kstrtouint((attr->attr.name + 4), 10, &port);
+ if (rc || (port > NUM_FC_PORTS))
+ return 0;
+
+ fc_regs = &afu->afu_map->global.fc_regs[port][0];
+ status =
+ (readq_be(&fc_regs[FC_MTIP_STATUS / 8]) & FC_MTIP_STATUS_MASK);
+
+ if (status == FC_MTIP_STATUS_ONLINE)
+ disp_status = "online";
+ else if (status == FC_MTIP_STATUS_OFFLINE)
+ disp_status = "offline";
+ else
+ disp_status = "unknown";
+
+ return snprintf(buf, PAGE_SIZE, "%s\n", disp_status);
+}
+
+/**
+ * cxlflash_show_lun_mode() - presents the current LUN mode of the host
+ * @dev: Generic device associated with the host.
+ * @attr: Device attribute representing the lun mode.
+ * @buf: Buffer of length PAGE_SIZE to report back the LUN mode in ASCII.
+ *
+ * Return: The size of the ASCII string returned in @buf.
+ */
+static ssize_t cxlflash_show_lun_mode(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct Scsi_Host *shost = class_to_shost(dev);
+ struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)shost->hostdata;
+ struct afu *afu = cfg->afu;
+
+ return snprintf(buf, PAGE_SIZE, "%u\n", afu->internal_lun);
+}
+
+/**
+ * cxlflash_store_lun_mode() - sets the LUN mode of the host
+ * @dev: Generic device associated with the host.
+ * @attr: Device attribute representing the lun mode.
+ * @buf: Buffer of length PAGE_SIZE containing the LUN mode in ASCII.
+ * @count: Length of data resizing in @buf.
+ *
+ * The CXL Flash AFU supports a dummy LUN mode where the external
+ * links and storage are not required. Space on the FPGA is used
+ * to create 1 or 2 small LUNs which are presented to the system
+ * as if they were a normal storage device. This feature is useful
+ * during development and also provides manufacturing with a way
+ * to test the AFU without an actual device.
+ *
+ * 0 = external LUN[s] (default)
+ * 1 = internal LUN (1 x 64K, 512B blocks, id 0)
+ * 2 = internal LUN (1 x 64K, 4K blocks, id 0)
+ * 3 = internal LUN (2 x 32K, 512B blocks, ids 0,1)
+ * 4 = internal LUN (2 x 32K, 4K blocks, ids 0,1)
+ *
+ * Return: The size of the ASCII string returned in @buf.
+ */
+static ssize_t cxlflash_store_lun_mode(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct Scsi_Host *shost = class_to_shost(dev);
+ struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)shost->hostdata;
+ struct afu *afu = cfg->afu;
+ int rc;
+ u32 lun_mode;
+
+ rc = kstrtouint(buf, 10, &lun_mode);
+ if (!rc && (lun_mode < 5) && (lun_mode != afu->internal_lun)) {
+ afu->internal_lun = lun_mode;
+ cxlflash_afu_reset(cfg);
+ scsi_scan_host(cfg->host);
+ }
+
+ return count;
+}
+
+/**
+ * cxlflash_show_dev_mode() - presents the current mode of the device
+ * @dev: Generic device associated with the device.
+ * @attr: Device attribute representing the device mode.
+ * @buf: Buffer of length PAGE_SIZE to report back the dev mode in ASCII.
+ *
+ * Return: The size of the ASCII string returned in @buf.
+ */
+static ssize_t cxlflash_show_dev_mode(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct scsi_device *sdev = to_scsi_device(dev);
+
+ return snprintf(buf, PAGE_SIZE, "%s\n",
+ sdev->hostdata ? "superpipe" : "legacy");
+}
+
+/**
+ * cxlflash_wait_for_pci_err_recovery() - wait for error recovery during probe
+ * @cxlflash: Internal structure associated with the host.
+ */
+static void cxlflash_wait_for_pci_err_recovery(struct cxlflash_cfg *cfg)
+{
+ struct pci_dev *pdev = cfg->dev;
+
+ if (pci_channel_offline(pdev))
+ wait_event_timeout(cfg->eeh_waitq,
+ !pci_channel_offline(pdev),
+ CXLFLASH_PCI_ERROR_RECOVERY_TIMEOUT);
+}
+
+/*
+ * Host attributes
+ */
+static DEVICE_ATTR(port0, S_IRUGO, cxlflash_show_port_status, NULL);
+static DEVICE_ATTR(port1, S_IRUGO, cxlflash_show_port_status, NULL);
+static DEVICE_ATTR(lun_mode, S_IRUGO | S_IWUSR, cxlflash_show_lun_mode,
+ cxlflash_store_lun_mode);
+
+static struct device_attribute *cxlflash_host_attrs[] = {
+ &dev_attr_port0,
+ &dev_attr_port1,
+ &dev_attr_lun_mode,
+ NULL
+};
+
+/*
+ * Device attributes
+ */
+static DEVICE_ATTR(mode, S_IRUGO, cxlflash_show_dev_mode, NULL);
+
+static struct device_attribute *cxlflash_dev_attrs[] = {
+ &dev_attr_mode,
+ NULL
+};
+
+/*
+ * Host template
+ */
+static struct scsi_host_template driver_template = {
+ .module = THIS_MODULE,
+ .name = CXLFLASH_ADAPTER_NAME,
+ .info = cxlflash_driver_info,
+ .proc_name = CXLFLASH_NAME,
+ .queuecommand = cxlflash_queuecommand,
+ .eh_device_reset_handler = cxlflash_eh_device_reset_handler,
+ .eh_host_reset_handler = cxlflash_eh_host_reset_handler,
+ .change_queue_depth = cxlflash_change_queue_depth,
+ .cmd_per_lun = 16,
+ .can_queue = CXLFLASH_MAX_CMDS,
+ .this_id = -1,
+ .sg_tablesize = SG_NONE, /* No scatter gather support. */
+ .max_sectors = CXLFLASH_MAX_SECTORS,
+ .use_clustering = ENABLE_CLUSTERING,
+ .shost_attrs = cxlflash_host_attrs,
+ .sdev_attrs = cxlflash_dev_attrs,
+};
+
+/*
+ * Device dependent values
+ */
+static struct dev_dependent_vals dev_corsa_vals = { CXLFLASH_MAX_SECTORS };
+
+/*
+ * PCI device binding table
+ */
+static struct pci_device_id cxlflash_pci_table[] = {
+ {PCI_VENDOR_ID_IBM, PCI_DEVICE_ID_IBM_CORSA,
+ PCI_ANY_ID, PCI_ANY_ID, 0, 0, (kernel_ulong_t)&dev_corsa_vals},
+ {}
+};
+
+MODULE_DEVICE_TABLE(pci, cxlflash_pci_table);
+
+/**
+ * free_mem() - free memory associated with the AFU
+ * @cxlflash: Internal structure associated with the host.
+ */
+static void free_mem(struct cxlflash_cfg *cfg)
+{
+ int i;
+ char *buf = NULL;
+ struct afu *afu = cfg->afu;
+
+ if (cfg->afu) {
+ for (i = 0; i < CXLFLASH_NUM_CMDS; i++) {
+ buf = afu->cmd[i].buf;
+ if (!((u64)buf & (PAGE_SIZE - 1)))
+ free_page((ulong)buf);
+ }
+
+ free_pages((ulong)afu, get_order(sizeof(struct afu)));
+ cfg->afu = NULL;
+ }
+}
+
+/**
+ * stop_afu() - stops the AFU command timers and unmaps the MMIO space
+ * @cxlflash: Internal structure associated with the host.
+ *
+ * Safe to call with AFU in a partially allocated/initialized state.
+ */
+static void stop_afu(struct cxlflash_cfg *cfg)
+{
+ int i;
+ struct afu *afu = cfg->afu;
+
+ if (likely(afu)) {
+ for (i = 0; i < CXLFLASH_NUM_CMDS; i++)
+ complete(&afu->cmd[i].cevent);
+
+ if (likely(afu->afu_map)) {
+ cxl_psa_unmap((void *)afu->afu_map);
+ afu->afu_map = NULL;
+ }
+ }
+}
+
+/**
+ * term_mc() - terminates the master context
+ * @cxlflash: Internal structure associated with the host.
+ * @level: Depth of allocation, where to begin waterfall tear down.
+ *
+ * Safe to call with AFU/MC in partially allocated/initialized state.
+ */
+static void term_mc(struct cxlflash_cfg *cfg, enum undo_level level)
+{
+ int rc = 0;
+ struct afu *afu = cfg->afu;
+
+ if (!afu || !cfg->mcctx) {
+ pr_err("%s: returning from term_mc with NULL afu or MC\n",
+ __func__);
+ return;
+ }
+
+ switch (level) {
+ case UNDO_START:
+ rc = cxl_stop_context(cfg->mcctx);
+ BUG_ON(rc);
+ case UNMAP_THREE:
+ cxl_unmap_afu_irq(cfg->mcctx, 3, afu);
+ case UNMAP_TWO:
+ cxl_unmap_afu_irq(cfg->mcctx, 2, afu);
+ case UNMAP_ONE:
+ cxl_unmap_afu_irq(cfg->mcctx, 1, afu);
+ case FREE_IRQ:
+ cxl_free_afu_irqs(cfg->mcctx);
+ case RELEASE_CONTEXT:
+ cfg->mcctx = NULL;
+ }
+}
+
+/**
+ * term_afu() - terminates the AFU
+ * @cxlflash: Internal structure associated with the host.
+ *
+ * Safe to call with AFU/MC in partially allocated/initialized state.
+ */
+static void term_afu(struct cxlflash_cfg *cfg)
+{
+ term_mc(cfg, UNDO_START);
+
+ if (cfg->afu)
+ stop_afu(cfg);
+
+ pr_debug("%s: returning\n", __func__);
+}
+
+/**
+ * cxlflash_remove() - PCI entry point to tear down host
+ * @pdev: PCI device associated with the host.
+ *
+ * Safe to use as a cleanup in partially allocated/initialized state.
+ */
+static void cxlflash_remove(struct pci_dev *pdev)
+{
+ struct cxlflash_cfg *cfg = pci_get_drvdata(pdev);
+ ulong lock_flags;
+
+ /* If a Task Management Function is active, wait for it to complete
+ * before continuing with remove.
+ */
+ spin_lock_irqsave(&cfg->tmf_waitq.lock, lock_flags);
+ if (cfg->tmf_active)
+ wait_event_interruptible_locked_irq(cfg->tmf_waitq,
+ !cfg->tmf_active);
+ spin_unlock_irqrestore(&cfg->tmf_waitq.lock, lock_flags);
+
+ switch (cfg->init_state) {
+ case INIT_STATE_SCSI:
+ scsi_remove_host(cfg->host);
+ scsi_host_put(cfg->host);
+ /* Fall through */
+ case INIT_STATE_AFU:
+ term_afu(cfg);
+ case INIT_STATE_PCI:
+ pci_release_regions(cfg->dev);
+ pci_disable_device(pdev);
+ case INIT_STATE_NONE:
+ flush_work(&cfg->work_q);
+ free_mem(cfg);
+ break;
+ }
+
+ pr_debug("%s: returning\n", __func__);
+}
+
+/**
+ * alloc_mem() - allocates the AFU and its command pool
+ * @cxlflash: Internal structure associated with the host.
+ *
+ * A partially allocated state remains on failure.
+ *
+ * Return:
+ * 0 on success
+ * -ENOMEM on failure to allocate memory
+ */
+static int alloc_mem(struct cxlflash_cfg *cfg)
+{
+ int rc = 0;
+ int i;
+ char *buf = NULL;
+
+ /* This allocation is about 12K, i.e. only 1 64k page
+ * and upto 4 4k pages
+ */
+ cfg->afu = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
+ get_order(sizeof(struct afu)));
+ if (unlikely(!cfg->afu)) {
+ pr_err("%s: cannot get %d free pages\n",
+ __func__, get_order(sizeof(struct afu)));
+ rc = -ENOMEM;
+ goto out;
+ }
+ cfg->afu->parent = cfg;
+ cfg->afu->afu_map = NULL;
+
+ for (i = 0; i < CXLFLASH_NUM_CMDS; buf += CMD_BUFSIZE, i++) {
+ if (!((u64)buf & (PAGE_SIZE - 1))) {
+ buf = (void *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
+ if (unlikely(!buf)) {
+ pr_err("%s: Allocate command buffers fail!\n",
+ __func__);
+ rc = -ENOMEM;
+ free_mem(cfg);
+ goto out;
+ }
+ }
+
+ cfg->afu->cmd[i].buf = buf;
+ atomic_set(&cfg->afu->cmd[i].free, 1);
+ cfg->afu->cmd[i].slot = i;
+ }
+
+out:
+ return rc;
+}
+
+/**
+ * init_pci() - initializes the host as a PCI device
+ * @cxlflash: Internal structure associated with the host.
+ *
+ * Return:
+ * 0 on success
+ * -EIO on unable to communicate with device
+ * A return code from the PCI sub-routines
+ */
+static int init_pci(struct cxlflash_cfg *cfg)
+{
+ struct pci_dev *pdev = cfg->dev;
+ int rc = 0;
+
+ cfg->cxlflash_regs_pci = pci_resource_start(pdev, 0);
+ rc = pci_request_regions(pdev, CXLFLASH_NAME);
+ if (rc < 0) {
+ dev_err(&pdev->dev,
+ "%s: Couldn't register memory range of registers\n",
+ __func__);
+ goto out;
+ }
+
+ rc = pci_enable_device(pdev);
+ if (rc || pci_channel_offline(pdev)) {
+ if (pci_channel_offline(pdev)) {
+ cxlflash_wait_for_pci_err_recovery(cfg);
+ rc = pci_enable_device(pdev);
+ }
+
+ if (rc) {
+ dev_err(&pdev->dev, "%s: Cannot enable adapter\n",
+ __func__);
+ cxlflash_wait_for_pci_err_recovery(cfg);
+ goto out_release_regions;
+ }
+ }
+
+ rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(64));
+ if (rc < 0) {
+ dev_dbg(&pdev->dev, "%s: Failed to set 64 bit PCI DMA mask\n",
+ __func__);
+ rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
+ }
+
+ if (rc < 0) {
+ dev_err(&pdev->dev, "%s: Failed to set PCI DMA mask\n",
+ __func__);
+ goto out_disable;
+ }
+
+ pci_set_master(pdev);
+
+ if (pci_channel_offline(pdev)) {
+ cxlflash_wait_for_pci_err_recovery(cfg);
+ if (pci_channel_offline(pdev)) {
+ rc = -EIO;
+ goto out_msi_disable;
+ }
+ }
+
+ rc = pci_save_state(pdev);
+
+ if (rc != PCIBIOS_SUCCESSFUL) {
+ dev_err(&pdev->dev, "%s: Failed to save PCI config space\n",
+ __func__);
+ rc = -EIO;
+ goto cleanup_nolog;
+ }
+
+out:
+ pr_debug("%s: returning rc=%d\n", __func__, rc);
+ return rc;
+
+cleanup_nolog:
+out_msi_disable:
+ cxlflash_wait_for_pci_err_recovery(cfg);
+out_disable:
+ pci_disable_device(pdev);
+out_release_regions:
+ pci_release_regions(pdev);
+ goto out;
+
+}
+
+/**
+ * init_scsi() - adds the host to the SCSI stack and kicks off host scan
+ * @cxlflash: Internal structure associated with the host.
+ *
+ * Return:
+ * 0 on success
+ * A return code from adding the host
+ */
+static int init_scsi(struct cxlflash_cfg *cfg)
+{
+ struct pci_dev *pdev = cfg->dev;
+ int rc = 0;
+
+ rc = scsi_add_host(cfg->host, &pdev->dev);
+ if (rc) {
+ dev_err(&pdev->dev, "%s: scsi_add_host failed (rc=%d)\n",
+ __func__, rc);
+ goto out;
+ }
+
+ scsi_scan_host(cfg->host);
+
+out:
+ pr_debug("%s: returning rc=%d\n", __func__, rc);
+ return rc;
+}
+
+/**
+ * set_port_online() - transitions the specified host FC port to online state
+ * @fc_regs: Top of MMIO region defined for specified port.
+ *
+ * The provided MMIO region must be mapped prior to call. Online state means
+ * that the FC link layer has synced, completed the handshaking process, and
+ * is ready for login to start.
+ */
+static void set_port_online(u64 *fc_regs)
+{
+ u64 cmdcfg;
+
+ cmdcfg = readq_be(&fc_regs[FC_MTIP_CMDCONFIG / 8]);
+ cmdcfg &= (~FC_MTIP_CMDCONFIG_OFFLINE); /* clear OFF_LINE */
+ cmdcfg |= (FC_MTIP_CMDCONFIG_ONLINE); /* set ON_LINE */
+ writeq_be(cmdcfg, &fc_regs[FC_MTIP_CMDCONFIG / 8]);
+}
+
+/**
+ * set_port_offline() - transitions the specified host FC port to offline state
+ * @fc_regs: Top of MMIO region defined for specified port.
+ *
+ * The provided MMIO region must be mapped prior to call.
+ */
+static void set_port_offline(u64 *fc_regs)
+{
+ u64 cmdcfg;
+
+ cmdcfg = readq_be(&fc_regs[FC_MTIP_CMDCONFIG / 8]);
+ cmdcfg &= (~FC_MTIP_CMDCONFIG_ONLINE); /* clear ON_LINE */
+ cmdcfg |= (FC_MTIP_CMDCONFIG_OFFLINE); /* set OFF_LINE */
+ writeq_be(cmdcfg, &fc_regs[FC_MTIP_CMDCONFIG / 8]);
+}
+
+/**
+ * wait_port_online() - waits for the specified host FC port come online
+ * @fc_regs: Top of MMIO region defined for specified port.
+ * @delay_us: Number of microseconds to delay between reading port status.
+ * @nretry: Number of cycles to retry reading port status.
+ *
+ * The provided MMIO region must be mapped prior to call. This will timeout
+ * when the cable is not plugged in.
+ *
+ * Return:
+ * TRUE (1) when the specified port is online
+ * FALSE (0) when the specified port fails to come online after timeout
+ * -EINVAL when @delay_us is less than 1000
+ */
+static int wait_port_online(u64 *fc_regs, u32 delay_us, u32 nretry)
+{
+ u64 status;
+
+ if (delay_us < 1000) {
+ pr_err("%s: invalid delay specified %d\n", __func__, delay_us);
+ return -EINVAL;
+ }
+
+ do {
+ msleep(delay_us / 1000);
+ status = readq_be(&fc_regs[FC_MTIP_STATUS / 8]);
+ } while ((status & FC_MTIP_STATUS_MASK) != FC_MTIP_STATUS_ONLINE &&
+ nretry--);
+
+ return ((status & FC_MTIP_STATUS_MASK) == FC_MTIP_STATUS_ONLINE);
+}
+
+/**
+ * wait_port_offline() - waits for the specified host FC port go offline
+ * @fc_regs: Top of MMIO region defined for specified port.
+ * @delay_us: Number of microseconds to delay between reading port status.
+ * @nretry: Number of cycles to retry reading port status.
+ *
+ * The provided MMIO region must be mapped prior to call.
+ *
+ * Return:
+ * TRUE (1) when the specified port is offline
+ * FALSE (0) when the specified port fails to go offline after timeout
+ * -EINVAL when @delay_us is less than 1000
+ */
+static int wait_port_offline(u64 *fc_regs, u32 delay_us, u32 nretry)
+{
+ u64 status;
+
+ if (delay_us < 1000) {
+ pr_err("%s: invalid delay specified %d\n", __func__, delay_us);
+ return -EINVAL;
+ }
+
+ do {
+ msleep(delay_us / 1000);
+ status = readq_be(&fc_regs[FC_MTIP_STATUS / 8]);
+ } while ((status & FC_MTIP_STATUS_MASK) != FC_MTIP_STATUS_OFFLINE &&
+ nretry--);
+
+ return ((status & FC_MTIP_STATUS_MASK) == FC_MTIP_STATUS_OFFLINE);
+}
+
+/**
+ * afu_set_wwpn() - configures the WWPN for the specified host FC port
+ * @afu: AFU associated with the host that owns the specified FC port.
+ * @port: Port number being configured.
+ * @fc_regs: Top of MMIO region defined for specified port.
+ * @wwpn: The world-wide-port-number previously discovered for port.
+ *
+ * The provided MMIO region must be mapped prior to call. As part of the
+ * sequence to configure the WWPN, the port is toggled offline and then back
+ * online. This toggling action can cause this routine to delay up to a few
+ * seconds. When configured to use the internal LUN feature of the AFU, a
+ * failure to come online is overridden.
+ *
+ * Return:
+ * 0 when the WWPN is successfully written and the port comes back online
+ * -1 when the port fails to go offline or come back up online
+ */
+static int afu_set_wwpn(struct afu *afu, int port, u64 *fc_regs, u64 wwpn)
+{
+ int ret = 0;
+
+ set_port_offline(fc_regs);
+
+ if (!wait_port_offline(fc_regs, FC_PORT_STATUS_RETRY_INTERVAL_US,
+ FC_PORT_STATUS_RETRY_CNT)) {
+ pr_debug("%s: wait on port %d to go offline timed out\n",
+ __func__, port);
+ ret = -1; /* but continue on to leave the port back online */
+ }
+
+ if (ret == 0)
+ writeq_be(wwpn, &fc_regs[FC_PNAME / 8]);
+
+ set_port_online(fc_regs);
+
+ if (!wait_port_online(fc_regs, FC_PORT_STATUS_RETRY_INTERVAL_US,
+ FC_PORT_STATUS_RETRY_CNT)) {
+ pr_debug("%s: wait on port %d to go online timed out\n",
+ __func__, port);
+ ret = -1;
+
+ /*
+ * Override for internal lun!!!
+ */
+ if (afu->internal_lun) {
+ pr_debug("%s: Overriding port %d online timeout!!!\n",
+ __func__, port);
+ ret = 0;
+ }
+ }
+
+ pr_debug("%s: returning rc=%d\n", __func__, ret);
+
+ return ret;
+}
+
+/**
+ * afu_link_reset() - resets the specified host FC port
+ * @afu: AFU associated with the host that owns the specified FC port.
+ * @port: Port number being configured.
+ * @fc_regs: Top of MMIO region defined for specified port.
+ *
+ * The provided MMIO region must be mapped prior to call. The sequence to
+ * reset the port involves toggling it offline and then back online. This
+ * action can cause this routine to delay up to a few seconds. An effort
+ * is made to maintain link with the device by switching to host to use
+ * the alternate port exclusively while the reset takes place.
+ * failure to come online is overridden.
+ */
+static void afu_link_reset(struct afu *afu, int port, u64 *fc_regs)
+{
+ u64 port_sel;
+
+ /* first switch the AFU to the other links, if any */
+ port_sel = readq_be(&afu->afu_map->global.regs.afu_port_sel);
+ port_sel &= ~(1 << port);
+ writeq_be(port_sel, &afu->afu_map->global.regs.afu_port_sel);
+ cxlflash_afu_sync(afu, 0, 0, AFU_GSYNC);
+
+ set_port_offline(fc_regs);
+ if (!wait_port_offline(fc_regs, FC_PORT_STATUS_RETRY_INTERVAL_US,
+ FC_PORT_STATUS_RETRY_CNT))
+ pr_err("%s: wait on port %d to go offline timed out\n",
+ __func__, port);
+
+ set_port_online(fc_regs);
+ if (!wait_port_online(fc_regs, FC_PORT_STATUS_RETRY_INTERVAL_US,
+ FC_PORT_STATUS_RETRY_CNT))
+ pr_err("%s: wait on port %d to go online timed out\n",
+ __func__, port);
+
+ /* switch back to include this port */
+ port_sel |= (1 << port);
+ writeq_be(port_sel, &afu->afu_map->global.regs.afu_port_sel);
+ cxlflash_afu_sync(afu, 0, 0, AFU_GSYNC);
+
+ pr_debug("%s: returning port_sel=%lld\n", __func__, port_sel);
+}
+
+/*
+ * Asynchronous interrupt information table
+ */
+static const struct asyc_intr_info ainfo[] = {
+ {SISL_ASTATUS_FC0_OTHER, "other error", 0, CLR_FC_ERROR | LINK_RESET},
+ {SISL_ASTATUS_FC0_LOGO, "target initiated LOGO", 0, 0},
+ {SISL_ASTATUS_FC0_CRC_T, "CRC threshold exceeded", 0, LINK_RESET},
+ {SISL_ASTATUS_FC0_LOGI_R, "login timed out, retrying", 0, 0},
+ {SISL_ASTATUS_FC0_LOGI_F, "login failed", 0, CLR_FC_ERROR},
+ {SISL_ASTATUS_FC0_LOGI_S, "login succeeded", 0, 0},
+ {SISL_ASTATUS_FC0_LINK_DN, "link down", 0, 0},
+ {SISL_ASTATUS_FC0_LINK_UP, "link up", 0, 0},
+ {SISL_ASTATUS_FC1_OTHER, "other error", 1, CLR_FC_ERROR | LINK_RESET},
+ {SISL_ASTATUS_FC1_LOGO, "target initiated LOGO", 1, 0},
+ {SISL_ASTATUS_FC1_CRC_T, "CRC threshold exceeded", 1, LINK_RESET},
+ {SISL_ASTATUS_FC1_LOGI_R, "login timed out, retrying", 1, 0},
+ {SISL_ASTATUS_FC1_LOGI_F, "login failed", 1, CLR_FC_ERROR},
+ {SISL_ASTATUS_FC1_LOGI_S, "login succeeded", 1, 0},
+ {SISL_ASTATUS_FC1_LINK_DN, "link down", 1, 0},
+ {SISL_ASTATUS_FC1_LINK_UP, "link up", 1, 0},
+ {0x0, "", 0, 0} /* terminator */
+};
+
+/**
+ * find_ainfo() - locates and returns asynchronous interrupt information
+ * @status: Status code set by AFU on error.
+ *
+ * Return: The located information or NULL when the status code is invalid.
+ */
+static const struct asyc_intr_info *find_ainfo(u64 status)
+{
+ const struct asyc_intr_info *info;
+
+ for (info = &ainfo[0]; info->status; info++)
+ if (info->status == status)
+ return info;
+
+ return NULL;
+}
+
+/**
+ * afu_err_intr_init() - clears and initializes the AFU for error interrupts
+ * @afu: AFU associated with the host.
+ */
+static void afu_err_intr_init(struct afu *afu)
+{
+ int i;
+ u64 reg;
+
+ /* global async interrupts: AFU clears afu_ctrl on context exit
+ * if async interrupts were sent to that context. This prevents
+ * the AFU form sending further async interrupts when
+ * there is
+ * nobody to receive them.
+ */
+
+ /* mask all */
+ writeq_be(-1ULL, &afu->afu_map->global.regs.aintr_mask);
+ /* set LISN# to send and point to master context */
+ reg = ((u64) (((afu->ctx_hndl << 8) | SISL_MSI_ASYNC_ERROR)) << 40);
+
+ if (afu->internal_lun)
+ reg |= 1; /* Bit 63 indicates local lun */
+ writeq_be(reg, &afu->afu_map->global.regs.afu_ctrl);
+ /* clear all */
+ writeq_be(-1ULL, &afu->afu_map->global.regs.aintr_clear);
+ /* unmask bits that are of interest */
+ /* note: afu can send an interrupt after this step */
+ writeq_be(SISL_ASTATUS_MASK, &afu->afu_map->global.regs.aintr_mask);
+ /* clear again in case a bit came on after previous clear but before */
+ /* unmask */
+ writeq_be(-1ULL, &afu->afu_map->global.regs.aintr_clear);
+
+ /* Clear/Set internal lun bits */
+ reg = readq_be(&afu->afu_map->global.fc_regs[0][FC_CONFIG2 / 8]);
+ reg &= SISL_FC_INTERNAL_MASK;
+ if (afu->internal_lun)
+ reg |= ((u64)(afu->internal_lun - 1) << SISL_FC_INTERNAL_SHIFT);
+ writeq_be(reg, &afu->afu_map->global.fc_regs[0][FC_CONFIG2 / 8]);
+
+ /* now clear FC errors */
+ for (i = 0; i < NUM_FC_PORTS; i++) {
+ writeq_be(0xFFFFFFFFU,
+ &afu->afu_map->global.fc_regs[i][FC_ERROR / 8]);
+ writeq_be(0, &afu->afu_map->global.fc_regs[i][FC_ERRCAP / 8]);
+ }
+
+ /* sync interrupts for master's IOARRIN write */
+ /* note that unlike asyncs, there can be no pending sync interrupts */
+ /* at this time (this is a fresh context and master has not written */
+ /* IOARRIN yet), so there is nothing to clear. */
+
+ /* set LISN#, it is always sent to the context that wrote IOARRIN */
+ writeq_be(SISL_MSI_SYNC_ERROR, &afu->host_map->ctx_ctrl);
+ writeq_be(SISL_ISTATUS_MASK, &afu->host_map->intr_mask);
+}
+
+/**
+ * cxlflash_sync_err_irq() - interrupt handler for synchronous errors
+ * @irq: Interrupt number.
+ * @data: Private data provided at interrupt registration, the AFU.
+ *
+ * Return: Always return IRQ_HANDLED.
+ */
+static irqreturn_t cxlflash_sync_err_irq(int irq, void *data)
+{
+ struct afu *afu = (struct afu *)data;
+ u64 reg;
+ u64 reg_unmasked;
+
+ reg = readq_be(&afu->host_map->intr_status);
+ reg_unmasked = (reg & SISL_ISTATUS_UNMASK);
+
+ if (reg_unmasked == 0UL) {
+ pr_err("%s: %llX: spurious interrupt, intr_status %016llX\n",
+ __func__, (u64)afu, reg);
+ goto cxlflash_sync_err_irq_exit;
+ }
+
+ pr_err("%s: %llX: unexpected interrupt, intr_status %016llX\n",
+ __func__, (u64)afu, reg);
+
+ writeq_be(reg_unmasked, &afu->host_map->intr_clear);
+
+cxlflash_sync_err_irq_exit:
+ pr_debug("%s: returning rc=%d\n", __func__, IRQ_HANDLED);
+ return IRQ_HANDLED;
+}
+
+/**
+ * cxlflash_rrq_irq() - interrupt handler for read-response queue (normal path)
+ * @irq: Interrupt number.
+ * @data: Private data provided at interrupt registration, the AFU.
+ *
+ * Return: Always return IRQ_HANDLED.
+ */
+static irqreturn_t cxlflash_rrq_irq(int irq, void *data)
+{
+ struct afu *afu = (struct afu *)data;
+ struct afu_cmd *cmd;
+ bool toggle = afu->toggle;
+ u64 entry,
+ *hrrq_start = afu->hrrq_start,
+ *hrrq_end = afu->hrrq_end,
+ *hrrq_curr = afu->hrrq_curr;
+
+ /* Process however many RRQ entries that are ready */
+ while (true) {
+ entry = *hrrq_curr;
+
+ if ((entry & SISL_RESP_HANDLE_T_BIT) != toggle)
+ break;
+
+ cmd = (struct afu_cmd *)(entry & ~SISL_RESP_HANDLE_T_BIT);
+ cmd_complete(cmd);
+
+ /* Advance to next entry or wrap and flip the toggle bit */
+ if (hrrq_curr < hrrq_end)
+ hrrq_curr++;
+ else {
+ hrrq_curr = hrrq_start;
+ toggle ^= SISL_RESP_HANDLE_T_BIT;
+ }
+ }
+
+ afu->hrrq_curr = hrrq_curr;
+ afu->toggle = toggle;
+
+ return IRQ_HANDLED;
+}
+
+/**
+ * cxlflash_async_err_irq() - interrupt handler for asynchronous errors
+ * @irq: Interrupt number.
+ * @data: Private data provided at interrupt registration, the AFU.
+ *
+ * Return: Always return IRQ_HANDLED.
+ */
+static irqreturn_t cxlflash_async_err_irq(int irq, void *data)
+{
+ struct afu *afu = (struct afu *)data;
+ struct cxlflash_cfg *cfg;
+ u64 reg_unmasked;
+ const struct asyc_intr_info *info;
+ struct sisl_global_map *global = &afu->afu_map->global;
+ u64 reg;
+ u8 port;
+ int i;
+
+ cfg = afu->parent;
+
+ reg = readq_be(&global->regs.aintr_status);
+ reg_unmasked = (reg & SISL_ASTATUS_UNMASK);
+
+ if (reg_unmasked == 0) {
+ pr_err("%s: spurious interrupt, aintr_status 0x%016llX\n",
+ __func__, reg);
+ goto out;
+ }
+
+ /* it is OK to clear AFU status before FC_ERROR */
+ writeq_be(reg_unmasked, &global->regs.aintr_clear);
+
+ /* check each bit that is on */
+ for (i = 0; reg_unmasked; i++, reg_unmasked = (reg_unmasked >> 1)) {
+ info = find_ainfo(1ULL << i);
+ if ((reg_unmasked & 0x1) || !info)
+ continue;
+
+ port = info->port;
+
+ pr_err("%s: FC Port %d -> %s, fc_status 0x%08llX\n",
+ __func__, port, info->desc,
+ readq_be(&global->fc_regs[port][FC_STATUS / 8]));
+
+ /*
+ * do link reset first, some OTHER errors will set FC_ERROR
+ * again if cleared before or w/o a reset
+ */
+ if (info->action & LINK_RESET) {
+ pr_err("%s: FC Port %d: resetting link\n",
+ __func__, port);
+ cfg->lr_state = LINK_RESET_REQUIRED;
+ cfg->lr_port = port;
+ schedule_work(&cfg->work_q);
+ }
+
+ if (info->action & CLR_FC_ERROR) {
+ reg = readq_be(&global->fc_regs[port][FC_ERROR / 8]);
+
+ /*
+ * since all errors are unmasked, FC_ERROR and FC_ERRCAP
+ * should be the same and tracing one is sufficient.
+ */
+
+ pr_err("%s: fc %d: clearing fc_error 0x%08llX\n",
+ __func__, port, reg);
+
+ writeq_be(reg, &global->fc_regs[port][FC_ERROR / 8]);
+ writeq_be(0, &global->fc_regs[port][FC_ERRCAP / 8]);
+ }
+ }
+
+out:
+ pr_debug("%s: returning rc=%d, afu=%p\n", __func__, IRQ_HANDLED, afu);
+ return IRQ_HANDLED;
+}
+
+/**
+ * start_context() - starts the master context
+ * @cxlflash: Internal structure associated with the host.
+ *
+ * Return: A success or failure value from CXL services.
+ */
+static int start_context(struct cxlflash_cfg *cfg)
+{
+ int rc = 0;
+
+ rc = cxl_start_context(cfg->mcctx,
+ cfg->afu->work.work_element_descriptor,
+ NULL);
+
+ pr_debug("%s: returning rc=%d\n", __func__, rc);
+ return rc;
+}
+
+/**
+ * read_vpd() - obtains the WWPNs from VPD
+ * @cxlflash: Internal structure associated with the host.
+ * @wwpn: Array of size NUM_FC_PORTS to pass back WWPNs
+ *
+ * Return:
+ * 0 on success
+ * -ENODEV when VPD or WWPN keywords not found
+ */
+static int read_vpd(struct cxlflash_cfg *cfg, u64 wwpn[])
+{
+ struct pci_dev *dev = cfg->parent_dev;
+ int rc = 0;
+ int ro_start, ro_size, i, j, k;
+ ssize_t vpd_size;
+ char vpd_data[CXLFLASH_VPD_LEN];
+ char tmp_buf[WWPN_BUF_LEN] = { 0 };
+ char *wwpn_vpd_tags[NUM_FC_PORTS] = { "V5", "V6" };
+
+ /* Get the VPD data from the device */
+ vpd_size = pci_read_vpd(dev, 0, sizeof(vpd_data), vpd_data);
+ if (unlikely(vpd_size <= 0)) {
+ pr_err("%s: Unable to read VPD (size = %ld)\n",
+ __func__, vpd_size);
+ rc = -ENODEV;
+ goto out;
+ }
+
+ /* Get the read only section offset */
+ ro_start = pci_vpd_find_tag(vpd_data, 0, vpd_size,
+ PCI_VPD_LRDT_RO_DATA);
+ if (unlikely(ro_start < 0)) {
+ pr_err("%s: VPD Read-only data not found\n", __func__);
+ rc = -ENODEV;
+ goto out;
+ }
+
+ /* Get the read only section size, cap when extends beyond read VPD */
+ ro_size = pci_vpd_lrdt_size(&vpd_data[ro_start]);
+ j = ro_size;
+ i = ro_start + PCI_VPD_LRDT_TAG_SIZE;
+ if (unlikely((i + j) > vpd_size)) {
+ pr_debug("%s: Might need to read more VPD (%d > %ld)\n",
+ __func__, (i + j), vpd_size);
+ ro_size = vpd_size - i;
+ }
+
+ /*
+ * Find the offset of the WWPN tag within the read only
+ * VPD data and validate the found field (partials are
+ * no good to us). Convert the ASCII data to an integer
+ * value. Note that we must copy to a temporary buffer
+ * because the conversion service requires that the ASCII
+ * string be terminated.
+ */
+ for (k = 0; k < NUM_FC_PORTS; k++) {
+ j = ro_size;
+ i = ro_start + PCI_VPD_LRDT_TAG_SIZE;
+
+ i = pci_vpd_find_info_keyword(vpd_data, i, j, wwpn_vpd_tags[k]);
+ if (unlikely(i < 0)) {
+ pr_err("%s: Port %d WWPN not found in VPD\n",
+ __func__, k);
+ rc = -ENODEV;
+ goto out;
+ }
+
+ j = pci_vpd_info_field_size(&vpd_data[i]);
+ i += PCI_VPD_INFO_FLD_HDR_SIZE;
+ if (unlikely((i + j > vpd_size) || (j != WWPN_LEN))) {
+ pr_err("%s: Port %d WWPN incomplete or VPD corrupt\n",
+ __func__, k);
+ rc = -ENODEV;
+ goto out;
+ }
+
+ memcpy(tmp_buf, &vpd_data[i], WWPN_LEN);
+ rc = kstrtoul(tmp_buf, WWPN_LEN, (ulong *)&wwpn[k]);
+ if (unlikely(rc)) {
+ pr_err("%s: Fail to convert port %d WWPN to integer\n",
+ __func__, k);
+ rc = -ENODEV;
+ goto out;
+ }
+ }
+
+out:
+ pr_debug("%s: returning rc=%d\n", __func__, rc);
+ return rc;
+}
+
+/**
+ * cxlflash_context_reset() - timeout handler for AFU commands
+ * @cmd: AFU command that timed out.
+ *
+ * Sends a reset to the AFU.
+ */
+void cxlflash_context_reset(struct afu_cmd *cmd)
+{
+ int nretry = 0;
+ u64 rrin = 0x1;
+ u64 room = 0;
+ struct afu *afu = cmd->parent;
+ ulong lock_flags;
+
+ pr_debug("%s: cmd=%p\n", __func__, cmd);
+
+ spin_lock_irqsave(&cmd->slock, lock_flags);
+
+ /* Already completed? */
+ if (cmd->sa.host_use_b[0] & B_DONE) {
+ spin_unlock_irqrestore(&cmd->slock, lock_flags);
+ return;
+ }
+
+ cmd->sa.host_use_b[0] |= (B_DONE | B_ERROR | B_TIMEOUT);
+ spin_unlock_irqrestore(&cmd->slock, lock_flags);
+
+ /*
+ * We really want to send this reset at all costs, so spread
+ * out wait time on successive retries for available room.
+ */
+ do {
+ room = readq_be(&afu->host_map->cmd_room);
+ atomic64_set(&afu->room, room);
+ if (room)
+ goto write_rrin;
+ udelay(nretry);
+ } while (nretry++ < MC_ROOM_RETRY_CNT);
+
+ pr_err("%s: no cmd_room to send reset\n", __func__);
+ return;
+
+write_rrin:
+ nretry = 0;
+ writeq_be(rrin, &afu->host_map->ioarrin);
+ do {
+ rrin = readq_be(&afu->host_map->ioarrin);
+ if (rrin != 0x1)
+ break;
+ /* Double delay each time */
+ udelay(2 ^ nretry);
+ } while (nretry++ < MC_ROOM_RETRY_CNT);
+}
+
+/**
+ * init_pcr() - initialize the provisioning and control registers
+ * @cxlflash: Internal structure associated with the host.
+ *
+ * Also sets up fast access to the mapped registers and initializes AFU
+ * command fields that never change.
+ */
+void init_pcr(struct cxlflash_cfg *cfg)
+{
+ struct afu *afu = cfg->afu;
+ struct sisl_ctrl_map *ctrl_map;
+ int i;
+
+ for (i = 0; i < MAX_CONTEXT; i++) {
+ ctrl_map = &afu->afu_map->ctrls[i].ctrl;
+ /* disrupt any clients that could be running */
+ /* e. g. clients that survived a master restart */
+ writeq_be(0, &ctrl_map->rht_start);
+ writeq_be(0, &ctrl_map->rht_cnt_id);
+ writeq_be(0, &ctrl_map->ctx_cap);
+ }
+
+ /* copy frequently used fields into afu */
+ afu->ctx_hndl = (u16) cxl_process_element(cfg->mcctx);
+ /* ctx_hndl is 16 bits in CAIA */
+ afu->host_map = &afu->afu_map->hosts[afu->ctx_hndl].host;
+ afu->ctrl_map = &afu->afu_map->ctrls[afu->ctx_hndl].ctrl;
+
+ /* Program the Endian Control for the master context */
+ writeq_be(SISL_ENDIAN_CTRL, &afu->host_map->endian_ctrl);
+
+ /* initialize cmd fields that never change */
+ for (i = 0; i < CXLFLASH_NUM_CMDS; i++) {
+ afu->cmd[i].rcb.ctx_id = afu->ctx_hndl;
+ afu->cmd[i].rcb.msi = SISL_MSI_RRQ_UPDATED;
+ afu->cmd[i].rcb.rrq = 0x0;
+ }
+}
+
+/**
+ * init_global() - initialize AFU global registers
+ * @cxlflash: Internal structure associated with the host.
+ */
+int init_global(struct cxlflash_cfg *cfg)
+{
+ struct afu *afu = cfg->afu;
+ u64 wwpn[NUM_FC_PORTS]; /* wwpn of AFU ports */
+ int i = 0, num_ports = 0;
+ int rc = 0;
+ u64 reg;
+
+ rc = read_vpd(cfg, &wwpn[0]);
+ if (rc) {
+ pr_err("%s: could not read vpd rc=%d\n", __func__, rc);
+ goto out;
+ }
+
+ pr_debug("%s: wwpn0=0x%llX wwpn1=0x%llX\n", __func__, wwpn[0], wwpn[1]);
+
+ /* set up RRQ in AFU for master issued cmds */
+ writeq_be((u64) afu->hrrq_start, &afu->host_map->rrq_start);
+ writeq_be((u64) afu->hrrq_end, &afu->host_map->rrq_end);
+
+ /* AFU configuration */
+ reg = readq_be(&afu->afu_map->global.regs.afu_config);
+ reg |= SISL_AFUCONF_AR_ALL|SISL_AFUCONF_ENDIAN;
+ /* enable all auto retry options and control endianness */
+ /* leave others at default: */
+ /* CTX_CAP write protected, mbox_r does not clear on read and */
+ /* checker on if dual afu */
+ writeq_be(reg, &afu->afu_map->global.regs.afu_config);
+
+ /* global port select: select either port */
+ if (afu->internal_lun) {
+ /* only use port 0 */
+ writeq_be(PORT0, &afu->afu_map->global.regs.afu_port_sel);
+ num_ports = NUM_FC_PORTS - 1;
+ } else {
+ writeq_be(BOTH_PORTS, &afu->afu_map->global.regs.afu_port_sel);
+ num_ports = NUM_FC_PORTS;
+ }
+
+ for (i = 0; i < num_ports; i++) {
+ /* unmask all errors (but they are still masked at AFU) */
+ writeq_be(0, &afu->afu_map->global.fc_regs[i][FC_ERRMSK / 8]);
+ /* clear CRC error cnt & set a threshold */
+ (void)readq_be(&afu->afu_map->global.
+ fc_regs[i][FC_CNT_CRCERR / 8]);
+ writeq_be(MC_CRC_THRESH, &afu->afu_map->global.fc_regs[i]
+ [FC_CRC_THRESH / 8]);
+
+ /* set WWPNs. If already programmed, wwpn[i] is 0 */
+ if (wwpn[i] != 0 &&
+ afu_set_wwpn(afu, i,
+ &afu->afu_map->global.fc_regs[i][0],
+ wwpn[i])) {
+ pr_err("%s: failed to set WWPN on port %d\n",
+ __func__, i);
+ rc = -EIO;
+ goto out;
+ }
+ /* Programming WWPN back to back causes additional
+ * offline/online transitions and a PLOGI
+ */
+ msleep(100);
+
+ }
+
+ /* set up master's own CTX_CAP to allow real mode, host translation */
+ /* tbls, afu cmds and read/write GSCSI cmds. */
+ /* First, unlock ctx_cap write by reading mbox */
+ (void)readq_be(&afu->ctrl_map->mbox_r); /* unlock ctx_cap */
+ writeq_be((SISL_CTX_CAP_REAL_MODE | SISL_CTX_CAP_HOST_XLATE |
+ SISL_CTX_CAP_READ_CMD | SISL_CTX_CAP_WRITE_CMD |
+ SISL_CTX_CAP_AFU_CMD | SISL_CTX_CAP_GSCSI_CMD),
+ &afu->ctrl_map->ctx_cap);
+ /* init heartbeat */
+ afu->hb = readq_be(&afu->afu_map->global.regs.afu_hb);
+
+out:
+ return rc;
+}
+
+/**
+ * start_afu() - initializes and starts the AFU
+ * @cxlflash: Internal structure associated with the host.
+ */
+static int start_afu(struct cxlflash_cfg *cfg)
+{
+ struct afu *afu = cfg->afu;
+ struct afu_cmd *cmd;
+
+ int i = 0;
+ int rc = 0;
+
+ for (i = 0; i < CXLFLASH_NUM_CMDS; i++) {
+ cmd = &afu->cmd[i];
+
+ init_completion(&cmd->cevent);
+ spin_lock_init(&cmd->slock);
+ cmd->parent = afu;
+ }
+
+ init_pcr(cfg);
+
+ /* initialize RRQ pointers */
+ afu->hrrq_start = &afu->rrq_entry[0];
+ afu->hrrq_end = &afu->rrq_entry[NUM_RRQ_ENTRY - 1];
+ afu->hrrq_curr = afu->hrrq_start;
+ afu->toggle = 1;
+
+ rc = init_global(cfg);
+
+ pr_debug("%s: returning rc=%d\n", __func__, rc);
+ return rc;
+}
+
+/**
+ * init_mc() - create and register as the master context
+ * @cxlflash: Internal structure associated with the host.
+ *
+ * Return:
+ * 0 on success
+ * -ENOMEM when unable to obtain a context from CXL services
+ * A failure value from CXL services.
+ */
+static int init_mc(struct cxlflash_cfg *cfg)
+{
+ struct cxl_context *ctx;
+ struct device *dev = &cfg->dev->dev;
+ struct afu *afu = cfg->afu;
+ int rc = 0;
+ enum undo_level level;
+
+ ctx = cxl_get_context(cfg->dev);
+ if (unlikely(!ctx))
+ return -ENOMEM;
+ cfg->mcctx = ctx;
+
+ /* Set it up as a master with the CXL */
+ cxl_set_master(ctx);
+
+ /* During initialization reset the AFU to start from a clean slate */
+ rc = cxl_afu_reset(cfg->mcctx);
+ if (unlikely(rc)) {
+ dev_err(dev, "%s: initial AFU reset failed rc=%d\n",
+ __func__, rc);
+ level = RELEASE_CONTEXT;
+ goto out;
+ }
+
+ rc = cxl_allocate_afu_irqs(ctx, 3);
+ if (unlikely(rc)) {
+ dev_err(dev, "%s: call to allocate_afu_irqs failed rc=%d!\n",
+ __func__, rc);
+ level = RELEASE_CONTEXT;
+ goto out;
+ }
+
+ rc = cxl_map_afu_irq(ctx, 1, cxlflash_sync_err_irq, afu,
+ "SISL_MSI_SYNC_ERROR");
+ if (unlikely(rc <= 0)) {
+ dev_err(dev, "%s: IRQ 1 (SISL_MSI_SYNC_ERROR) map failed!\n",
+ __func__);
+ level = FREE_IRQ;
+ goto out;
+ }
+
+ rc = cxl_map_afu_irq(ctx, 2, cxlflash_rrq_irq, afu,
+ "SISL_MSI_RRQ_UPDATED");
+ if (unlikely(rc <= 0)) {
+ dev_err(dev, "%s: IRQ 2 (SISL_MSI_RRQ_UPDATED) map failed!\n",
+ __func__);
+ level = UNMAP_ONE;
+ goto out;
+ }
+
+ rc = cxl_map_afu_irq(ctx, 3, cxlflash_async_err_irq, afu,
+ "SISL_MSI_ASYNC_ERROR");
+ if (unlikely(rc <= 0)) {
+ dev_err(dev, "%s: IRQ 3 (SISL_MSI_ASYNC_ERROR) map failed!\n",
+ __func__);
+ level = UNMAP_TWO;
+ goto out;
+ }
+
+ rc = 0;
+
+ /* This performs the equivalent of the CXL_IOCTL_START_WORK.
+ * The CXL_IOCTL_GET_PROCESS_ELEMENT is implicit in the process
+ * element (pe) that is embedded in the context (ctx)
+ */
+ rc = start_context(cfg);
+ if (unlikely(rc)) {
+ dev_err(dev, "%s: start context failed rc=%d\n", __func__, rc);
+ level = UNMAP_THREE;
+ goto out;
+ }
+ret:
+ pr_debug("%s: returning rc=%d\n", __func__, rc);
+ return rc;
+out:
+ term_mc(cfg, level);
+ goto ret;
+}
+
+/**
+ * init_afu() - setup as master context and start AFU
+ * @cxlflash: Internal structure associated with the host.
+ *
+ * This routine is a higher level of control for configuring the
+ * AFU on probe and reset paths.
+ *
+ * Return:
+ * 0 on success
+ * -ENOMEM when unable to map the AFU MMIO space
+ * A failure value from internal services.
+ */
+static int init_afu(struct cxlflash_cfg *cfg)
+{
+ u64 reg;
+ int rc = 0;
+ struct afu *afu = cfg->afu;
+ struct device *dev = &cfg->dev->dev;
+
+ rc = init_mc(cfg);
+ if (rc) {
+ dev_err(dev, "%s: call to init_mc failed, rc=%d!\n",
+ __func__, rc);
+ goto err1;
+ }
+
+ /* Map the entire MMIO space of the AFU.
+ */
+ afu->afu_map = cxl_psa_map(cfg->mcctx);
+ if (!afu->afu_map) {
+ rc = -ENOMEM;
+ term_mc(cfg, UNDO_START);
+ dev_err(dev, "%s: call to cxl_psa_map failed!\n", __func__);
+ goto err1;
+ }
+
+ /* don't byte reverse on reading afu_version, else the string form */
+ /* will be backwards */
+ reg = afu->afu_map->global.regs.afu_version;
+ memcpy(afu->version, ®, 8);
+ afu->interface_version =
+ readq_be(&afu->afu_map->global.regs.interface_version);
+ pr_debug("%s: afu version %s, interface version 0x%llX\n",
+ __func__, afu->version, afu->interface_version);
+
+ rc = start_afu(cfg);
+ if (rc) {
+ dev_err(dev, "%s: call to start_afu failed, rc=%d!\n",
+ __func__, rc);
+ term_mc(cfg, UNDO_START);
+ cxl_psa_unmap((void *)afu->afu_map);
+ afu->afu_map = NULL;
+ goto err1;
+ }
+
+ afu_err_intr_init(cfg->afu);
+ atomic64_set(&afu->room, readq_be(&afu->host_map->cmd_room));
+
+err1:
+ pr_debug("%s: returning rc=%d\n", __func__, rc);
+ return rc;
+}
+
+/**
+ * cxlflash_send_cmd() - sends an AFU command
+ * @afu: AFU associated with the host.
+ * @cmd: AFU command to send.
+ *
+ * Return:
+ * 0 on success
+ * -1 on failure
+ */
+int cxlflash_send_cmd(struct afu *afu, struct afu_cmd *cmd)
+{
+ struct cxlflash_cfg *cfg = afu->parent;
+ int nretry = 0;
+ int rc = 0;
+ u64 room;
+ long newval;
+
+ /*
+ * This routine is used by critical users such an AFU sync and to
+ * send a task management function (TMF). Thus we want to retry a
+ * bit before returning an error. To avoid the performance penalty
+ * of MMIO, we spread the update of 'room' over multiple commands.
+ */
+retry:
+ newval = atomic64_dec_if_positive(&afu->room);
+ if (!newval) {
+ do {
+ room = readq_be(&afu->host_map->cmd_room);
+ atomic64_set(&afu->room, room);
+ if (room)
+ goto write_ioarrin;
+ udelay(nretry);
+ } while (nretry++ < MC_ROOM_RETRY_CNT);
+
+ pr_err("%s: no cmd_room to send 0x%X\n",
+ __func__, cmd->rcb.cdb[0]);
+
+ goto no_room;
+ } else if (unlikely(newval < 0)) {
+ /* This should be rare. i.e. Only if two threads race and
+ * decrement before the MMIO read is done. In this case
+ * just benefit from the other thread having updated
+ * afu->room.
+ */
+ if (nretry++ < MC_ROOM_RETRY_CNT) {
+ udelay(nretry);
+ goto retry;
+ }
+
+ goto no_room;
+ }
+
+write_ioarrin:
+ writeq_be((u64)&cmd->rcb, &afu->host_map->ioarrin);
+out:
+ pr_debug("%s: cmd=%p len=%d ea=%p rc=%d\n", __func__, cmd,
+ cmd->rcb.data_len, (void *)cmd->rcb.data_ea, rc);
+ return rc;
+
+no_room:
+ afu->read_room = true;
+ schedule_work(&cfg->work_q);
+ rc = SCSI_MLQUEUE_HOST_BUSY;
+ goto out;
+}
+
+/**
+ * cxlflash_wait_resp() - polls for a response or timeout to a sent AFU command
+ * @afu: AFU associated with the host.
+ * @cmd: AFU command that was sent.
+ */
+void cxlflash_wait_resp(struct afu *afu, struct afu_cmd *cmd)
+{
+ ulong timeout = jiffies + (cmd->rcb.timeout * 2 * HZ);
+
+ timeout = wait_for_completion_timeout(&cmd->cevent, timeout);
+ if (!timeout)
+ cxlflash_context_reset(cmd);
+
+ if (unlikely(cmd->sa.ioasc != 0))
+ pr_err("%s: CMD 0x%X failed, IOASC: flags 0x%X, afu_rc 0x%X, "
+ "scsi_rc 0x%X, fc_rc 0x%X\n", __func__, cmd->rcb.cdb[0],
+ cmd->sa.rc.flags, cmd->sa.rc.afu_rc, cmd->sa.rc.scsi_rc,
+ cmd->sa.rc.fc_rc);
+}
+
+/**
+ * cxlflash_afu_sync() - builds and sends an AFU sync command
+ * @afu: AFU associated with the host.
+ * @ctx_hndl_u: Identifies context requesting sync.
+ * @res_hndl_u: Identifies resource requesting sync.
+ * @mode: Type of sync to issue (lightweight, heavyweight, global).
+ *
+ * The AFU can only take 1 sync command at a time. This routine enforces this
+ * limitation by using a mutex to provide exlusive access to the AFU during
+ * the sync. This design point requires calling threads to not be on interrupt
+ * context due to the possibility of sleeping during concurrent sync operations.
+ *
+ * Return:
+ * 0 on success
+ * -1 on failure
+ */
+int cxlflash_afu_sync(struct afu *afu, ctx_hndl_t ctx_hndl_u,
+ res_hndl_t res_hndl_u, u8 mode)
+{
+ struct afu_cmd *cmd = NULL;
+ int rc = 0;
+ int retry_cnt = 0;
+ static DEFINE_MUTEX(sync_active);
+
+ mutex_lock(&sync_active);
+retry:
+ cmd = cxlflash_cmd_checkout(afu);
+ if (unlikely(!cmd)) {
+ retry_cnt++;
+ udelay(1000 * retry_cnt);
+ if (retry_cnt < MC_RETRY_CNT)
+ goto retry;
+ pr_err("%s: could not get a free command\n", __func__);
+ rc = -1;
+ goto out;
+ }
+
+ pr_debug("%s: afu=%p cmd=%p %d\n", __func__, afu, cmd, ctx_hndl_u);
+
+ memset(cmd->rcb.cdb, 0, sizeof(cmd->rcb.cdb));
+
+ cmd->rcb.req_flags = SISL_REQ_FLAGS_AFU_CMD;
+ cmd->rcb.port_sel = 0x0; /* NA */
+ cmd->rcb.lun_id = 0x0; /* NA */
+ cmd->rcb.data_len = 0x0;
+ cmd->rcb.data_ea = 0x0;
+ cmd->rcb.timeout = MC_AFU_SYNC_TIMEOUT;
+
+ cmd->rcb.cdb[0] = 0xC0; /* AFU Sync */
+ cmd->rcb.cdb[1] = mode;
+
+ /* The cdb is aligned, no unaligned accessors required */
+ *((u16 *)&cmd->rcb.cdb[2]) = swab16(ctx_hndl_u);
+ *((u32 *)&cmd->rcb.cdb[4]) = swab32(res_hndl_u);
+
+ rc = cxlflash_send_cmd(afu, cmd);
+ if (unlikely(rc))
+ goto out;
+
+ cxlflash_wait_resp(afu, cmd);
+
+ /* set on timeout */
+ if (unlikely((cmd->sa.ioasc != 0) ||
+ (cmd->sa.host_use_b[0] & B_ERROR)))
+ rc = -1;
+out:
+ mutex_unlock(&sync_active);
+ if (cmd)
+ cxlflash_cmd_checkin(cmd);
+ pr_debug("%s: returning rc=%d\n", __func__, rc);
+ return rc;
+}
+
+/**
+ * cxlflash_afu_reset() - resets the AFU
+ * @cxlflash: Internal structure associated with the host.
+ *
+ * Return:
+ * 0 on success
+ * A failure value from internal services.
+ */
+int cxlflash_afu_reset(struct cxlflash_cfg *cfg)
+{
+ int rc = 0;
+ /* Stop the context before the reset. Since the context is
+ * no longer available restart it after the reset is complete
+ */
+
+ term_afu(cfg);
+
+ rc = init_afu(cfg);
+
+ pr_debug("%s: returning rc=%d\n", __func__, rc);
+ return rc;
+}
+
+/**
+ * cxlflash_worker_thread() - work thread handler for the AFU
+ * @work: Work structure contained within cxlflash associated with host.
+ *
+ * Handles the following events:
+ * - Link reset which cannot be performed on interrupt context due to
+ * blocking up to a few seconds
+ * - Read AFU command room
+ */
+static void cxlflash_worker_thread(struct work_struct *work)
+{
+ struct cxlflash_cfg *cfg =
+ container_of(work, struct cxlflash_cfg, work_q);
+ struct afu *afu = cfg->afu;
+ int port;
+ ulong lock_flags;
+
+ spin_lock_irqsave(cfg->host->host_lock, lock_flags);
+
+ if (cfg->lr_state == LINK_RESET_REQUIRED) {
+ port = cfg->lr_port;
+ if (port < 0)
+ pr_err("%s: invalid port index %d\n", __func__, port);
+ else {
+ spin_unlock_irqrestore(cfg->host->host_lock,
+ lock_flags);
+
+ /* The reset can block... */
+ afu_link_reset(afu, port,
+ &afu->afu_map->
+ global.fc_regs[port][0]);
+ spin_lock_irqsave(cfg->host->host_lock, lock_flags);
+ }
+
+ cfg->lr_state = LINK_RESET_COMPLETE;
+ }
+
+ if (afu->read_room) {
+ atomic64_set(&afu->room, readq_be(&afu->host_map->cmd_room));
+ afu->read_room = false;
+ }
+
+ spin_unlock_irqrestore(cfg->host->host_lock, lock_flags);
+}
+
+/**
+ * cxlflash_probe() - PCI entry point to add host
+ * @pdev: PCI device associated with the host.
+ * @dev_id: PCI device id associated with device.
+ *
+ * Return: 0 on success / non-zero on failure
+ */
+static int cxlflash_probe(struct pci_dev *pdev,
+ const struct pci_device_id *dev_id)
+{
+ struct Scsi_Host *host;
+ struct cxlflash_cfg *cfg = NULL;
+ struct device *phys_dev;
+ struct dev_dependent_vals *ddv;
+ int rc = 0;
+
+ dev_dbg(&pdev->dev, "%s: Found CXLFLASH with IRQ: %d\n",
+ __func__, pdev->irq);
+
+ ddv = (struct dev_dependent_vals *)dev_id->driver_data;
+ driver_template.max_sectors = ddv->max_sectors;
+
+ host = scsi_host_alloc(&driver_template, sizeof(struct cxlflash_cfg));
+ if (!host) {
+ dev_err(&pdev->dev, "%s: call to scsi_host_alloc failed!\n",
+ __func__);
+ rc = -ENOMEM;
+ goto out;
+ }
+
+ host->max_id = CXLFLASH_MAX_NUM_TARGETS_PER_BUS;
+ host->max_lun = CXLFLASH_MAX_NUM_LUNS_PER_TARGET;
+ host->max_channel = NUM_FC_PORTS - 1;
+ host->unique_id = host->host_no;
+ host->max_cmd_len = CXLFLASH_MAX_CDB_LEN;
+
+ cfg = (struct cxlflash_cfg *)host->hostdata;
+ cfg->host = host;
+ rc = alloc_mem(cfg);
+ if (rc) {
+ dev_err(&pdev->dev, "%s: call to scsi_host_alloc failed!\n",
+ __func__);
+ rc = -ENOMEM;
+ goto out;
+ }
+
+ cfg->init_state = INIT_STATE_NONE;
+ cfg->dev = pdev;
+ cfg->dev_id = (struct pci_device_id *)dev_id;
+ cfg->mcctx = NULL;
+ cfg->err_recovery_active = 0;
+
+ init_waitqueue_head(&cfg->tmf_waitq);
+ init_waitqueue_head(&cfg->eeh_waitq);
+
+ INIT_WORK(&cfg->work_q, cxlflash_worker_thread);
+ cfg->lr_state = LINK_RESET_INVALID;
+ cfg->lr_port = -1;
+
+ pci_set_drvdata(pdev, cfg);
+
+ /* Use the special service provided to look up the physical
+ * PCI device, since we are called on the probe of the virtual
+ * PCI host bus (vphb)
+ */
+ phys_dev = cxl_get_phys_dev(pdev);
+ if (!dev_is_pci(phys_dev)) {
+ pr_err("%s: not a pci dev\n", __func__);
+ rc = -ENODEV;
+ goto out_remove;
+ }
+ cfg->parent_dev = to_pci_dev(phys_dev);
+
+ cfg->cxl_afu = cxl_pci_to_afu(pdev);
+
+ rc = init_pci(cfg);
+ if (rc) {
+ dev_err(&pdev->dev, "%s: call to init_pci "
+ "failed rc=%d!\n", __func__, rc);
+ goto out_remove;
+ }
+ cfg->init_state = INIT_STATE_PCI;
+
+ rc = init_afu(cfg);
+ if (rc) {
+ dev_err(&pdev->dev, "%s: call to init_afu "
+ "failed rc=%d!\n", __func__, rc);
+ goto out_remove;
+ }
+ cfg->init_state = INIT_STATE_AFU;
+
+
+ rc = init_scsi(cfg);
+ if (rc) {
+ dev_err(&pdev->dev, "%s: call to init_scsi "
+ "failed rc=%d!\n", __func__, rc);
+ goto out_remove;
+ }
+ cfg->init_state = INIT_STATE_SCSI;
+
+out:
+ pr_debug("%s: returning rc=%d\n", __func__, rc);
+ return rc;
+
+out_remove:
+ cxlflash_remove(pdev);
+ goto out;
+}
+
+/*
+ * PCI device structure
+ */
+static struct pci_driver cxlflash_driver = {
+ .name = CXLFLASH_NAME,
+ .id_table = cxlflash_pci_table,
+ .probe = cxlflash_probe,
+ .remove = cxlflash_remove,
+};
+
+/**
+ * init_cxlflash() - module entry point
+ *
+ * Return: 0 on success / non-zero on failure
+ */
+static int __init init_cxlflash(void)
+{
+ pr_info("%s: IBM Power CXL Flash Adapter: %s\n",
+ __func__, CXLFLASH_DRIVER_DATE);
+
+ return pci_register_driver(&cxlflash_driver);
+}
+
+/**
+ * exit_cxlflash() - module exit point
+ */
+static void __exit exit_cxlflash(void)
+{
+ pci_unregister_driver(&cxlflash_driver);
+}
+
+module_init(init_cxlflash);
+module_exit(exit_cxlflash);
new file mode 100644
@@ -0,0 +1,104 @@
+/*
+ * CXL Flash Device Driver
+ *
+ * Written by: Manoj N. Kumar <manoj@linux.vnet.ibm.com>, IBM Corporation
+ * Matthew R. Ochs <mrochs@linux.vnet.ibm.com>, IBM Corporation
+ *
+ * Copyright (C) 2015 IBM Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _CXLFLASH_MAIN_H
+#define _CXLFLASH_MAIN_H
+
+#include <linux/list.h>
+#include <linux/types.h>
+#include <scsi/scsi.h>
+#include <scsi/scsi_device.h>
+
+#define CXLFLASH_NAME "cxlflash"
+#define CXLFLASH_ADAPTER_NAME "IBM POWER CXL Flash Adapter"
+#define CXLFLASH_DRIVER_DATE "(June 2, 2015)"
+
+#define PCI_DEVICE_ID_IBM_CORSA 0x04F0
+#define CXLFLASH_SUBS_DEV_ID 0x04F0
+
+/* Since there is only one target, make it 0 */
+#define CXLFLASH_TARGET 0
+#define CXLFLASH_MAX_CDB_LEN 16
+
+/* Really only one target per bus since the Texan is directly attached */
+#define CXLFLASH_MAX_NUM_TARGETS_PER_BUS 1
+#define CXLFLASH_MAX_NUM_LUNS_PER_TARGET 65536
+
+#define CXLFLASH_PCI_ERROR_RECOVERY_TIMEOUT (120 * HZ)
+
+#define NUM_FC_PORTS CXLFLASH_NUM_FC_PORTS /* ports per AFU */
+
+/* FC defines */
+#define FC_MTIP_CMDCONFIG 0x010
+#define FC_MTIP_STATUS 0x018
+
+#define FC_PNAME 0x300
+#define FC_CONFIG 0x320
+#define FC_CONFIG2 0x328
+#define FC_STATUS 0x330
+#define FC_ERROR 0x380
+#define FC_ERRCAP 0x388
+#define FC_ERRMSK 0x390
+#define FC_CNT_CRCERR 0x538
+#define FC_CRC_THRESH 0x580
+
+#define FC_MTIP_CMDCONFIG_ONLINE 0x20ULL
+#define FC_MTIP_CMDCONFIG_OFFLINE 0x40ULL
+
+#define FC_MTIP_STATUS_MASK 0x30ULL
+#define FC_MTIP_STATUS_ONLINE 0x20ULL
+#define FC_MTIP_STATUS_OFFLINE 0x10ULL
+
+/* TIMEOUT and RETRY definitions */
+
+/* AFU command timeout values */
+#define MC_AFU_SYNC_TIMEOUT 5 /* 5 secs */
+
+/* AFU command room retry limit */
+#define MC_ROOM_RETRY_CNT 10
+
+/* FC CRC clear periodic timer */
+#define MC_CRC_THRESH 100 /* threshold in 5 mins */
+
+#define FC_PORT_STATUS_RETRY_CNT 100 /* 100 100ms retries = 10 seconds */
+#define FC_PORT_STATUS_RETRY_INTERVAL_US 100000 /* microseconds */
+
+/* VPD defines */
+#define CXLFLASH_VPD_LEN 256
+#define WWPN_LEN 16
+#define WWPN_BUF_LEN (WWPN_LEN + 1)
+
+enum undo_level {
+ RELEASE_CONTEXT = 0,
+ FREE_IRQ,
+ UNMAP_ONE,
+ UNMAP_TWO,
+ UNMAP_THREE,
+ UNDO_START
+};
+
+struct dev_dependent_vals {
+ u64 max_sectors;
+};
+
+struct asyc_intr_info {
+ u64 status;
+ char *desc;
+ u8 port;
+ u8 action;
+#define CLR_FC_ERROR 0x01
+#define LINK_RESET 0x02
+};
+
+#endif /* _CXLFLASH_MAIN_H */
new file mode 100755
@@ -0,0 +1,465 @@
+/*
+ * CXL Flash Device Driver
+ *
+ * Written by: Manoj N. Kumar <manoj@linux.vnet.ibm.com>, IBM Corporation
+ * Matthew R. Ochs <mrochs@linux.vnet.ibm.com>, IBM Corporation
+ *
+ * Copyright (C) 2015 IBM Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _SISLITE_H
+#define _SISLITE_H
+
+#include <linux/types.h>
+
+typedef u16 ctx_hndl_t;
+typedef u32 res_hndl_t;
+
+#define SIZE_4K 4096
+#define SIZE_64K 65536
+
+/*
+ * IOARCB: 64 bytes, min 16 byte alignment required, host native endianness
+ * except for SCSI CDB which remains big endian per SCSI standards.
+ */
+struct sisl_ioarcb {
+ u16 ctx_id; /* ctx_hndl_t */
+ u16 req_flags;
+#define SISL_REQ_FLAGS_RES_HNDL 0x8000U /* bit 0 (MSB) */
+#define SISL_REQ_FLAGS_PORT_LUN_ID 0x0000U
+
+#define SISL_REQ_FLAGS_SUP_UNDERRUN 0x4000U /* bit 1 */
+
+#define SISL_REQ_FLAGS_TIMEOUT_SECS 0x0000U /* bits 8,9 */
+#define SISL_REQ_FLAGS_TIMEOUT_MSECS 0x0040U
+#define SISL_REQ_FLAGS_TIMEOUT_USECS 0x0080U
+#define SISL_REQ_FLAGS_TIMEOUT_CYCLES 0x00C0U
+
+#define SISL_REQ_FLAGS_TMF_CMD 0x0004u /* bit 13 */
+
+#define SISL_REQ_FLAGS_AFU_CMD 0x0002U /* bit 14 */
+
+#define SISL_REQ_FLAGS_HOST_WRITE 0x0001U /* bit 15 (LSB) */
+#define SISL_REQ_FLAGS_HOST_READ 0x0000U
+
+ union {
+ u32 res_hndl; /* res_hndl_t */
+ u32 port_sel; /* this is a selection mask:
+ * 0x1 -> port#0 can be selected,
+ * 0x2 -> port#1 can be selected.
+ * Can be bitwise ORed.
+ */
+ };
+ u64 lun_id;
+ u32 data_len; /* 4K for read/write */
+ u32 ioadl_len;
+ union {
+ u64 data_ea; /* min 16 byte aligned */
+ u64 ioadl_ea;
+ };
+ u8 msi; /* LISN to send on RRQ write */
+#define SISL_MSI_CXL_PFAULT 0 /* reserved for CXL page faults */
+#define SISL_MSI_SYNC_ERROR 1 /* recommended for AFU sync error */
+#define SISL_MSI_RRQ_UPDATED 2 /* recommended for IO completion */
+#define SISL_MSI_ASYNC_ERROR 3 /* master only - for AFU async error */
+
+ u8 rrq; /* 0 for a single RRQ */
+ u16 timeout; /* in units specified by req_flags */
+ u32 rsvd1;
+ u8 cdb[16]; /* must be in big endian */
+ struct scsi_cmnd *scp;
+} __packed;
+
+struct sisl_rc {
+ u8 flags;
+#define SISL_RC_FLAGS_SENSE_VALID 0x80U
+#define SISL_RC_FLAGS_FCP_RSP_CODE_VALID 0x40U
+#define SISL_RC_FLAGS_OVERRUN 0x20U
+#define SISL_RC_FLAGS_UNDERRUN 0x10U
+
+ u8 afu_rc;
+#define SISL_AFU_RC_RHT_INVALID 0x01U /* user error */
+#define SISL_AFU_RC_RHT_UNALIGNED 0x02U /* should never happen */
+#define SISL_AFU_RC_RHT_OUT_OF_BOUNDS 0x03u /* user error */
+#define SISL_AFU_RC_RHT_DMA_ERR 0x04u /* see afu_extra
+ may retry if afu_retry is off
+ possible on master exit
+ */
+#define SISL_AFU_RC_RHT_RW_PERM 0x05u /* no RW perms, user error */
+#define SISL_AFU_RC_LXT_UNALIGNED 0x12U /* should never happen */
+#define SISL_AFU_RC_LXT_OUT_OF_BOUNDS 0x13u /* user error */
+#define SISL_AFU_RC_LXT_DMA_ERR 0x14u /* see afu_extra
+ may retry if afu_retry is off
+ possible on master exit
+ */
+#define SISL_AFU_RC_LXT_RW_PERM 0x15u /* no RW perms, user error */
+
+#define SISL_AFU_RC_NOT_XLATE_HOST 0x1au /* possible if master exited */
+
+ /* NO_CHANNELS means the FC ports selected by dest_port in
+ * IOARCB or in the LXT entry are down when the AFU tried to select
+ * a FC port. If the port went down on an active IO, it will set
+ * fc_rc to =0x54(NOLOGI) or 0x57(LINKDOWN) instead.
+ */
+#define SISL_AFU_RC_NO_CHANNELS 0x20U /* see afu_extra, may retry */
+#define SISL_AFU_RC_CAP_VIOLATION 0x21U /* either user error or
+ afu reset/master restart
+ */
+#define SISL_AFU_RC_OUT_OF_DATA_BUFS 0x30U /* always retry */
+#define SISL_AFU_RC_DATA_DMA_ERR 0x31U /* see afu_extra
+ may retry if afu_retry is off
+ */
+
+ u8 scsi_rc; /* SCSI status byte, retry as appropriate */
+#define SISL_SCSI_RC_CHECK 0x02U
+#define SISL_SCSI_RC_BUSY 0x08u
+
+ u8 fc_rc; /* retry */
+ /*
+ * We should only see fc_rc=0x57 (LINKDOWN) or 0x54(NOLOGI) for
+ * commands that are in flight when a link goes down or is logged out.
+ * If the link is down or logged out before AFU selects the port, either
+ * it will choose the other port or we will get afu_rc=0x20 (no_channel)
+ * if there is no valid port to use.
+ *
+ * ABORTPEND/ABORTOK/ABORTFAIL/TGTABORT can be retried, typically these
+ * would happen if a frame is dropped and something times out.
+ * NOLOGI or LINKDOWN can be retried if the other port is up.
+ * RESIDERR can be retried as well.
+ *
+ * ABORTFAIL might indicate that lots of frames are getting CRC errors.
+ * So it maybe retried once and reset the link if it happens again.
+ * The link can also be reset on the CRC error threshold interrupt.
+ */
+#define SISL_FC_RC_ABORTPEND 0x52 /* exchange timeout or abort request */
+#define SISL_FC_RC_WRABORTPEND 0x53 /* due to write XFER_RDY invalid */
+#define SISL_FC_RC_NOLOGI 0x54 /* port not logged in, in-flight cmds */
+#define SISL_FC_RC_NOEXP 0x55 /* FC protocol error or HW bug */
+#define SISL_FC_RC_INUSE 0x56 /* tag already in use, HW bug */
+#define SISL_FC_RC_LINKDOWN 0x57 /* link down, in-flight cmds */
+#define SISL_FC_RC_ABORTOK 0x58 /* pending abort completed w/success */
+#define SISL_FC_RC_ABORTFAIL 0x59 /* pending abort completed w/fail */
+#define SISL_FC_RC_RESID 0x5A /* ioasa underrun/overrun flags set */
+#define SISL_FC_RC_RESIDERR 0x5B /* actual data len does not match SCSI
+ reported len, possbly due to dropped
+ frames */
+#define SISL_FC_RC_TGTABORT 0x5C /* command aborted by target */
+};
+
+#define SISL_SENSE_DATA_LEN 20 /* Sense data length */
+
+/*
+ * IOASA: 64 bytes & must follow IOARCB, min 16 byte alignment required,
+ * host native endianness
+ */
+struct sisl_ioasa {
+ union {
+ struct sisl_rc rc;
+ u32 ioasc;
+#define SISL_IOASC_GOOD_COMPLETION 0x00000000U
+ };
+ u32 resid;
+ u8 port;
+ u8 afu_extra;
+ /* when afu_rc=0x04, 0x14, 0x31 (_xxx_DMA_ERR):
+ * afu_exta contains PSL response code. Useful codes are:
+ */
+#define SISL_AFU_DMA_ERR_PAGE_IN 0x0A /* AFU_retry_on_pagein Action
+ * Enabled N/A
+ * Disabled retry
+ */
+#define SISL_AFU_DMA_ERR_INVALID_EA 0x0B /* this is a hard error
+ * afu_rc Implies
+ * 0x04, 0x14 master exit.
+ * 0x31 user error.
+ */
+ /* when afu rc=0x20 (no channels):
+ * afu_extra bits [4:5]: available portmask, [6:7]: requested portmask.
+ */
+#define SISL_AFU_NO_CLANNELS_AMASK(afu_extra) (((afu_extra) & 0x0C) >> 2)
+#define SISL_AFU_NO_CLANNELS_RMASK(afu_extra) ((afu_extra) & 0x03)
+
+ u8 scsi_extra;
+ u8 fc_extra;
+ u8 sense_data[SISL_SENSE_DATA_LEN];
+
+ /* These fields are defined by the SISlite architecture for the
+ * host to use as they see fit for their implementation.
+ */
+ union {
+ u64 host_use[4];
+ u8 host_use_b[32];
+ };
+} __packed;
+
+#define SISL_RESP_HANDLE_T_BIT 0x1ULL /* Toggle bit */
+
+/* MMIO space is required to support only 64-bit access */
+
+/*
+ * This AFU has two mechanisms to deal with endian-ness.
+ * One is a global configuration (in the afu_config) register
+ * below that specifies the endian-ness of the host.
+ * The other is a per context (i.e. application) specification
+ * controlled by the endian_ctrl field here. Since the master
+ * context is one such application the master context's
+ * endian-ness is set to be the same as the host.
+ *
+ * As per the SISlite spec, the MMIO registers are always
+ * big endian.
+ */
+#define SISL_ENDIAN_CTRL_BE 0x8000000000000080ULL
+#define SISL_ENDIAN_CTRL_LE 0x0000000000000000ULL
+
+#ifdef __BIG_ENDIAN
+#define SISL_ENDIAN_CTRL SISL_ENDIAN_CTRL_BE
+#else
+#define SISL_ENDIAN_CTRL SISL_ENDIAN_CTRL_LE
+#endif
+
+/* per context host transport MMIO */
+struct sisl_host_map {
+ __be64 endian_ctrl; /* Per context Endian Control. The AFU will
+ * operate on whatever the context is of the
+ * host application.
+ */
+
+ __be64 intr_status; /* this sends LISN# programmed in ctx_ctrl.
+ * Only recovery in a PERM_ERR is a context
+ * exit since there is no way to tell which
+ * command caused the error.
+ */
+#define SISL_ISTATUS_PERM_ERR_CMDROOM 0x0010ULL /* b59, user error */
+#define SISL_ISTATUS_PERM_ERR_RCB_READ 0x0008ULL /* b60, user error */
+#define SISL_ISTATUS_PERM_ERR_SA_WRITE 0x0004ULL /* b61, user error */
+#define SISL_ISTATUS_PERM_ERR_RRQ_WRITE 0x0002ULL /* b62, user error */
+ /* Page in wait accessing RCB/IOASA/RRQ is reported in b63.
+ * Same error in data/LXT/RHT access is reported via IOASA.
+ */
+#define SISL_ISTATUS_TEMP_ERR_PAGEIN 0x0001ULL /* b63, can be generated
+ * only when AFU auto
+ * retry is disabled.
+ * If user can determine
+ * the command that
+ * caused the error, it
+ * can be retried.
+ */
+#define SISL_ISTATUS_UNMASK (0x001FULL) /* 1 means unmasked */
+#define SISL_ISTATUS_MASK ~(SISL_ISTATUS_UNMASK) /* 1 means masked */
+
+ __be64 intr_clear;
+ __be64 intr_mask;
+ __be64 ioarrin; /* only write what cmd_room permits */
+ __be64 rrq_start; /* start & end are both inclusive */
+ __be64 rrq_end; /* write sequence: start followed by end */
+ __be64 cmd_room;
+ __be64 ctx_ctrl; /* least signiifcant byte or b56:63 is LISN# */
+ __be64 mbox_w; /* restricted use */
+};
+
+/* per context provisioning & control MMIO */
+struct sisl_ctrl_map {
+ __be64 rht_start;
+ __be64 rht_cnt_id;
+ /* both cnt & ctx_id args must be ULL */
+#define SISL_RHT_CNT_ID(cnt, ctx_id) (((cnt) << 48) | ((ctx_id) << 32))
+
+ __be64 ctx_cap; /* afu_rc below is when the capability is violated */
+#define SISL_CTX_CAP_PROXY_ISSUE 0x8000000000000000ULL /* afu_rc 0x21 */
+#define SISL_CTX_CAP_REAL_MODE 0x4000000000000000ULL /* afu_rc 0x21 */
+#define SISL_CTX_CAP_HOST_XLATE 0x2000000000000000ULL /* afu_rc 0x1a */
+#define SISL_CTX_CAP_PROXY_TARGET 0x1000000000000000ULL /* afu_rc 0x21 */
+#define SISL_CTX_CAP_AFU_CMD 0x0000000000000008ULL /* afu_rc 0x21 */
+#define SISL_CTX_CAP_GSCSI_CMD 0x0000000000000004ULL /* afu_rc 0x21 */
+#define SISL_CTX_CAP_WRITE_CMD 0x0000000000000002ULL /* afu_rc 0x21 */
+#define SISL_CTX_CAP_READ_CMD 0x0000000000000001ULL /* afu_rc 0x21 */
+ __be64 mbox_r;
+};
+
+/* single copy global regs */
+struct sisl_global_regs {
+ __be64 aintr_status;
+ /* In cxlflash, each FC port/link gets a byte of status */
+#define SISL_ASTATUS_FC0_OTHER 0x8000ULL /* b48, other err,
+ FC_ERRCAP[31:20] */
+#define SISL_ASTATUS_FC0_LOGO 0x4000ULL /* b49, target sent FLOGI/PLOGI/LOGO
+ while logged in */
+#define SISL_ASTATUS_FC0_CRC_T 0x2000ULL /* b50, CRC threshold exceeded */
+#define SISL_ASTATUS_FC0_LOGI_R 0x1000ULL /* b51, login state mechine timed out
+ and retrying */
+#define SISL_ASTATUS_FC0_LOGI_F 0x0800ULL /* b52, login failed,
+ FC_ERROR[19:0] */
+#define SISL_ASTATUS_FC0_LOGI_S 0x0400ULL /* b53, login succeeded */
+#define SISL_ASTATUS_FC0_LINK_DN 0x0200ULL /* b54, link online to offline */
+#define SISL_ASTATUS_FC0_LINK_UP 0x0100ULL /* b55, link offline to online */
+
+#define SISL_ASTATUS_FC1_OTHER 0x0080ULL /* b56 */
+#define SISL_ASTATUS_FC1_LOGO 0x0040ULL /* b57 */
+#define SISL_ASTATUS_FC1_CRC_T 0x0020ULL /* b58 */
+#define SISL_ASTATUS_FC1_LOGI_R 0x0010ULL /* b59 */
+#define SISL_ASTATUS_FC1_LOGI_F 0x0008ULL /* b60 */
+#define SISL_ASTATUS_FC1_LOGI_S 0x0004ULL /* b61 */
+#define SISL_ASTATUS_FC1_LINK_DN 0x0002ULL /* b62 */
+#define SISL_ASTATUS_FC1_LINK_UP 0x0001ULL /* b63 */
+
+#define SISL_FC_INTERNAL_UNMASK 0x0000000300000000ULL /* 1 means unmasked */
+#define SISL_FC_INTERNAL_MASK ~(SISL_FC_INTERNAL_UNMASK)
+#define SISL_FC_INTERNAL_SHIFT 32
+
+#define SISL_ASTATUS_UNMASK 0xFFFFULL /* 1 means unmasked */
+#define SISL_ASTATUS_MASK ~(SISL_ASTATUS_UNMASK) /* 1 means masked */
+
+ __be64 aintr_clear;
+ __be64 aintr_mask;
+ __be64 afu_ctrl;
+ __be64 afu_hb;
+ __be64 afu_scratch_pad;
+ __be64 afu_port_sel;
+#define SISL_AFUCONF_AR_IOARCB 0x4000ULL
+#define SISL_AFUCONF_AR_LXT 0x2000ULL
+#define SISL_AFUCONF_AR_RHT 0x1000ULL
+#define SISL_AFUCONF_AR_DATA 0x0800ULL
+#define SISL_AFUCONF_AR_RSRC 0x0400ULL
+#define SISL_AFUCONF_AR_IOASA 0x0200ULL
+#define SISL_AFUCONF_AR_RRQ 0x0100ULL
+/* Aggregate all Auto Retry Bits */
+#define SISL_AFUCONF_AR_ALL (SISL_AFUCONF_AR_IOARCB|SISL_AFUCONF_AR_LXT| \
+ SISL_AFUCONF_AR_RHT|SISL_AFUCONF_AR_DATA| \
+ SISL_AFUCONF_AR_RSRC|SISL_AFUCONF_AR_IOASA| \
+ SISL_AFUCONF_AR_RRQ)
+#ifdef __BIG_ENDIAN
+#define SISL_AFUCONF_ENDIAN 0x0000ULL
+#else
+#define SISL_AFUCONF_ENDIAN 0x0020ULL
+#endif
+#define SISL_AFUCONF_MBOX_CLR_READ 0x0010ULL
+ __be64 afu_config;
+ __be64 rsvd[0xf8];
+ __be64 afu_version;
+ __be64 interface_version;
+};
+
+#define CXLFLASH_NUM_FC_PORTS 2
+#define CXLFLASH_MAX_CONTEXT 512 /* how many contexts per afu */
+#define CXLFLASH_NUM_VLUNS 512
+
+struct sisl_global_map {
+ union {
+ struct sisl_global_regs regs;
+ char page0[SIZE_4K]; /* page 0 */
+ };
+
+ char page1[SIZE_4K]; /* page 1 */
+
+ /* pages 2 & 3 */
+ __be64 fc_regs[CXLFLASH_NUM_FC_PORTS][CXLFLASH_NUM_VLUNS];
+
+ /* pages 4 & 5 (lun tbl) */
+ __be64 fc_port[CXLFLASH_NUM_FC_PORTS][CXLFLASH_NUM_VLUNS];
+
+};
+
+/*
+ * CXL Flash Memory Map
+ *
+ * +-------------------------------+
+ * | 512 * 64 KB User MMIO |
+ * | (per context) |
+ * | User Accessible |
+ * +-------------------------------+
+ * | 512 * 128 B per context |
+ * | Provisioning and Control |
+ * | Trusted Process accessible |
+ * +-------------------------------+
+ * | 64 KB Global |
+ * | Trusted Process accessible |
+ * +-------------------------------+
+*/
+struct cxlflash_afu_map {
+ union {
+ struct sisl_host_map host;
+ char harea[SIZE_64K]; /* 64KB each */
+ } hosts[CXLFLASH_MAX_CONTEXT];
+
+ union {
+ struct sisl_ctrl_map ctrl;
+ char carea[cache_line_size()]; /* 128B each */
+ } ctrls[CXLFLASH_MAX_CONTEXT];
+
+ union {
+ struct sisl_global_map global;
+ char garea[SIZE_64K]; /* 64KB single block */
+ };
+};
+
+/* LBA translation control blocks */
+
+struct sisl_lxt_entry {
+ u64 rlba_base; /* bits 0:47 is base
+ * b48:55 is lun index
+ * b58:59 is write & read perms
+ * (if no perm, afu_rc=0x15)
+ * b60:63 is port_sel mask
+ */
+
+};
+
+/* Per the SISlite spec, RHT entries are to be 16-byte aligned */
+struct sisl_rht_entry {
+ struct sisl_lxt_entry *lxt_start;
+ u32 lxt_cnt;
+ u16 rsvd;
+ u8 fp; /* format & perm nibbles.
+ * (if no perm, afu_rc=0x05)
+ */
+ u8 nmask;
+} __packed __aligned(16);
+
+struct sisl_rht_entry_f1 {
+ u64 lun_id;
+ union {
+ struct {
+ u8 valid;
+ u8 rsvd[5];
+ u8 fp;
+ u8 port_sel;
+ };
+
+ u64 dw;
+ };
+} __packed __aligned(16);
+
+/* make the fp byte */
+#define SISL_RHT_FP(fmt, perm) (((fmt) << 4) | (perm))
+
+/* make the fp byte for a clone from a source fp and clone flags
+ * flags must be only 2 LSB bits.
+ */
+#define SISL_RHT_FP_CLONE(src_fp, cln_flags) ((src_fp) & (0xFC | (cln_flags)))
+
+#define RHT_PERM_READ 0x01U
+#define RHT_PERM_WRITE 0x02U
+#define RHT_PERM_RW (RHT_PERM_READ | RHT_PERM_WRITE)
+
+/* extract the perm bits from a fp */
+#define SISL_RHT_PERM(fp) ((fp) & RHT_PERM_RW)
+
+#define PORT0 0x01U
+#define PORT1 0x02U
+#define BOTH_PORTS (PORT0 | PORT1)
+
+/* AFU Sync Mode byte */
+#define AFU_LW_SYNC 0x0U
+#define AFU_HW_SYNC 0x1U
+#define AFU_GSYNC 0x2U
+
+/* Special Task Management Function CDB */
+#define TMF_LUN_RESET 0x1U
+#define TMF_CLEAR_ACA 0x2U
+
+#endif /* _SISLITE_H */