Merge tag 'scsi-misc' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi

Pull SCSI updates from James Bottomley: "First round of SCSI updates for the 4.4 merge window. This batch includes a couple of minor fixes, some core changes to help issues we're still seeing with the suspend/resume code and updates to lpfc and cxlflash. We're (actually Martin Petersen is) trying to wrangle a mpt2/mpt3sas merger for the merge window which will help enormously with the maintenance burden, so there will be another round before it closes" * tag 'scsi-misc' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi: (56 commits) cxlflash: Fix to avoid bypassing context cleanup cxlflash: Fix to avoid lock instrumentation rejection cxlflash: Fix to avoid corrupting port selection mask cxlflash: Fix to escalate to LINK_RESET on login timeout cxlflash: Fix to avoid leaving dangling interrupt resources cxlflash: Fix to avoid potential deadlock on EEH cxlflash: Correct trace string cxlflash: Fix to avoid corrupting adapter fops cxlflash: Fix to double the delay each time MAINTAINERS: Add cxlflash driver cxlflash: Fix to prevent stale AFU RRQ cxlflash: Correct spelling, grammar, and alignment mistakes cxlflash: Fix to prevent EEH recovery failure cxlflash: Fix MMIO and endianness errors cxlflash: Fix function prolog parameters and return codes cxlflash: Remove unnecessary scsi_block_requests cxlflash: Correct behavior in device reset handler following EEH cxlflash: Fix to prevent workq from accessing freed memory cxlflash: Correct usage of scsi_host_put() cxlflash: Fix AFU version access/storage and add check ...
2026-05-01 15:00:59 -07:00 · 2015-11-05 16:20:21 -08:00
parent 39cf7c3981 a82544c7ba
commit a3e7531535
37 changed files with 1317 additions and 1138 deletions
@@ -3186,6 +3186,15 @@ F:	Documentation/powerpc/cxl.txt
 F:	Documentation/powerpc/cxl.txt
 F:	Documentation/ABI/testing/sysfs-class-cxl

+CXLFLASH (IBM Coherent Accelerator Processor Interface CAPI Flash) SCSI DRIVER
+M:	Manoj N. Kumar <manoj@linux.vnet.ibm.com>
+M:	Matthew R. Ochs <mrochs@linux.vnet.ibm.com>
+L:	linux-scsi@vger.kernel.org
+S:	Supported
+F:	drivers/scsi/cxlflash/
+F:	include/uapi/scsi/cxlflash_ioctls.h
+F:	Documentation/powerpc/cxlflash.txt
+
 STMMAC ETHERNET DRIVER
 M:	Giuseppe Cavallaro <peppe.cavallaro@st.com>
 L:	netdev@vger.kernel.org
@@ -9473,8 +9482,8 @@ F:	include/uapi/linux/phantom.h

 SERVER ENGINES 10Gbps iSCSI - BladeEngine 2 DRIVER
 M:	Jayamohan Kallickal <jayamohan.kallickal@avagotech.com>
-M:	Minh Tran <minh.tran@avagotech.com>
-M:	John Soni Jose <sony.john-n@avagotech.com>
+M:	Ketan Mukadam <ketan.mukadam@avagotech.com>
+M:	John Soni Jose <sony.john@avagotech.com>
 L:	linux-scsi@vger.kernel.org
 W:	http://www.avagotech.com
 S:	Supported
@@ -1,9 +1,9 @@
 config BE2ISCSI
-	tristate "ServerEngines' 10Gbps iSCSI - BladeEngine 2"
+	tristate "Emulex 10Gbps iSCSI - BladeEngine 2"
 	depends on PCI && SCSI && NET
 	select SCSI_ISCSI_ATTRS
 	select ISCSI_BOOT_SYSFS

 	help
-	This driver implements the iSCSI functionality for ServerEngines'
+	This driver implements the iSCSI functionality for Emulex
 	10Gbps Storage adapter - BladeEngine 2.
@@ -1,5 +1,5 @@
 #
-# Makefile to build the iSCSI driver for ServerEngine's BladeEngine.
+# Makefile to build the iSCSI driver for Emulex OneConnect.
 #
 #

@@ -1,5 +1,5 @@
 /**
- * Copyright (C) 2005 - 2015 Avago Technologies
+ * Copyright (C) 2005 - 2015 Emulex
 * All rights reserved.
 *
 * This program is free software; you can redistribute it and/or
@@ -10,7 +10,7 @@
 * Contact Information:
 * linux-drivers@avagotech.com
 *
- * Avago Technologies
+ * Emulex
 * 3333 Susan Street
 * Costa Mesa, CA 92626
 */
@@ -1,5 +1,5 @@
 /**
- * Copyright (C) 2005 - 2015 Avago Technologies
+ * Copyright (C) 2005 - 2015 Emulex
 * All rights reserved.
 *
 * This program is free software; you can redistribute it and/or
@@ -10,7 +10,7 @@
 * Contact Information:
 * linux-drivers@avagotech.com
 *
- * Avago Technologies
+ * Emulex
 * 3333 Susan Street
 * Costa Mesa, CA 92626
 */
@@ -1,5 +1,5 @@
 /**
- * Copyright (C) 2005 - 2015 Avago Technologies
+ * Copyright (C) 2005 - 2015 Emulex
 * All rights reserved.
 *
 * This program is free software; you can redistribute it and/or
@@ -10,7 +10,7 @@
 * Contact Information:
 * linux-drivers@avagotech.com
 *
- * Avago Technologies
+ * Emulex
 * 3333 Susan Street
 * Costa Mesa, CA 92626
 */
@@ -1,5 +1,5 @@
 /**
- * Copyright (C) 2005 - 2015 Avago Technologies
+ * Copyright (C) 2005 - 2015 Emulex
 * All rights reserved.
 *
 * This program is free software; you can redistribute it and/or
@@ -12,7 +12,7 @@
 * Contact Information:
 * linux-drivers@avagotech.com
 *
- * Avago Technologies
+ * Emulex
 * 3333 Susan Street
 * Costa Mesa, CA 92626
 */
@@ -1,5 +1,5 @@
 /**
- * Copyright (C) 2005 - 2015 Avago Technologies
+ * Copyright (C) 2005 - 2015 Emulex
 * All rights reserved.
 *
 * This program is free software; you can redistribute it and/or
@@ -12,7 +12,7 @@
 * Contact Information:
 * linux-drivers@avagotech.com
 *
- * Avago Technologies
+ * Emulex
 * 3333 Susan Street
 * Costa Mesa, CA 92626
 */
@@ -50,7 +50,7 @@ static unsigned int enable_msix = 1;

 MODULE_DESCRIPTION(DRV_DESC " " BUILD_STR);
 MODULE_VERSION(BUILD_STR);
-MODULE_AUTHOR("Avago Technologies");
+MODULE_AUTHOR("Emulex Corporation");
 MODULE_LICENSE("GPL");
 module_param(be_iopoll_budget, int, 0);
 module_param(enable_msix, int, 0);
@@ -552,7 +552,7 @@ MODULE_DEVICE_TABLE(pci, beiscsi_pci_id_table);

 static struct scsi_host_template beiscsi_sht = {
 	.module = THIS_MODULE,
-	.name = "Avago Technologies 10Gbe open-iscsi Initiator Driver",
+	.name = "Emulex 10Gbe open-iscsi Initiator Driver",
 	.proc_name = DRV_NAME,
 	.queuecommand = iscsi_queuecommand,
 	.change_queue_depth = scsi_change_queue_depth,
@@ -1,5 +1,5 @@
 /**
- * Copyright (C) 2005 - 2015 Avago Technologies
+ * Copyright (C) 2005 - 2015 Emulex
 * All rights reserved.
 *
 * This program is free software; you can redistribute it and/or
@@ -12,7 +12,7 @@
 * Contact Information:
 * linux-drivers@avagotech.com
 *
- * Avago Technologies
+ * Emulex
 * 3333 Susan Street
 * Costa Mesa, CA 92626
 */
@@ -37,7 +37,7 @@

 #define DRV_NAME		"be2iscsi"
 #define BUILD_STR		"10.6.0.0"
-#define BE_NAME			"Avago Technologies OneConnect" \
+#define BE_NAME			"Emulex OneConnect" \
 				"Open-iSCSI Driver version" BUILD_STR
 #define DRV_DESC		BE_NAME " " "Driver"

@@ -1,5 +1,5 @@
 /**
- * Copyright (C) 2005 - 2015 Avago Technologies
+ * Copyright (C) 2005 - 2015 Emulex
 * All rights reserved.
 *
 * This program is free software; you can redistribute it and/or
@@ -12,7 +12,7 @@
 * Contact Information:
 * linux-drivers@avagotech.com
 *
- * Avago Technologies
+ * Emulex
 * 3333 Susan Street
 * Costa Mesa, CA 92626
 */
@@ -1,5 +1,5 @@
 /**
- * Copyright (C) 2005 - 2015 Avago Technologies
+ * Copyright (C) 2005 - 2015 Emulex
 * All rights reserved.
 *
 * This program is free software; you can redistribute it and/or
@@ -12,7 +12,7 @@
 * Contact Information:
 * linux-drivers@avagotech.com
 *
- * Avago Technologies
+ * Emulex
 * 3333 Susan Street
 * Costa Mesa, CA 92626
 */
@@ -856,7 +856,6 @@ static void bnx2fc_indicate_netevent(void *context, unsigned long event,
 		return;

 	default:
-		printk(KERN_ERR PFX "Unknown netevent %ld", event);
 		return;
 	}

@@ -16,10 +16,12 @@
 #define _CXLFLASH_COMMON_H

 #include <linux/list.h>
+#include <linux/rwsem.h>
 #include <linux/types.h>
 #include <scsi/scsi.h>
 #include <scsi/scsi_device.h>

+extern const struct file_operations cxlflash_cxl_fops;

 #define MAX_CONTEXT  CXLFLASH_MAX_CONTEXT       /* num contexts per afu */

@@ -78,7 +80,7 @@ enum cxlflash_init_state {

 enum cxlflash_state {
 	STATE_NORMAL,	/* Normal running state, everything good */
-	STATE_LIMBO,	/* Limbo running state, trying to reset/recover */
+	STATE_RESET,	/* Reset state, trying to reset/recover */
 	STATE_FAILTERM	/* Failed/terminating state, error out users/threads */
 };

@@ -101,29 +103,28 @@ struct cxlflash_cfg {
 	enum cxlflash_init_state init_state;
 	enum cxlflash_lr_state lr_state;
 	int lr_port;
+	atomic_t scan_host_needed;

 	struct cxl_afu *cxl_afu;
-
-	struct pci_pool *cxlflash_cmd_pool;
 	struct pci_dev *parent_dev;

 	atomic_t recovery_threads;
 	struct mutex ctx_recovery_mutex;
 	struct mutex ctx_tbl_list_mutex;
+	struct rw_semaphore ioctl_rwsem;
 	struct ctx_info *ctx_tbl[MAX_CONTEXT];
 	struct list_head ctx_err_recovery; /* contexts w/ recovery pending */
 	struct file_operations cxl_fops;

-	atomic_t num_user_contexts;
-
 	/* Parameters that are LUN table related */
 	int last_lun_index[CXLFLASH_NUM_FC_PORTS];
 	int promote_lun_index;
 	struct list_head lluns; /* list of llun_info structs */

 	wait_queue_head_t tmf_waitq;
+	spinlock_t tmf_slock;
 	bool tmf_active;
-	wait_queue_head_t limbo_waitq;
+	wait_queue_head_t reset_waitq;
 	enum cxlflash_state state;
 };

@@ -160,9 +161,9 @@ struct afu {

 	/* 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 */
+	struct cxlflash_afu_map __iomem *afu_map;	/* entire MMIO map */
+	struct sisl_host_map __iomem *host_map;		/* MC host map */
+	struct sisl_ctrl_map __iomem *ctrl_map;		/* MC control map */

 	ctx_hndl_t ctx_hndl;	/* master's context handle */
 	u64 *hrrq_start;
@@ -175,7 +176,7 @@ struct afu {
 	u32 cmd_couts;		/* Number of command checkouts */
 	u32 internal_lun;	/* User-desired LUN mode for this AFU */

-	char version[8];
+	char version[16];
 	u64 interface_version;

 	struct cxlflash_cfg *parent; /* Pointer back to parent cxlflash_cfg */
@@ -184,17 +185,12 @@ struct afu {

 static inline u64 lun_to_lunid(u64 lun)
 {
-	u64 lun_id;
+	__be64 lun_id;

 	int_to_scsilun(lun, (struct scsi_lun *)&lun_id);
-	return swab64(lun_id);
+	return be64_to_cpu(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);
 void cxlflash_list_init(void);
 void cxlflash_term_global_luns(void);
@@ -41,7 +41,6 @@ static struct llun_info *create_local(struct scsi_device *sdev, u8 *wwid)
 	}

 	lli->sdev = sdev;
-	lli->newly_created = true;
 	lli->host_no = sdev->host->host_no;
 	lli->in_table = false;

@@ -74,24 +73,19 @@ out:
 }

 /**
- * refresh_local() - find and update local LUN information structure by WWID
+ * lookup_local() - find a local LUN information structure by WWID
 * @cfg:	Internal structure associated with the host.
 * @wwid:	WWID associated with LUN.
 *
- * When the LUN is found, mark it by updating it's newly_created field.
- *
 * Return: Found local lun_info structure on success, NULL on failure
- * If a LUN with the WWID is found in the list, refresh it's state.
 */
-static struct llun_info *refresh_local(struct cxlflash_cfg *cfg, u8 *wwid)
+static struct llun_info *lookup_local(struct cxlflash_cfg *cfg, u8 *wwid)
 {
 	struct llun_info *lli, *temp;

 	list_for_each_entry_safe(lli, temp, &cfg->lluns, list)
-		if (!memcmp(lli->wwid, wwid, DK_CXLFLASH_MANAGE_LUN_WWID_LEN)) {
-			lli->newly_created = false;
+		if (!memcmp(lli->wwid, wwid, DK_CXLFLASH_MANAGE_LUN_WWID_LEN))
 			return lli;
-		}

 	return NULL;
 }
@@ -120,7 +114,8 @@ static struct glun_info *lookup_global(u8 *wwid)
 *
 * The LUN is kept both in a local list (per adapter) and in a global list
 * (across all adapters). Certain attributes of the LUN are local to the
- * adapter (such as index, port selection mask etc.).
+ * adapter (such as index, port selection mask, etc.).
+ *
 * The block allocation map is shared across all adapters (i.e. associated
 * wih the global list). Since different attributes are associated with
 * the per adapter and global entries, allocate two separate structures for each
@@ -128,6 +123,8 @@ static struct glun_info *lookup_global(u8 *wwid)
 *
 * Keep a pointer back from the local to the global entry.
 *
+ * This routine assumes the caller holds the global mutex.
+ *
 * Return: Found/Allocated local lun_info structure on success, NULL on failure
 */
 static struct llun_info *find_and_create_lun(struct scsi_device *sdev, u8 *wwid)
@@ -137,11 +134,10 @@ static struct llun_info *find_and_create_lun(struct scsi_device *sdev, u8 *wwid)
 	struct Scsi_Host *shost = sdev->host;
 	struct cxlflash_cfg *cfg = shost_priv(shost);

-	mutex_lock(&global.mutex);
 	if (unlikely(!wwid))
 		goto out;

-	lli = refresh_local(cfg, wwid);
+	lli = lookup_local(cfg, wwid);
 	if (lli)
 		goto out;

@@ -169,7 +165,6 @@ static struct llun_info *find_and_create_lun(struct scsi_device *sdev, u8 *wwid)
 	list_add(&gli->list, &global.gluns);

 out:
-	mutex_unlock(&global.mutex);
 	pr_debug("%s: returning %p\n", __func__, lli);
 	return lli;
 }
@@ -235,10 +230,11 @@ int cxlflash_manage_lun(struct scsi_device *sdev,
 	u64 flags = manage->hdr.flags;
 	u32 chan = sdev->channel;

+	mutex_lock(&global.mutex);
 	lli = find_and_create_lun(sdev, manage->wwid);
 	pr_debug("%s: ENTER: WWID = %016llX%016llX, flags = %016llX li = %p\n",
-		 __func__, get_unaligned_le64(&manage->wwid[0]),
-		 get_unaligned_le64(&manage->wwid[8]),
+		 __func__, get_unaligned_be64(&manage->wwid[0]),
+		 get_unaligned_be64(&manage->wwid[8]),
 		 manage->hdr.flags, lli);
 	if (unlikely(!lli)) {
 		rc = -ENOMEM;
@@ -246,21 +242,28 @@ int cxlflash_manage_lun(struct scsi_device *sdev,
 	}

 	if (flags & DK_CXLFLASH_MANAGE_LUN_ENABLE_SUPERPIPE) {
-		if (lli->newly_created)
-			lli->port_sel = CHAN2PORT(chan);
-		else
-			lli->port_sel = BOTH_PORTS;
-		/* Store off lun in unpacked, AFU-friendly format */
+		/*
+		 * Update port selection mask based upon channel, store off LUN
+		 * in unpacked, AFU-friendly format, and hang LUN reference in
+		 * the sdev.
+		 */
+		lli->port_sel |= CHAN2PORT(chan);
 		lli->lun_id[chan] = lun_to_lunid(sdev->lun);
 		sdev->hostdata = lli;
 	} else if (flags & DK_CXLFLASH_MANAGE_LUN_DISABLE_SUPERPIPE) {
 		if (lli->parent->mode != MODE_NONE)
 			rc = -EBUSY;
-		else
+		else {
 			sdev->hostdata = NULL;
+			lli->port_sel &= ~CHAN2PORT(chan);
+		}
 	}

+	pr_debug("%s: port_sel = %08X chan = %u lun_id = %016llX\n", __func__,
+		 lli->port_sel, chan, lli->lun_id[chan]);
+
 out:
+	mutex_unlock(&global.mutex);
 	pr_debug("%s: returning rc=%d\n", __func__, rc);
 	return rc;
 }
@@ -99,6 +99,7 @@ struct asyc_intr_info {
 	u8 action;
 #define CLR_FC_ERROR	0x01
 #define LINK_RESET	0x02
+#define SCAN_HOST	0x04
 };

 #ifndef CONFIG_CXL_EEH
@@ -146,7 +146,7 @@ struct sisl_rc {
 #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
+					   reported len, possibly due to dropped
 					   frames */
 #define SISL_FC_RC_TGTABORT	0x5C	/* command aborted by target */
 };
@@ -258,7 +258,7 @@ struct sisl_host_map {
 	__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 ctx_ctrl;	/* least significant byte or b56:63 is LISN# */
 	__be64 mbox_w;		/* restricted use */
 };

@@ -290,7 +290,7 @@ struct sisl_global_regs {
 #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
+#define SISL_ASTATUS_FC0_LOGI_R  0x1000ULL /* b51, login state machine timed out
 						   and retrying */
 #define SISL_ASTATUS_FC0_LOGI_F  0x0800ULL /* b52, login failed,
 					      FC_ERROR[19:0] */
@@ -340,7 +340,7 @@ struct sisl_global_regs {
 #define SISL_AFUCONF_MBOX_CLR_READ     0x0010ULL
 	__be64 afu_config;
 	__be64 rsvd[0xf8];
-	__be64 afu_version;
+	__le64 afu_version;
 	__be64 interface_version;
 };

@@ -76,7 +76,7 @@ void cxlflash_free_errpage(void)
 *
 * When the host needs to go down, all users must be quiesced and their
 * memory freed. This is accomplished by putting the contexts in error
- * state which will notify the user and let them 'drive' the tear-down.
+ * state which will notify the user and let them 'drive' the tear down.
 * Meanwhile, this routine camps until all user contexts have been removed.
 */
 void cxlflash_stop_term_user_contexts(struct cxlflash_cfg *cfg)
@@ -100,7 +100,7 @@ void cxlflash_stop_term_user_contexts(struct cxlflash_cfg *cfg)

 		dev_dbg(dev, "%s: Wait for user contexts to quiesce...\n",
 			__func__);
-		wake_up_all(&cfg->limbo_waitq);
+		wake_up_all(&cfg->reset_waitq);
 		ssleep(1);
 	}
 }
@@ -162,10 +162,7 @@ struct ctx_info *get_context(struct cxlflash_cfg *cfg, u64 rctxid,

 	if (likely(ctxid < MAX_CONTEXT)) {
 		while (true) {
-			rc = mutex_lock_interruptible(&cfg->ctx_tbl_list_mutex);
-			if (rc)
-				goto out;
-
+			mutex_lock(&cfg->ctx_tbl_list_mutex);
 			ctxi = cfg->ctx_tbl[ctxid];
 			if (ctxi)
 				if ((file && (ctxi->file != file)) ||
@@ -253,7 +250,7 @@ static int afu_attach(struct cxlflash_cfg *cfg, struct ctx_info *ctxi)
 {
 	struct device *dev = &cfg->dev->dev;
 	struct afu *afu = cfg->afu;
-	struct sisl_ctrl_map *ctrl_map = ctxi->ctrl_map;
+	struct sisl_ctrl_map __iomem *ctrl_map = ctxi->ctrl_map;
 	int rc = 0;
 	u64 val;

@@ -283,6 +280,24 @@ out:
 * @sdev:	SCSI device associated with LUN.
 * @lli:	LUN destined for capacity request.
 *
+ * The READ_CAP16 can take quite a while to complete. Should an EEH occur while
+ * in scsi_execute(), the EEH handler will attempt to recover. As part of the
+ * recovery, the handler drains all currently running ioctls, waiting until they
+ * have completed before proceeding with a reset. As this routine is used on the
+ * ioctl path, this can create a condition where the EEH handler becomes stuck,
+ * infinitely waiting for this ioctl thread. To avoid this behavior, temporarily
+ * unmark this thread as an ioctl thread by releasing the ioctl read semaphore.
+ * This will allow the EEH handler to proceed with a recovery while this thread
+ * is still running. Once the scsi_execute() returns, reacquire the ioctl read
+ * semaphore and check the adapter state in case it changed while inside of
+ * scsi_execute(). The state check will wait if the adapter is still being
+ * recovered or return a failure if the recovery failed. In the event that the
+ * adapter reset failed, simply return the failure as the ioctl would be unable
+ * to continue.
+ *
+ * Note that the above puts a requirement on this routine to only be called on
+ * an ioctl thread.
+ *
 * Return: 0 on success, -errno on failure
 */
 static int read_cap16(struct scsi_device *sdev, struct llun_info *lli)
@@ -296,7 +311,7 @@ static int read_cap16(struct scsi_device *sdev, struct llun_info *lli)
 	int rc = 0;
 	int result = 0;
 	int retry_cnt = 0;
-	u32 tout = (MC_DISCOVERY_TIMEOUT * HZ);
+	u32 to = CMD_TIMEOUT * HZ;

 retry:
 	cmd_buf = kzalloc(CMD_BUFSIZE, GFP_KERNEL);
@@ -314,8 +329,18 @@ retry:
 	dev_dbg(dev, "%s: %ssending cmd(0x%x)\n", __func__,
 		retry_cnt ? "re" : "", scsi_cmd[0]);

+	/* Drop the ioctl read semahpore across lengthy call */
+	up_read(&cfg->ioctl_rwsem);
 	result = scsi_execute(sdev, scsi_cmd, DMA_FROM_DEVICE, cmd_buf,
-			      CMD_BUFSIZE, sense_buf, tout, 5, 0, NULL);
+			      CMD_BUFSIZE, sense_buf, to, CMD_RETRIES, 0, NULL);
+	down_read(&cfg->ioctl_rwsem);
+	rc = check_state(cfg);
+	if (rc) {
+		dev_err(dev, "%s: Failed state! result=0x08%X\n",
+			__func__, result);
+		rc = -ENODEV;
+		goto out;
+	}

 	if (driver_byte(result) == DRIVER_SENSE) {
 		result &= ~(0xFF<<24); /* DRIVER_SENSE is not an error */
@@ -365,8 +390,8 @@ retry:
 	 * as the buffer is allocated on an aligned boundary.
 	 */
 	mutex_lock(&gli->mutex);
-	gli->max_lba = be64_to_cpu(*((u64 *)&cmd_buf[0]));
-	gli->blk_len = be32_to_cpu(*((u32 *)&cmd_buf[8]));
+	gli->max_lba = be64_to_cpu(*((__be64 *)&cmd_buf[0]));
+	gli->blk_len = be32_to_cpu(*((__be32 *)&cmd_buf[8]));
 	mutex_unlock(&gli->mutex);

 out:
@@ -712,7 +737,6 @@ static void destroy_context(struct cxlflash_cfg *cfg,
 	kfree(ctxi->rht_needs_ws);
 	kfree(ctxi->rht_lun);
 	kfree(ctxi);
-	atomic_dec_if_positive(&cfg->num_user_contexts);
 }

 /**
@@ -737,7 +761,7 @@ static struct ctx_info *create_context(struct cxlflash_cfg *cfg,
 	struct afu *afu = cfg->afu;
 	struct ctx_info *ctxi = NULL;
 	struct llun_info **lli = NULL;
-	bool *ws = NULL;
+	u8 *ws = NULL;
 	struct sisl_rht_entry *rhte;

 	ctxi = kzalloc(sizeof(*ctxi), GFP_KERNEL);
@@ -769,7 +793,6 @@ static struct ctx_info *create_context(struct cxlflash_cfg *cfg,
 	INIT_LIST_HEAD(&ctxi->luns);
 	INIT_LIST_HEAD(&ctxi->list); /* initialize for list_empty() */

-	atomic_inc(&cfg->num_user_contexts);
 	mutex_lock(&ctxi->mutex);
 out:
 	return ctxi;
@@ -880,6 +903,9 @@ static int _cxlflash_disk_detach(struct scsi_device *sdev,
 			sys_close(lfd);
 	}

+	/* Release the sdev reference that bound this LUN to the context */
+	scsi_device_put(sdev);
+
 out:
 	if (put_ctx)
 		put_context(ctxi);
@@ -1161,10 +1187,7 @@ out:
 	return rc;
 }

-/*
- * Local fops for adapter file descriptor
- */
-static const struct file_operations cxlflash_cxl_fops = {
+const struct file_operations cxlflash_cxl_fops = {
 	.owner = THIS_MODULE,
 	.mmap = cxlflash_cxl_mmap,
 	.release = cxlflash_cxl_release,
@@ -1210,6 +1233,46 @@ static const struct file_operations null_fops = {
 	.owner = THIS_MODULE,
 };

+/**
+ * check_state() - checks and responds to the current adapter state
+ * @cfg:	Internal structure associated with the host.
+ *
+ * This routine can block and should only be used on process context.
+ * It assumes that the caller is an ioctl thread and holding the ioctl
+ * read semaphore. This is temporarily let up across the wait to allow
+ * for draining actively running ioctls. Also note that when waking up
+ * from waiting in reset, the state is unknown and must be checked again
+ * before proceeding.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+int check_state(struct cxlflash_cfg *cfg)
+{
+	struct device *dev = &cfg->dev->dev;
+	int rc = 0;
+
+retry:
+	switch (cfg->state) {
+	case STATE_RESET:
+		dev_dbg(dev, "%s: Reset state, going to wait...\n", __func__);
+		up_read(&cfg->ioctl_rwsem);
+		rc = wait_event_interruptible(cfg->reset_waitq,
+					      cfg->state != STATE_RESET);
+		down_read(&cfg->ioctl_rwsem);
+		if (unlikely(rc))
+			break;
+		goto retry;
+	case STATE_FAILTERM:
+		dev_dbg(dev, "%s: Failed/Terminating!\n", __func__);
+		rc = -ENODEV;
+		break;
+	default:
+		break;
+	}
+
+	return rc;
+}
+
 /**
 * cxlflash_disk_attach() - attach a LUN to a context
 * @sdev:	SCSI device associated with LUN.
@@ -1243,10 +1306,6 @@ static int cxlflash_disk_attach(struct scsi_device *sdev,

 	int fd = -1;

-	/* On first attach set fileops */
-	if (atomic_read(&cfg->num_user_contexts) == 0)
-		cfg->cxl_fops = cxlflash_cxl_fops;
-
 	if (attach->num_interrupts > 4) {
 		dev_dbg(dev, "%s: Cannot support this many interrupts %llu\n",
 			__func__, attach->num_interrupts);
@@ -1287,11 +1346,17 @@ static int cxlflash_disk_attach(struct scsi_device *sdev,
 			}
 	}

+	rc = scsi_device_get(sdev);
+	if (unlikely(rc)) {
+		dev_err(dev, "%s: Unable to get sdev reference!\n", __func__);
+		goto out;
+	}
+
 	lun_access = kzalloc(sizeof(*lun_access), GFP_KERNEL);
 	if (unlikely(!lun_access)) {
 		dev_err(dev, "%s: Unable to allocate lun_access!\n", __func__);
 		rc = -ENOMEM;
-		goto out;
+		goto err0;
 	}

 	lun_access->lli = lli;
@@ -1311,21 +1376,21 @@ static int cxlflash_disk_attach(struct scsi_device *sdev,
 		dev_err(dev, "%s: Could not initialize context %p\n",
 			__func__, ctx);
 		rc = -ENODEV;
-		goto err0;
+		goto err1;
 	}

 	ctxid = cxl_process_element(ctx);
 	if (unlikely((ctxid > MAX_CONTEXT) || (ctxid < 0))) {
 		dev_err(dev, "%s: ctxid (%d) invalid!\n", __func__, ctxid);
 		rc = -EPERM;
-		goto err1;
+		goto err2;
 	}

 	file = cxl_get_fd(ctx, &cfg->cxl_fops, &fd);
 	if (unlikely(fd < 0)) {
 		rc = -ENODEV;
 		dev_err(dev, "%s: Could not get file descriptor\n", __func__);
-		goto err1;
+		goto err2;
 	}

 	/* Translate read/write O_* flags from fcntl.h to AFU permission bits */
@@ -1335,7 +1400,7 @@ static int cxlflash_disk_attach(struct scsi_device *sdev,
 	if (unlikely(!ctxi)) {
 		dev_err(dev, "%s: Failed to create context! (%d)\n",
 			__func__, ctxid);
-		goto err2;
+		goto err3;
 	}

 	work = &ctxi->work;
@@ -1346,13 +1411,13 @@ static int cxlflash_disk_attach(struct scsi_device *sdev,
 	if (unlikely(rc)) {
 		dev_dbg(dev, "%s: Could not start context rc=%d\n",
 			__func__, rc);
-		goto err3;
+		goto err4;
 	}

 	rc = afu_attach(cfg, ctxi);
 	if (unlikely(rc)) {
 		dev_err(dev, "%s: Could not attach AFU rc %d\n", __func__, rc);
-		goto err4;
+		goto err5;
 	}

 	/*
@@ -1375,7 +1440,8 @@ out_attach:
 	attach->block_size = gli->blk_len;
 	attach->mmio_size = sizeof(afu->afu_map->hosts[0].harea);
 	attach->last_lba = gli->max_lba;
-	attach->max_xfer = (sdev->host->max_sectors * 512) / gli->blk_len;
+	attach->max_xfer = sdev->host->max_sectors * MAX_SECTOR_UNIT;
+	attach->max_xfer /= gli->blk_len;

 out:
 	attach->adap_fd = fd;
@@ -1387,13 +1453,13 @@ out:
 		__func__, ctxid, fd, attach->block_size, rc, attach->last_lba);
 	return rc;

-err4:
+err5:
 	cxl_stop_context(ctx);
-err3:
+err4:
 	put_context(ctxi);
 	destroy_context(cfg, ctxi);
 	ctxi = NULL;
-err2:
+err3:
 	/*
 	 * Here, we're overriding the fops with a dummy all-NULL fops because
 	 * fput() calls the release fop, which will cause us to mistakenly
@@ -1405,10 +1471,12 @@ err2:
 	fput(file);
 	put_unused_fd(fd);
 	fd = -1;
-err1:
+err2:
 	cxl_release_context(ctx);
-err0:
+err1:
 	kfree(lun_access);
+err0:
+	scsi_device_put(sdev);
 	goto out;
 }

@@ -1510,41 +1578,6 @@ err1:
 	goto out;
 }

-/**
- * check_state() - checks and responds to the current adapter state
- * @cfg:	Internal structure associated with the host.
- *
- * This routine can block and should only be used on process context.
- * Note that when waking up from waiting in limbo, the state is unknown
- * and must be checked again before proceeding.
- *
- * Return: 0 on success, -errno on failure
- */
-static int check_state(struct cxlflash_cfg *cfg)
-{
-	struct device *dev = &cfg->dev->dev;
-	int rc = 0;
-
-retry:
-	switch (cfg->state) {
-	case STATE_LIMBO:
-		dev_dbg(dev, "%s: Limbo, going to wait...\n", __func__);
-		rc = wait_event_interruptible(cfg->limbo_waitq,
-					      cfg->state != STATE_LIMBO);
-		if (unlikely(rc))
-			break;
-		goto retry;
-	case STATE_FAILTERM:
-		dev_dbg(dev, "%s: Failed/Terminating!\n", __func__);
-		rc = -ENODEV;
-		break;
-	default:
-		break;
-	}
-
-	return rc;
-}
-
 /**
 * cxlflash_afu_recover() - initiates AFU recovery
 * @sdev:	SCSI device associated with LUN.
@@ -1561,10 +1594,10 @@ retry:
 * quite possible for this routine to act as the kernel's EEH detection
 * source (MMIO read of mbox_r). Because of this, there is a window of
 * time where an EEH might have been detected but not yet 'serviced'
- * (callback invoked, causing the device to enter limbo state). To avoid
+ * (callback invoked, causing the device to enter reset state). To avoid
 * looping in this routine during that window, a 1 second sleep is in place
 * between the time the MMIO failure is detected and the time a wait on the
- * limbo wait queue is attempted via check_state().
+ * reset wait queue is attempted via check_state().
 *
 * Return: 0 on success, -errno on failure
 */
@@ -1634,9 +1667,14 @@ retry_recover:
 	/* Test if in error state */
 	reg = readq_be(&afu->ctrl_map->mbox_r);
 	if (reg == -1) {
-		dev_dbg(dev, "%s: MMIO read fail! Wait for recovery...\n",
-			__func__);
-		mutex_unlock(&ctxi->mutex);
+		dev_dbg(dev, "%s: MMIO fail, wait for recovery.\n", __func__);
+
+		/*
+		 * Before checking the state, put back the context obtained with
+		 * get_context() as it is no longer needed and sleep for a short
+		 * period of time (see prolog notes).
+		 */
+		put_context(ctxi);
 		ctxi = NULL;
 		ssleep(1);
 		rc = check_state(cfg);
@@ -1765,12 +1803,21 @@ static int cxlflash_disk_verify(struct scsi_device *sdev,
 	 * inquiry (i.e. the Unit attention is due to the WWN changing).
 	 */
 	if (verify->hint & DK_CXLFLASH_VERIFY_HINT_SENSE) {
+		/* Can't hold mutex across process_sense/read_cap16,
+		 * since we could have an intervening EEH event.
+		 */
+		ctxi->unavail = true;
+		mutex_unlock(&ctxi->mutex);
 		rc = process_sense(sdev, verify);
 		if (unlikely(rc)) {
 			dev_err(dev, "%s: Failed to validate sense data (%d)\n",
 				__func__, rc);
+			mutex_lock(&ctxi->mutex);
+			ctxi->unavail = false;
 			goto out;
 		}
+		mutex_lock(&ctxi->mutex);
+		ctxi->unavail = false;
 	}

 	switch (gli->mode) {
@@ -1955,6 +2002,14 @@ out:
 * @cmd:	IOCTL command.
 * @arg:	Userspace ioctl data structure.
 *
+ * A read/write semaphore is used to implement a 'drain' of currently
+ * running ioctls. The read semaphore is taken at the beginning of each
+ * ioctl thread and released upon concluding execution. Additionally the
+ * semaphore should be released and then reacquired in any ioctl execution
+ * path which will wait for an event to occur that is outside the scope of
+ * the ioctl (i.e. an adapter reset). To drain the ioctls currently running,
+ * a thread simply needs to acquire the write semaphore.
+ *
 * Return: 0 on success, -errno on failure
 */
 int cxlflash_ioctl(struct scsi_device *sdev, int cmd, void __user *arg)
@@ -1989,6 +2044,9 @@ int cxlflash_ioctl(struct scsi_device *sdev, int cmd, void __user *arg)
 	{sizeof(struct dk_cxlflash_clone), (sioctl)cxlflash_disk_clone},
 	};

+	/* Hold read semaphore so we can drain if needed */
+	down_read(&cfg->ioctl_rwsem);
+
 	/* Restrict command set to physical support only for internal LUN */
 	if (afu->internal_lun)
 		switch (cmd) {
@@ -2070,6 +2128,7 @@ int cxlflash_ioctl(struct scsi_device *sdev, int cmd, void __user *arg)
 	/* fall through to exit */

 cxlflash_ioctl_exit:
+	up_read(&cfg->ioctl_rwsem);
 	if (unlikely(rc && known_ioctl))
 		dev_err(dev, "%s: ioctl %s (%08X) on dev(%d/%d/%d/%llu) "
 			"returned rc %d\n", __func__,
@@ -28,7 +28,10 @@ extern struct cxlflash_global global;
 */
 #define MC_CHUNK_SIZE     (1 << MC_RHT_NMASK)	/* in LBAs */

-#define MC_DISCOVERY_TIMEOUT 5  /* 5 secs */
+#define CMD_TIMEOUT 30  /* 30 secs */
+#define CMD_RETRIES 5   /* 5 retries for scsi_execute */
+
+#define MAX_SECTOR_UNIT  512 /* max_sector is in 512 byte multiples */

 #define CHAN2PORT(_x)	((_x) + 1)
 #define PORT2CHAN(_x)	((_x) - 1)
@@ -60,7 +63,6 @@ struct llun_info {
 	u32 lun_index;		/* Index in the LUN table */
 	u32 host_no;		/* host_no from Scsi_host */
 	u32 port_sel;		/* What port to use for this LUN */
-	bool newly_created;	/* Whether the LUN was just discovered */
 	bool in_table;		/* Whether a LUN table entry was created */

 	u8 wwid[16];		/* Keep a duplicate copy here? */
@@ -84,17 +86,17 @@ enum ctx_ctrl {
 	CTX_CTRL_FILE		= (1 << 5)
 };

-#define ENCODE_CTXID(_ctx, _id)	(((((u64)_ctx) & 0xFFFFFFFF0) << 28) | _id)
+#define ENCODE_CTXID(_ctx, _id)	(((((u64)_ctx) & 0xFFFFFFFF0ULL) << 28) | _id)
 #define DECODE_CTXID(_val)	(_val & 0xFFFFFFFF)

 struct ctx_info {
-	struct sisl_ctrl_map *ctrl_map; /* initialized at startup */
+	struct sisl_ctrl_map __iomem *ctrl_map; /* initialized at startup */
 	struct sisl_rht_entry *rht_start; /* 1 page (req'd for alignment),
 					     alloc/free on attach/detach */
 	u32 rht_out;		/* Number of checked out RHT entries */
 	u32 rht_perms;		/* User-defined permissions for RHT entries */
 	struct llun_info **rht_lun;       /* Mapping of RHT entries to LUNs */
-	bool *rht_needs_ws;	/* User-desired write-same function per RHTE */
+	u8 *rht_needs_ws;	/* User-desired write-same function per RHTE */

 	struct cxl_ioctl_start_work work;
 	u64 ctxid;
@@ -144,4 +146,6 @@ void cxlflash_ba_terminate(struct ba_lun *);

 int cxlflash_manage_lun(struct scsi_device *, struct dk_cxlflash_manage_lun *);

+int check_state(struct cxlflash_cfg *);
+
 #endif /* ifndef _CXLFLASH_SUPERPIPE_H */
@@ -132,7 +132,7 @@ static int ba_init(struct ba_lun *ba_lun)
 		return -ENOMEM;
 	}

-	/* Pass the allocated lun info as a handle to the user */
+	/* Pass the allocated LUN info as a handle to the user */
 	ba_lun->ba_lun_handle = bali;

 	pr_debug("%s: Successfully initialized the LUN: "
@@ -165,7 +165,7 @@ static int find_free_range(u32 low,
 			num_bits = (sizeof(*lam) * BITS_PER_BYTE);
 			bit_pos = find_first_bit(lam, num_bits);

-			pr_devel("%s: Found free bit %llX in lun "
+			pr_devel("%s: Found free bit %llX in LUN "
 				 "map entry %llX at bitmap index = %X\n",
 				 __func__, bit_pos, bali->lun_alloc_map[i],
 				 i);
@@ -400,6 +400,24 @@ static int init_vlun(struct llun_info *lli)
 * @lba:	Logical block address to start write same.
 * @nblks:	Number of logical blocks to write same.
 *
+ * The SCSI WRITE_SAME16 can take quite a while to complete. Should an EEH occur
+ * while in scsi_execute(), the EEH handler will attempt to recover. As part of
+ * the recovery, the handler drains all currently running ioctls, waiting until
+ * they have completed before proceeding with a reset. As this routine is used
+ * on the ioctl path, this can create a condition where the EEH handler becomes
+ * stuck, infinitely waiting for this ioctl thread. To avoid this behavior,
+ * temporarily unmark this thread as an ioctl thread by releasing the ioctl read
+ * semaphore. This will allow the EEH handler to proceed with a recovery while
+ * this thread is still running. Once the scsi_execute() returns, reacquire the
+ * ioctl read semaphore and check the adapter state in case it changed while
+ * inside of scsi_execute(). The state check will wait if the adapter is still
+ * being recovered or return a failure if the recovery failed. In the event that
+ * the adapter reset failed, simply return the failure as the ioctl would be
+ * unable to continue.
+ *
+ * Note that the above puts a requirement on this routine to only be called on
+ * an ioctl thread.
+ *
 * Return: 0 on success, -errno on failure
 */
 static int write_same16(struct scsi_device *sdev,
@@ -414,7 +432,7 @@ static int write_same16(struct scsi_device *sdev,
 	int ws_limit = SISLITE_MAX_WS_BLOCKS;
 	u64 offset = lba;
 	int left = nblks;
-	u32 tout = sdev->request_queue->rq_timeout;
+	u32 to = sdev->request_queue->rq_timeout;
 	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata;
 	struct device *dev = &cfg->dev->dev;

@@ -433,8 +451,20 @@ static int write_same16(struct scsi_device *sdev,
 		put_unaligned_be32(ws_limit < left ? ws_limit : left,
 				   &scsi_cmd[10]);

+		/* Drop the ioctl read semahpore across lengthy call */
+		up_read(&cfg->ioctl_rwsem);
 		result = scsi_execute(sdev, scsi_cmd, DMA_TO_DEVICE, cmd_buf,
-				      CMD_BUFSIZE, sense_buf, tout, 5, 0, NULL);
+				      CMD_BUFSIZE, sense_buf, to, CMD_RETRIES,
+				      0, NULL);
+		down_read(&cfg->ioctl_rwsem);
+		rc = check_state(cfg);
+		if (rc) {
+			dev_err(dev, "%s: Failed state! result=0x08%X\n",
+				__func__, result);
+			rc = -ENODEV;
+			goto out;
+		}
+
 		if (result) {
 			dev_err_ratelimited(dev, "%s: command failed for "
 					    "offset %lld result=0x%x\n",
@@ -681,14 +711,14 @@ out:
 }

 /**
- * _cxlflash_vlun_resize() - changes the size of a virtual lun
+ * _cxlflash_vlun_resize() - changes the size of a virtual LUN
 * @sdev:	SCSI device associated with LUN owning virtual LUN.
 * @ctxi:	Context owning resources.
 * @resize:	Resize ioctl data structure.
 *
 * On successful return, the user is informed of the new size (in blocks)
- * of the virtual lun in last LBA format. When the size of the virtual
- * lun is zero, the last LBA is reflected as -1. See comment in the
+ * of the virtual LUN in last LBA format. When the size of the virtual
+ * LUN is zero, the last LBA is reflected as -1. See comment in the
 * prologue for _cxlflash_disk_release() regarding AFU syncs and contexts
 * on the error recovery list.
 *
@@ -785,7 +815,7 @@ void cxlflash_restore_luntable(struct cxlflash_cfg *cfg)
 	u32 chan;
 	u32 lind;
 	struct afu *afu = cfg->afu;
-	struct sisl_global_map *agm = &afu->afu_map->global;
+	struct sisl_global_map __iomem *agm = &afu->afu_map->global;

 	mutex_lock(&global.mutex);

@@ -830,7 +860,7 @@ static int init_luntable(struct cxlflash_cfg *cfg, struct llun_info *lli)
 	u32 lind;
 	int rc = 0;
 	struct afu *afu = cfg->afu;
-	struct sisl_global_map *agm = &afu->afu_map->global;
+	struct sisl_global_map __iomem *agm = &afu->afu_map->global;

 	mutex_lock(&global.mutex);

@@ -885,8 +915,8 @@ out:
 * @arg:	UVirtual ioctl data structure.
 *
 * On successful return, the user is informed of the resource handle
- * to be used to identify the virtual lun and the size (in blocks) of
- * the virtual lun in last LBA format. When the size of the virtual lun
+ * to be used to identify the virtual LUN and the size (in blocks) of
+ * the virtual LUN in last LBA format. When the size of the virtual LUN
 * is zero, the last LBA is reflected as -1.
 *
 * Return: 0 on success, -errno on failure
@@ -914,16 +944,9 @@ int cxlflash_disk_virtual_open(struct scsi_device *sdev, void *arg)

 	pr_debug("%s: ctxid=%llu ls=0x%llx\n", __func__, ctxid, lun_size);

+	/* Setup the LUNs block allocator on first call */
 	mutex_lock(&gli->mutex);
 	if (gli->mode == MODE_NONE) {
-		/* Setup the LUN table and block allocator on first call */
-		rc = init_luntable(cfg, lli);
-		if (rc) {
-			dev_err(dev, "%s: call to init_luntable failed "
-				"rc=%d!\n", __func__, rc);
-			goto err0;
-		}
-
 		rc = init_vlun(lli);
 		if (rc) {
 			dev_err(dev, "%s: call to init_vlun failed rc=%d!\n",
@@ -941,6 +964,13 @@ int cxlflash_disk_virtual_open(struct scsi_device *sdev, void *arg)
 	}
 	mutex_unlock(&gli->mutex);

+	rc = init_luntable(cfg, lli);
+	if (rc) {
+		dev_err(dev, "%s: call to init_luntable failed rc=%d!\n",
+			__func__, rc);
+		goto err1;
+	}
+
 	ctxi = get_context(cfg, rctxid, lli, 0);
 	if (unlikely(!ctxi)) {
 		dev_err(dev, "%s: Bad context! (%llu)\n", __func__, ctxid);
--- a/Show More
+++ b/Show More