@@ -314,6 +314,7 @@ Code Seq#(hex) Include File Comments
0xB3 00 linux/mmc/ioctl.h
0xC0 00-0F linux/usb/iowarrior.h
0xCA 00-0F uapi/misc/cxl.h
+0xCA 80-8F uapi/scsi/cxlflash_ioctl.h
0xCB 00-1F CBM serial IEC bus in development:
<mailto:michael.klein@puffin.lb.shuttle.de>
0xCD 01 linux/reiserfs_fs.h
new file mode 100644
@@ -0,0 +1,257 @@
+Introduction
+============
+
+ The IBM Power architecture provides support for CAPI (Coherent
+ Accelerator Power Interface), which is available to certain PCIe slots
+ on Power 8 systems. CAPI can be thought of as a special tunneling
+ protocol through PCIe that allow PCIe adapters to look like special
+ purpose co-processors which can read or write an application's
+ memory and generate page faults. As a result, the host interface to
+ an adapter running in CAPI mode does not require the data buffers to
+ be mapped to the device's memory (IOMMU bypass) nor does it require
+ memory to be pinned.
+
+ On Linux, Coherent Accelerator (CXL) kernel services present CAPI
+ devices as a PCI device by implementing a virtual PCI host bridge.
+ This abstraction simplifies the infrastructure and programming
+ model, allowing for drivers to look similar to other native PCI
+ device drivers.
+
+ CXL provides a mechanism by which user space applications can
+ directly talk to a device (network or storage) bypassing the typical
+ kernel/device driver stack. The CXL Flash Adapter Driver enables a
+ user space application direct access to Flash storage.
+
+ The CXL Flash Adapter Driver is a kernel module that sits in the
+ SCSI stack as a low level device driver (below the SCSI disk and
+ protocol drivers) for the IBM CXL Flash Adapter. This driver is
+ responsible for the initialization of the adapter, setting up the
+ special path for user space access, and performing error recovery. It
+ communicates directly the Flash Accelerator Functional Unit (AFU)
+ as described in Documentation/powerpc/cxl.txt.
+
+ The cxlflash driver supports two, mutually exclusive, modes of
+ operation at the device (LUN) level:
+
+ - Any flash device (LUN) can be configured to be accessed as a
+ regular disk device (i.e.: /dev/sdc). This is the default mode.
+
+ - Any flash device (LUN) can be configured to be accessed from
+ user space with a special block library. This mode further
+ specifies the means of accessing the device and provides for
+ either raw access to the entire LUN (referred to as direct
+ or physical LUN access) or access to a kernel/AFU-mediated
+ partition of the LUN (referred to as virtual LUN access). The
+ segmentation of a disk device into virtual LUNs is assisted
+ by special translation services provided by the Flash AFU.
+
+Overview
+========
+
+ The Coherent Accelerator Interface Architecture (CAIA) introduces a
+ concept of a master context. A master typically has special privileges
+ granted to it by the kernel or hypervisor allowing it to perform AFU
+ wide management and control. The master may or may not be involved
+ directly in each user I/O, but at the minimum is involved in the
+ initial setup before the user application is allowed to send requests
+ directly to the AFU.
+
+ The CXL Flash Adapter Driver establishes a master context with the
+ AFU. It uses memory mapped I/O (MMIO) for this control and setup. The
+ Adapter Problem Space Memory Map looks like this:
+
+ +-------------------------------+
+ | 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 |
+ +-------------------------------+
+
+ This driver configures itself into the SCSI software stack as an
+ adapter driver. The driver is the only entity that is considered a
+ Trusted Process to program the Provisioning and Control and Global
+ areas in the MMIO Space shown above. The master context driver
+ discovers all LUNs attached to the CXL Flash adapter and instantiates
+ scsi block devices (/dev/sdb, /dev/sdc etc.) for each unique LUN
+ seen from each path.
+
+ Once these scsi block devices are instantiated, an application
+ written to a specification provided by the block library may get
+ access to the Flash from user space (without requiring a system call).
+
+ This master context driver also provides a series of ioctls for this
+ block library to enable this user space access. The driver supports
+ two modes for accessing the block device.
+
+ The first mode is called a virtual mode. In this mode a single scsi
+ block device (/dev/sdb) may be carved up into any number of distinct
+ virtual LUNs. The virtual LUNs may be resized as long as the sum of
+ the sizes of all the virtual LUNs, along with the meta-data associated
+ with it does not exceed the physical capacity.
+
+ The second mode is called the physical mode. In this mode a single
+ block device (/dev/sdb) may be opened directly by the block library
+ and the entire space for the LUN is available to the application.
+
+ Only the physical mode provides persistence of the data. i.e. The
+ data written to the block device will survive application exit and
+ restart and also reboot. The virtual LUNs do not persist (i.e. do
+ not survive after the application terminates or the system reboots).
+
+
+Block library API
+=================
+
+ Applications intending to get access to the CXL Flash from user
+ space should use the block library, as it abstracts the details of
+ interfacing directly with the cxlflash driver that are necessary for
+ performing administrative actions (i.e.: setup, tear down, resize).
+ The block library can be thought of as a 'user' of services,
+ implemented as IOCTLs, that are provided by the cxlflash driver
+ specifically for devices (LUNs) operating in user space access
+ mode. While it is not a requirement that applications understand
+ the interface between the block library and the cxlflash driver,
+ a high-level overview of each supported service (IOCTL) is provided
+ below.
+
+ The block library can be found on GitHub:
+ http://www.github.com/mikehollinger/ibmcapikv
+
+
+CXL Flash Driver IOCTLs
+=======================
+
+ Users, such as the block library, that wish to interface with a flash
+ device (LUN) via user space access need to use the services provided
+ by the cxlflash driver. As these services are implemented as ioctls,
+ a file descriptor handle must first be obtained in order to establish
+ the communication channel between a user and the kernel. This file
+ descriptor is obtained by opening the device special file associated
+ with the scsi disk device (/dev/sdb) that was created during LUN
+ discovery. As per the location of the cxlflash driver within the
+ SCSI protocol stack, this open is actually not seen by the cxlflash
+ driver. Upon successful open, the user receives a file descriptor
+ (herein referred to as fd1) that should be used for issuing the
+ subsequent ioctls listed below.
+
+ The structure definitions for these IOCTLs are available in:
+ uapi/scsi/cxlflash_ioctl.h
+
+DK_CXLFLASH_ATTACH
+------------------
+
+ This ioctl obtains, initializes, and starts a context using the CXL
+ kernel services. These services specify a context id (u16) by which
+ to uniquely identify the context and its allocated resources. The
+ services additionally provide a second file descriptor (herein
+ referred to as fd2) that is used by the block library to initiate
+ memory mapped I/O (via mmap()) to the CXL flash device and poll for
+ completion events. This file descriptor is intentionally installed by
+ this driver and not the CXL kernel services to allow for intermediary
+ notification and access in the event of a non-user-initiated close(),
+ such as a killed process. This design point is described in further
+ detail in the description for the DK_CXLFLASH_DETACH ioctl.
+
+ There are a few important aspects regarding the "tokens" (context id
+ and fd2) that are provided back to the user:
+
+ - These tokens are only valid for the process under which they
+ were created. The child of a forked process cannot continue
+ to use the context id or file descriptor created by its parent.
+
+ - These tokens are only valid for the lifetime of the context and
+ the process under which they were created. Once either is
+ destroyed, the tokens are to be considered stale and subsequent
+ usage will result in errors.
+
+ - When a context is no longer needed, the user shall detach from
+ the context via the DK_CXLFLASH_DETACH ioctl.
+
+ - A close on fd2 will invalidate the tokens. This operation is not
+ required by the user.
+
+DK_CXLFLASH_USER_DIRECT
+-----------------------
+ This ioctl is responsible for transitioning the LUN to direct
+ (physical) mode access and configuring the AFU for direct access from
+ user space on a per-context basis. Additionally, the block size and
+ last logical block address (LBA) are returned to the user.
+
+ As mentioned previously, when operating in user space access mode,
+ LUNs may be accessed in whole or in part. Only one mode is allowed
+ at a time and if one mode is active (outstanding references exist),
+ requests to use the LUN in a different mode are denied.
+
+ The AFU is configured for direct access from user space by adding an
+ entry to the AFU's resource handle table. The index of the entry is
+ treated as a resource handle that is returned to the user. The user
+ is then able to use the handle to reference the LUN during I/O.
+
+DK_CXLFLASH_RELEASE
+-------------------
+ This ioctl is responsible for releasing a previously obtained
+ reference to either a physical or virtual LUN. This can be
+ thought of as the inverse of the DK_CXLFLASH_USER_DIRECT or
+ DK_CXLFLASH_USER_VIRTUAL ioctls. Upon success, the resource handle
+ is no longer valid and the entry in the resource handle table is
+ made available to be used again.
+
+ As part of the release process for virtual LUNs, the virtual LUN
+ is first resized to 0 to clear out and free the translation tables
+ associated with the virtual LUN reference.
+
+DK_CXLFLASH_DETACH
+------------------
+ This ioctl is responsible for unregistering a context with the
+ cxlflash driver and release outstanding resources that were
+ not explicitly released via the DK_CXLFLASH_RELEASE ioctl. Upon
+ success, all "tokens" which had been provided to the user from the
+ DK_CXLFLASH_ATTACH onward are no longer valid.
+
+DK_CXLFLASH_VERIFY
+------------------
+ This ioctl is used to detect various changes such as the capacity of
+ the disk changing, the number of LUNs visible changing, etc. In cases
+ where the changes affect the application (such as a LUN resize), the
+ cxlflash driver will report the changed state to the application.
+
+ The user calls in when they want to validate that a LUN hasn't been
+ changed in response to a check condition. As the user is operating out
+ of band from the kernel, they will see these types of events without
+ the kernel's knowledge. When encountered, the user's architected
+ behavior is to call in to this ioctl, indicating what they want to
+ verify and passing along any appropriate information. For now, only
+ verifying a LUN change (ie: size different) with sense data is
+ supported.
+
+DK_CXLFLASH_RECOVER_AFU
+-----------------------
+ This ioctl is used to drive recovery (if such an action is warranted)
+ of a specified user context. Any state associated with the user context
+ is re-established upon successful recovery.
+
+ User contexts are put into an error condition when the device needs to
+ be reset or is terminating. Users are notified of this error condition
+ by seeing all 0xF's on an MMIO read. Upon encountering this, the
+ architected behavior for a user is to call into this ioctl to recover
+ their context. A user may also call into this ioctl at any time to
+ check if the device is operating normally. If a failure is returned
+ from this ioctl, the user is expected to gracefully clean up their
+ context via release/detach ioctls. Until they do, the context they
+ hold is not relinquished. The user may also optionally exit the process
+ at which time the context/resources they held will be freed as part of
+ the release fop.
+
+DK_CXLFLASH_MANAGE_LUN
+----------------------
+ This ioctl is used to switch a LUN from a mode where it is available
+ for file-system access (legacy), to a mode where it is set aside for
+ exclusive user space access (superpipe). In case a LUN is visible
+ across multiple ports and adapters, this ioctl is used to uniquely
+ identify each LUN by its World Wide Node Name (WWNN).
@@ -1,2 +1,2 @@
obj-$(CONFIG_CXLFLASH) += cxlflash.o
-cxlflash-y += main.o
+cxlflash-y += main.o superpipe.o lunmgt.o
@@ -107,6 +107,17 @@ struct cxlflash_cfg {
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 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;
+
+ struct list_head lluns; /* list of llun_info structs */
+
wait_queue_head_t tmf_waitq;
bool tmf_active;
wait_queue_head_t limbo_waitq;
@@ -182,4 +193,12 @@ 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);
+void cxlflash_free_errpage(void);
+int cxlflash_ioctl(struct scsi_device *, int, void __user *);
+void cxlflash_stop_term_user_contexts(struct cxlflash_cfg *);
+int cxlflash_mark_contexts_error(struct cxlflash_cfg *);
+void cxlflash_term_local_luns(struct cxlflash_cfg *);
+
#endif /* ifndef _CXLFLASH_COMMON_H */
new file mode 100644
@@ -0,0 +1,263 @@
+/*
+ * 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 <misc/cxl.h>
+#include <asm/unaligned.h>
+
+#include <scsi/scsi_host.h>
+#include <uapi/scsi/cxlflash_ioctl.h>
+
+#include "sislite.h"
+#include "common.h"
+#include "superpipe.h"
+
+/**
+ * create_local() - allocate and initialize a local LUN information structure
+ * @sdev: SCSI device associated with LUN.
+ * @wwid: World Wide Node Name for LUN.
+ *
+ * Return: Allocated local llun_info structure on success, NULL on failure
+ */
+static struct llun_info *create_local(struct scsi_device *sdev, u8 *wwid)
+{
+ struct llun_info *lli = NULL;
+
+ lli = kzalloc(sizeof(*lli), GFP_KERNEL);
+ if (unlikely(!lli)) {
+ pr_err("%s: could not allocate lli\n", __func__);
+ goto out;
+ }
+
+ lli->sdev = sdev;
+ lli->newly_created = true;
+ lli->host_no = sdev->host->host_no;
+
+ memcpy(lli->wwid, wwid, DK_CXLFLASH_MANAGE_LUN_WWID_LEN);
+out:
+ return lli;
+}
+
+/**
+ * create_global() - allocate and initialize a global LUN information structure
+ * @sdev: SCSI device associated with LUN.
+ * @wwid: World Wide Node Name for LUN.
+ *
+ * Return: Allocated global glun_info structure on success, NULL on failure
+ */
+static struct glun_info *create_global(struct scsi_device *sdev, u8 *wwid)
+{
+ struct glun_info *gli = NULL;
+
+ gli = kzalloc(sizeof(*gli), GFP_KERNEL);
+ if (unlikely(!gli)) {
+ pr_err("%s: could not allocate gli\n", __func__);
+ goto out;
+ }
+
+ mutex_init(&gli->mutex);
+ memcpy(gli->wwid, wwid, DK_CXLFLASH_MANAGE_LUN_WWID_LEN);
+out:
+ return gli;
+}
+
+/**
+ * refresh_local() - find and update 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)
+{
+ 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;
+ return lli;
+ }
+
+ return NULL;
+}
+
+/**
+ * lookup_global() - find a global LUN information structure by WWID
+ * @wwid: WWID associated with LUN.
+ *
+ * Return: Found global lun_info structure on success, NULL on failure
+ */
+static struct glun_info *lookup_global(u8 *wwid)
+{
+ struct glun_info *gli, *temp;
+
+ list_for_each_entry_safe(gli, temp, &global.gluns, list)
+ if (!memcmp(gli->wwid, wwid, DK_CXLFLASH_MANAGE_LUN_WWID_LEN))
+ return gli;
+
+ return NULL;
+}
+
+/**
+ * find_and_create_lun() - find or create a local LUN information structure
+ * @sdev: SCSI device associated with LUN.
+ * @wwid: WWID associated with LUN.
+ *
+ * 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.).
+ * 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
+ * LUN (one local, one global).
+ *
+ * Keep a pointer back from the local to the global entry.
+ *
+ * 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)
+{
+ struct llun_info *lli = NULL;
+ struct glun_info *gli = NULL;
+ 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);
+ if (lli)
+ goto out;
+
+ lli = create_local(sdev, wwid);
+ if (unlikely(!lli))
+ goto out;
+
+ gli = lookup_global(wwid);
+ if (gli) {
+ lli->parent = gli;
+ list_add(&lli->list, &cfg->lluns);
+ goto out;
+ }
+
+ gli = create_global(sdev, wwid);
+ if (unlikely(!gli)) {
+ kfree(lli);
+ lli = NULL;
+ goto out;
+ }
+
+ lli->parent = gli;
+ list_add(&lli->list, &cfg->lluns);
+
+ list_add(&gli->list, &global.gluns);
+
+out:
+ mutex_unlock(&global.mutex);
+ pr_debug("%s: returning %p\n", __func__, lli);
+ return lli;
+}
+
+/**
+ * cxlflash_term_local_luns() - Delete all entries from local LUN list, free.
+ * @cfg: Internal structure associated with the host.
+ */
+void cxlflash_term_local_luns(struct cxlflash_cfg *cfg)
+{
+ struct llun_info *lli, *temp;
+
+ mutex_lock(&global.mutex);
+ list_for_each_entry_safe(lli, temp, &cfg->lluns, list) {
+ list_del(&lli->list);
+ kfree(lli);
+ }
+ mutex_unlock(&global.mutex);
+}
+
+/**
+ * cxlflash_list_init() - initializes the global LUN list
+ */
+void cxlflash_list_init(void)
+{
+ INIT_LIST_HEAD(&global.gluns);
+ mutex_init(&global.mutex);
+ global.err_page = NULL;
+}
+
+/**
+ * cxlflash_term_global_luns() - frees resources associated with global LUN list
+ */
+void cxlflash_term_global_luns(void)
+{
+ struct glun_info *gli, *temp;
+
+ mutex_lock(&global.mutex);
+ list_for_each_entry_safe(gli, temp, &global.gluns, list) {
+ list_del(&gli->list);
+ kfree(gli);
+ }
+ mutex_unlock(&global.mutex);
+}
+
+/**
+ * cxlflash_manage_lun() - handles LUN management activities
+ * @sdev: SCSI device associated with LUN.
+ * @manage: Manage ioctl data structure.
+ *
+ * This routine is used to notify the driver about a LUN's WWID and associate
+ * SCSI devices (sdev) with a global LUN instance. Additionally it serves to
+ * change a LUN's operating mode: legacy or superpipe.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+int cxlflash_manage_lun(struct scsi_device *sdev,
+ struct dk_cxlflash_manage_lun *manage)
+{
+ int rc = 0;
+ struct llun_info *lli = NULL;
+ u64 flags = manage->hdr.flags;
+ u32 chan = sdev->channel;
+
+ 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]),
+ manage->hdr.flags, lli);
+ if (unlikely(!lli)) {
+ rc = -ENOMEM;
+ goto out;
+ }
+
+ 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 */
+ 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
+ sdev->hostdata = NULL;
+ }
+
+out:
+ pr_debug("%s: returning rc=%d\n", __func__, rc);
+ return rc;
+}
@@ -23,6 +23,7 @@
#include <scsi/scsi_cmnd.h>
#include <scsi/scsi_host.h>
+#include <uapi/scsi/cxlflash_ioctl.h>
#include "main.h"
#include "sislite.h"
@@ -519,7 +520,7 @@ static int cxlflash_eh_host_reset_handler(struct scsi_cmnd *scp)
case STATE_NORMAL:
cfg->state = STATE_LIMBO;
scsi_block_requests(cfg->host);
-
+ cxlflash_mark_contexts_error(cfg);
rcr = cxlflash_afu_reset(cfg);
if (rcr) {
rc = FAILED;
@@ -663,6 +664,21 @@ static ssize_t cxlflash_store_lun_mode(struct device *dev,
}
/**
+ * cxlflash_show_ioctl_version() - presents the current ioctl version of the host
+ * @dev: Generic device associated with the host.
+ * @attr: Device attribute representing the ioctl version.
+ * @buf: Buffer of length PAGE_SIZE to report back the ioctl version.
+ *
+ * Return: The size of the ASCII string returned in @buf.
+ */
+static ssize_t cxlflash_show_ioctl_version(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ return scnprintf(buf, PAGE_SIZE, "%u\n", DK_CXLFLASH_VERSION_0);
+}
+
+/**
* 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.
@@ -700,11 +716,13 @@ 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 DEVICE_ATTR(ioctl_version, S_IRUGO, cxlflash_show_ioctl_version, NULL);
static struct device_attribute *cxlflash_host_attrs[] = {
&dev_attr_port0,
&dev_attr_port1,
&dev_attr_lun_mode,
+ &dev_attr_ioctl_version,
NULL
};
@@ -725,6 +743,7 @@ static struct scsi_host_template driver_template = {
.module = THIS_MODULE,
.name = CXLFLASH_ADAPTER_NAME,
.info = cxlflash_driver_info,
+ .ioctl = cxlflash_ioctl,
.proc_name = CXLFLASH_NAME,
.queuecommand = cxlflash_queuecommand,
.eh_device_reset_handler = cxlflash_eh_device_reset_handler,
@@ -872,9 +891,11 @@ static void cxlflash_remove(struct pci_dev *pdev)
spin_unlock_irqrestore(&cfg->tmf_waitq.lock, lock_flags);
cfg->state = STATE_FAILTERM;
+ cxlflash_stop_term_user_contexts(cfg);
switch (cfg->init_state) {
case INIT_STATE_SCSI:
+ cxlflash_term_local_luns(cfg);
scsi_remove_host(cfg->host);
scsi_host_put(cfg->host);
/* Fall through */
@@ -2274,6 +2295,10 @@ static int cxlflash_probe(struct pci_dev *pdev,
INIT_WORK(&cfg->work_q, cxlflash_worker_thread);
cfg->lr_state = LINK_RESET_INVALID;
cfg->lr_port = -1;
+ mutex_init(&cfg->ctx_tbl_list_mutex);
+ mutex_init(&cfg->ctx_recovery_mutex);
+ INIT_LIST_HEAD(&cfg->ctx_err_recovery);
+ INIT_LIST_HEAD(&cfg->lluns);
pci_set_drvdata(pdev, cfg);
@@ -2335,6 +2360,7 @@ out_remove:
static pci_ers_result_t cxlflash_pci_error_detected(struct pci_dev *pdev,
pci_channel_state_t state)
{
+ int rc = 0;
struct cxlflash_cfg *cfg = pci_get_drvdata(pdev);
struct device *dev = &cfg->dev->dev;
@@ -2346,7 +2372,10 @@ static pci_ers_result_t cxlflash_pci_error_detected(struct pci_dev *pdev,
/* Turn off legacy I/O */
scsi_block_requests(cfg->host);
-
+ rc = cxlflash_mark_contexts_error(cfg);
+ if (unlikely(rc))
+ dev_err(dev, "%s: Failed to mark user contexts!(%d)\n",
+ __func__, rc);
term_mc(cfg, UNDO_START);
stop_afu(cfg);
@@ -2431,6 +2460,8 @@ static int __init init_cxlflash(void)
pr_info("%s: IBM Power CXL Flash Adapter: %s\n",
__func__, CXLFLASH_DRIVER_DATE);
+ cxlflash_list_init();
+
return pci_register_driver(&cxlflash_driver);
}
@@ -2439,6 +2470,9 @@ static int __init init_cxlflash(void)
*/
static void __exit exit_cxlflash(void)
{
+ cxlflash_term_global_luns();
+ cxlflash_free_errpage();
+
pci_unregister_driver(&cxlflash_driver);
}
@@ -409,7 +409,10 @@ struct sisl_lxt_entry {
};
-/* Per the SISlite spec, RHT entries are to be 16-byte aligned */
+/*
+ * RHT - Resource Handle Table
+ * 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;
new file mode 100644
@@ -0,0 +1,2014 @@
+/*
+ * 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/file.h>
+#include <linux/syscalls.h>
+#include <misc/cxl.h>
+#include <asm/unaligned.h>
+
+#include <scsi/scsi.h>
+#include <scsi/scsi_host.h>
+#include <scsi/scsi_cmnd.h>
+#include <scsi/scsi_eh.h>
+#include <uapi/scsi/cxlflash_ioctl.h>
+
+#include "sislite.h"
+#include "common.h"
+#include "superpipe.h"
+
+struct cxlflash_global global;
+
+/**
+ * marshal_det_to_rele() - translate detach to release structure
+ * @detach: Destination structure for the translate/copy.
+ * @rele: Source structure from which to translate/copy.
+ */
+static void marshal_det_to_rele(struct dk_cxlflash_detach *detach,
+ struct dk_cxlflash_release *release)
+{
+ release->hdr = detach->hdr;
+ release->context_id = detach->context_id;
+}
+
+/**
+ * cxlflash_free_errpage() - frees resources associated with global error page
+ */
+void cxlflash_free_errpage(void)
+{
+
+ mutex_lock(&global.mutex);
+ if (global.err_page) {
+ __free_page(global.err_page);
+ global.err_page = NULL;
+ }
+ mutex_unlock(&global.mutex);
+}
+
+/**
+ * cxlflash_stop_term_user_contexts() - stops/terminates known user contexts
+ * @cfg: Internal structure associated with the host.
+ *
+ * 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.
+ * Meanwhile, this routine camps until all user contexts have been removed.
+ */
+void cxlflash_stop_term_user_contexts(struct cxlflash_cfg *cfg)
+{
+ struct device *dev = &cfg->dev->dev;
+ int i, found;
+
+ cxlflash_mark_contexts_error(cfg);
+
+ while (true) {
+ found = false;
+
+ for (i = 0; i < MAX_CONTEXT; i++)
+ if (cfg->ctx_tbl[i]) {
+ found = true;
+ break;
+ }
+
+ if (!found && list_empty(&cfg->ctx_err_recovery))
+ return;
+
+ dev_dbg(dev, "%s: Wait for user contexts to quiesce...\n",
+ __func__);
+ wake_up_all(&cfg->limbo_waitq);
+ ssleep(1);
+ }
+}
+
+/**
+ * find_error_context() - locates a context by cookie on the error recovery list
+ * @cfg: Internal structure associated with the host.
+ * @rctxid: Desired context by id.
+ * @file: Desired context by file.
+ *
+ * Return: Found context on success, NULL on failure
+ */
+static struct ctx_info *find_error_context(struct cxlflash_cfg *cfg, u64 rctxid,
+ struct file *file)
+{
+ struct ctx_info *ctxi;
+
+ list_for_each_entry(ctxi, &cfg->ctx_err_recovery, list)
+ if ((ctxi->ctxid == rctxid) || (ctxi->file == file))
+ return ctxi;
+
+ return NULL;
+}
+
+/**
+ * get_context() - obtains a validated and locked context reference
+ * @cfg: Internal structure associated with the host.
+ * @rctxid: Desired context (raw, un-decoded format).
+ * @arg: LUN information or file associated with request.
+ * @ctx_ctrl: Control information to 'steer' desired lookup.
+ *
+ * NOTE: despite the name pid, in linux, current->pid actually refers
+ * to the lightweight process id (tid) and can change if the process is
+ * multi threaded. The tgid remains constant for the process and only changes
+ * when the process of fork. For all intents and purposes, think of tgid
+ * as a pid in the traditional sense.
+ *
+ * Return: Validated context on success, NULL on failure
+ */
+struct ctx_info *get_context(struct cxlflash_cfg *cfg, u64 rctxid,
+ void *arg, enum ctx_ctrl ctx_ctrl)
+{
+ struct device *dev = &cfg->dev->dev;
+ struct ctx_info *ctxi = NULL;
+ struct lun_access *lun_access = NULL;
+ struct file *file = NULL;
+ struct llun_info *lli = arg;
+ u64 ctxid = DECODE_CTXID(rctxid);
+ int rc;
+ pid_t pid = current->tgid, ctxpid = 0;
+
+ if (ctx_ctrl & CTX_CTRL_FILE) {
+ lli = NULL;
+ file = (struct file *)arg;
+ }
+
+ if (ctx_ctrl & CTX_CTRL_CLONE)
+ pid = current->parent->tgid;
+
+ if (likely(ctxid < MAX_CONTEXT)) {
+ while (true) {
+ rc = mutex_lock_interruptible(&cfg->ctx_tbl_list_mutex);
+ if (rc)
+ goto out;
+
+ ctxi = cfg->ctx_tbl[ctxid];
+ if (ctxi)
+ if ((file && (ctxi->file != file)) ||
+ (!file && (ctxi->ctxid != rctxid)))
+ ctxi = NULL;
+
+ if ((ctx_ctrl & CTX_CTRL_ERR) ||
+ (!ctxi && (ctx_ctrl & CTX_CTRL_ERR_FALLBACK)))
+ ctxi = find_error_context(cfg, rctxid, file);
+ if (!ctxi) {
+ mutex_unlock(&cfg->ctx_tbl_list_mutex);
+ goto out;
+ }
+
+ /*
+ * Need to acquire ownership of the context while still
+ * under the table/list lock to serialize with a remove
+ * thread. Use the 'try' to avoid stalling the
+ * table/list lock for a single context.
+ *
+ * Note that the lock order is:
+ *
+ * cfg->ctx_tbl_list_mutex -> ctxi->mutex
+ *
+ * Therefore release ctx_tbl_list_mutex before retrying.
+ */
+ rc = mutex_trylock(&ctxi->mutex);
+ mutex_unlock(&cfg->ctx_tbl_list_mutex);
+ if (rc)
+ break; /* got the context's lock! */
+ }
+
+ if (ctxi->unavail)
+ goto denied;
+
+ ctxpid = ctxi->pid;
+ if (likely(!(ctx_ctrl & CTX_CTRL_NOPID)))
+ if (pid != ctxpid)
+ goto denied;
+
+ if (lli) {
+ list_for_each_entry(lun_access, &ctxi->luns, list)
+ if (lun_access->lli == lli)
+ goto out;
+ goto denied;
+ }
+ }
+
+out:
+ dev_dbg(dev, "%s: rctxid=%016llX ctxinfo=%p ctxpid=%u pid=%u "
+ "ctx_ctrl=%u\n", __func__, rctxid, ctxi, ctxpid, pid,
+ ctx_ctrl);
+
+ return ctxi;
+
+denied:
+ mutex_unlock(&ctxi->mutex);
+ ctxi = NULL;
+ goto out;
+}
+
+/**
+ * put_context() - release a context that was retrieved from get_context()
+ * @ctxi: Context to release.
+ *
+ * For now, releasing the context equates to unlocking it's mutex.
+ */
+void put_context(struct ctx_info *ctxi)
+{
+ mutex_unlock(&ctxi->mutex);
+}
+
+/**
+ * afu_attach() - attach a context to the AFU
+ * @cfg: Internal structure associated with the host.
+ * @ctxi: Context to attach.
+ *
+ * Upon setting the context capabilities, they must be confirmed with
+ * a read back operation as the context might have been closed since
+ * the mailbox was unlocked. When this occurs, registration is failed.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+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;
+ int rc = 0;
+ u64 val;
+
+ /* Unlock cap and restrict user to read/write cmds in translated mode */
+ readq_be(&ctrl_map->mbox_r);
+ val = (SISL_CTX_CAP_READ_CMD | SISL_CTX_CAP_WRITE_CMD);
+ writeq_be(val, &ctrl_map->ctx_cap);
+ val = readq_be(&ctrl_map->ctx_cap);
+ if (val != (SISL_CTX_CAP_READ_CMD | SISL_CTX_CAP_WRITE_CMD)) {
+ dev_err(dev, "%s: ctx may be closed val=%016llX\n",
+ __func__, val);
+ rc = -EAGAIN;
+ goto out;
+ }
+
+ /* Set up MMIO registers pointing to the RHT */
+ writeq_be((u64)ctxi->rht_start, &ctrl_map->rht_start);
+ val = SISL_RHT_CNT_ID((u64)MAX_RHT_PER_CONTEXT, (u64)(afu->ctx_hndl));
+ writeq_be(val, &ctrl_map->rht_cnt_id);
+out:
+ dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
+ return rc;
+}
+
+/**
+ * read_cap16() - issues a SCSI READ_CAP16 command
+ * @sdev: SCSI device associated with LUN.
+ * @lli: LUN destined for capacity request.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+static int read_cap16(struct scsi_device *sdev, struct llun_info *lli)
+{
+ struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata;
+ struct device *dev = &cfg->dev->dev;
+ struct glun_info *gli = lli->parent;
+ u8 *cmd_buf = NULL;
+ u8 *scsi_cmd = NULL;
+ u8 *sense_buf = NULL;
+ int rc = 0;
+ int result = 0;
+ int retry_cnt = 0;
+ u32 tout = (MC_DISCOVERY_TIMEOUT * HZ);
+
+retry:
+ cmd_buf = kzalloc(CMD_BUFSIZE, GFP_KERNEL);
+ scsi_cmd = kzalloc(MAX_COMMAND_SIZE, GFP_KERNEL);
+ sense_buf = kzalloc(SCSI_SENSE_BUFFERSIZE, GFP_KERNEL);
+ if (unlikely(!cmd_buf || !scsi_cmd || !sense_buf)) {
+ rc = -ENOMEM;
+ goto out;
+ }
+
+ scsi_cmd[0] = SERVICE_ACTION_IN_16; /* read cap(16) */
+ scsi_cmd[1] = SAI_READ_CAPACITY_16; /* service action */
+ put_unaligned_be32(CMD_BUFSIZE, &scsi_cmd[10]);
+
+ dev_dbg(dev, "%s: %ssending cmd(0x%x)\n", __func__,
+ retry_cnt ? "re" : "", scsi_cmd[0]);
+
+ result = scsi_execute(sdev, scsi_cmd, DMA_FROM_DEVICE, cmd_buf,
+ CMD_BUFSIZE, sense_buf, tout, 5, 0, NULL);
+
+ if (driver_byte(result) == DRIVER_SENSE) {
+ result &= ~(0xFF<<24); /* DRIVER_SENSE is not an error */
+ if (result & SAM_STAT_CHECK_CONDITION) {
+ struct scsi_sense_hdr sshdr;
+
+ scsi_normalize_sense(sense_buf, SCSI_SENSE_BUFFERSIZE,
+ &sshdr);
+ switch (sshdr.sense_key) {
+ case NO_SENSE:
+ case RECOVERED_ERROR:
+ /* fall through */
+ case NOT_READY:
+ result &= ~SAM_STAT_CHECK_CONDITION;
+ break;
+ case UNIT_ATTENTION:
+ switch (sshdr.asc) {
+ case 0x29: /* Power on Reset or Device Reset */
+ /* fall through */
+ case 0x2A: /* Device capacity changed */
+ case 0x3F: /* Report LUNs changed */
+ /* Retry the command once more */
+ if (retry_cnt++ < 1) {
+ kfree(cmd_buf);
+ kfree(scsi_cmd);
+ kfree(sense_buf);
+ goto retry;
+ }
+ }
+ break;
+ default:
+ break;
+ }
+ }
+ }
+
+ if (result) {
+ dev_err(dev, "%s: command failed, result=0x%x\n",
+ __func__, result);
+ rc = -EIO;
+ goto out;
+ }
+
+ /*
+ * Read cap was successful, grab values from the buffer;
+ * note that we don't need to worry about unaligned access
+ * 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]));
+ mutex_unlock(&gli->mutex);
+
+out:
+ kfree(cmd_buf);
+ kfree(scsi_cmd);
+ kfree(sense_buf);
+
+ dev_dbg(dev, "%s: maxlba=%lld blklen=%d rc=%d\n",
+ __func__, gli->max_lba, gli->blk_len, rc);
+ return rc;
+}
+
+/**
+ * get_rhte() - obtains validated resource handle table entry reference
+ * @ctxi: Context owning the resource handle.
+ * @rhndl: Resource handle associated with entry.
+ * @lli: LUN associated with request.
+ *
+ * Return: Validated RHTE on success, NULL on failure
+ */
+struct sisl_rht_entry *get_rhte(struct ctx_info *ctxi, res_hndl_t rhndl,
+ struct llun_info *lli)
+{
+ struct sisl_rht_entry *rhte = NULL;
+
+ if (unlikely(!ctxi->rht_start)) {
+ pr_debug("%s: Context does not have allocated RHT!\n",
+ __func__);
+ goto out;
+ }
+
+ if (unlikely(rhndl >= MAX_RHT_PER_CONTEXT)) {
+ pr_debug("%s: Bad resource handle! (%d)\n", __func__, rhndl);
+ goto out;
+ }
+
+ if (unlikely(ctxi->rht_lun[rhndl] != lli)) {
+ pr_debug("%s: Bad resource handle LUN! (%d)\n",
+ __func__, rhndl);
+ goto out;
+ }
+
+ rhte = &ctxi->rht_start[rhndl];
+ if (unlikely(rhte->nmask == 0)) {
+ pr_debug("%s: Unopened resource handle! (%d)\n",
+ __func__, rhndl);
+ rhte = NULL;
+ goto out;
+ }
+
+out:
+ return rhte;
+}
+
+/**
+ * rhte_checkout() - obtains free/empty resource handle table entry
+ * @ctxi: Context owning the resource handle.
+ * @lli: LUN associated with request.
+ *
+ * Return: Free RHTE on success, NULL on failure
+ */
+struct sisl_rht_entry *rhte_checkout(struct ctx_info *ctxi,
+ struct llun_info *lli)
+{
+ struct sisl_rht_entry *rhte = NULL;
+ int i;
+
+ /* Find a free RHT entry */
+ for (i = 0; i < MAX_RHT_PER_CONTEXT; i++)
+ if (ctxi->rht_start[i].nmask == 0) {
+ rhte = &ctxi->rht_start[i];
+ ctxi->rht_out++;
+ break;
+ }
+
+ if (likely(rhte))
+ ctxi->rht_lun[i] = lli;
+
+ pr_debug("%s: returning rhte=%p (%d)\n", __func__, rhte, i);
+ return rhte;
+}
+
+/**
+ * rhte_checkin() - releases a resource handle table entry
+ * @ctxi: Context owning the resource handle.
+ * @rhte: RHTE to release.
+ */
+void rhte_checkin(struct ctx_info *ctxi,
+ struct sisl_rht_entry *rhte)
+{
+ u32 rsrc_handle = rhte - ctxi->rht_start;
+
+ rhte->nmask = 0;
+ rhte->fp = 0;
+ ctxi->rht_out--;
+ ctxi->rht_lun[rsrc_handle] = NULL;
+}
+
+/**
+ * rhte_format1() - populates a RHTE for format 1
+ * @rhte: RHTE to populate.
+ * @lun_id: LUN ID of LUN associated with RHTE.
+ * @perm: Desired permissions for RHTE.
+ * @port_sel: Port selection mask
+ */
+static void rht_format1(struct sisl_rht_entry *rhte, u64 lun_id, u32 perm,
+ u32 port_sel)
+{
+ /*
+ * Populate the Format 1 RHT entry for direct access (physical
+ * LUN) using the synchronization sequence defined in the
+ * SISLite specification.
+ */
+ struct sisl_rht_entry_f1 dummy = { 0 };
+ struct sisl_rht_entry_f1 *rhte_f1 = (struct sisl_rht_entry_f1 *)rhte;
+
+ memset(rhte_f1, 0, sizeof(*rhte_f1));
+ rhte_f1->fp = SISL_RHT_FP(1U, 0);
+ dma_wmb(); /* Make setting of format bit visible */
+
+ rhte_f1->lun_id = lun_id;
+ dma_wmb(); /* Make setting of LUN id visible */
+
+ /*
+ * Use a dummy RHT Format 1 entry to build the second dword
+ * of the entry that must be populated in a single write when
+ * enabled (valid bit set to TRUE).
+ */
+ dummy.valid = 0x80;
+ dummy.fp = SISL_RHT_FP(1U, perm);
+ dummy.port_sel = port_sel;
+ rhte_f1->dw = dummy.dw;
+
+ dma_wmb(); /* Make remaining RHT entry fields visible */
+}
+
+/**
+ * cxlflash_lun_attach() - attaches a user to a LUN and manages the LUN's mode
+ * @gli: LUN to attach.
+ * @mode: Desired mode of the LUN.
+ * @locked: Mutex status on current thread.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+int cxlflash_lun_attach(struct glun_info *gli, enum lun_mode mode, bool locked)
+{
+ int rc = 0;
+
+ if (!locked)
+ mutex_lock(&gli->mutex);
+
+ if (gli->mode == MODE_NONE)
+ gli->mode = mode;
+ else if (gli->mode != mode) {
+ pr_debug("%s: LUN operating in mode %d, requested mode %d\n",
+ __func__, gli->mode, mode);
+ rc = -EINVAL;
+ goto out;
+ }
+
+ gli->users++;
+ WARN_ON(gli->users <= 0);
+out:
+ pr_debug("%s: Returning rc=%d gli->mode=%u gli->users=%u\n",
+ __func__, rc, gli->mode, gli->users);
+ if (!locked)
+ mutex_unlock(&gli->mutex);
+ return rc;
+}
+
+/**
+ * cxlflash_lun_detach() - detaches a user from a LUN and resets the LUN's mode
+ * @gli: LUN to detach.
+ */
+void cxlflash_lun_detach(struct glun_info *gli)
+{
+ mutex_lock(&gli->mutex);
+ WARN_ON(gli->mode == MODE_NONE);
+ if (--gli->users == 0)
+ gli->mode = MODE_NONE;
+ pr_debug("%s: gli->users=%u\n", __func__, gli->users);
+ WARN_ON(gli->users < 0);
+ mutex_unlock(&gli->mutex);
+}
+
+/**
+ * _cxlflash_disk_release() - releases the specified resource entry
+ * @sdev: SCSI device associated with LUN.
+ * @ctxi: Context owning resources.
+ * @release: Release ioctl data structure.
+ *
+ * Note that the AFU sync should _not_ be performed when the context is sitting
+ * on the error recovery list. A context on the error recovery list is not known
+ * to the AFU due to reset. When the context is recovered, it will be reattached
+ * and made known again to the AFU.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+int _cxlflash_disk_release(struct scsi_device *sdev,
+ struct ctx_info *ctxi,
+ struct dk_cxlflash_release *release)
+{
+ struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata;
+ struct device *dev = &cfg->dev->dev;
+ struct llun_info *lli = sdev->hostdata;
+ struct glun_info *gli = lli->parent;
+ struct afu *afu = cfg->afu;
+ bool put_ctx = false;
+
+ res_hndl_t rhndl = release->rsrc_handle;
+
+ int rc = 0;
+ u64 ctxid = DECODE_CTXID(release->context_id),
+ rctxid = release->context_id;
+
+ struct sisl_rht_entry *rhte;
+ struct sisl_rht_entry_f1 *rhte_f1;
+
+ dev_dbg(dev, "%s: ctxid=%llu rhndl=0x%llx gli->mode=%u gli->users=%u\n",
+ __func__, ctxid, release->rsrc_handle, gli->mode, gli->users);
+
+ if (!ctxi) {
+ ctxi = get_context(cfg, rctxid, lli, CTX_CTRL_ERR_FALLBACK);
+ if (unlikely(!ctxi)) {
+ dev_dbg(dev, "%s: Bad context! (%llu)\n",
+ __func__, ctxid);
+ rc = -EINVAL;
+ goto out;
+ }
+
+ put_ctx = true;
+ }
+
+ rhte = get_rhte(ctxi, rhndl, lli);
+ if (unlikely(!rhte)) {
+ dev_dbg(dev, "%s: Bad resource handle! (%d)\n",
+ __func__, rhndl);
+ rc = -EINVAL;
+ goto out;
+ }
+
+ switch (gli->mode) {
+ case MODE_PHYSICAL:
+ /*
+ * Clear the Format 1 RHT entry for direct access
+ * (physical LUN) using the synchronization sequence
+ * defined in the SISLite specification.
+ */
+ rhte_f1 = (struct sisl_rht_entry_f1 *)rhte;
+
+ rhte_f1->valid = 0;
+ dma_wmb(); /* Make revocation of RHT entry visible */
+
+ rhte_f1->lun_id = 0;
+ dma_wmb(); /* Make clearing of LUN id visible */
+
+ rhte_f1->dw = 0;
+ dma_wmb(); /* Make RHT entry bottom-half clearing visible */
+
+ if (!ctxi->err_recovery_active)
+ cxlflash_afu_sync(afu, ctxid, rhndl, AFU_HW_SYNC);
+ break;
+ default:
+ WARN(1, "Unsupported LUN mode!");
+ goto out;
+ }
+
+ rhte_checkin(ctxi, rhte);
+ cxlflash_lun_detach(gli);
+
+out:
+ if (put_ctx)
+ put_context(ctxi);
+ dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
+ return rc;
+}
+
+int cxlflash_disk_release(struct scsi_device *sdev,
+ struct dk_cxlflash_release *release)
+{
+ return _cxlflash_disk_release(sdev, NULL, release);
+}
+
+/**
+ * destroy_context() - releases a context
+ * @cfg: Internal structure associated with the host.
+ * @ctxi: Context to release.
+ *
+ * Note that the rht_lun member of the context was cut from a single
+ * allocation when the context was created and therefore does not need
+ * to be explicitly freed. Also note that we conditionally check for the
+ * existence of the context control map before clearing the RHT registers
+ * and context capabilities because it is possible to destroy a context
+ * while the context is in the error state (previous mapping was removed
+ * [so we don't have to worry about clearing] and context is waiting for
+ * a new mapping).
+ */
+static void destroy_context(struct cxlflash_cfg *cfg,
+ struct ctx_info *ctxi)
+{
+ struct afu *afu = cfg->afu;
+
+ WARN_ON(!list_empty(&ctxi->luns));
+
+ /* Clear RHT registers and drop all capabilities for this context */
+ if (afu->afu_map && ctxi->ctrl_map) {
+ writeq_be(0, &ctxi->ctrl_map->rht_start);
+ writeq_be(0, &ctxi->ctrl_map->rht_cnt_id);
+ writeq_be(0, &ctxi->ctrl_map->ctx_cap);
+ }
+
+ /* Free memory associated with context */
+ free_page((ulong)ctxi->rht_start);
+ kfree(ctxi->rht_lun);
+ kfree(ctxi);
+ atomic_dec_if_positive(&cfg->num_user_contexts);
+}
+
+/**
+ * create_context() - allocates and initializes a context
+ * @cfg: Internal structure associated with the host.
+ * @ctx: Previously obtained CXL context reference.
+ * @ctxid: Previously obtained process element associated with CXL context.
+ * @adap_fd: Previously obtained adapter fd associated with CXL context.
+ * @file: Previously obtained file associated with CXL context.
+ * @perms: User-specified permissions.
+ *
+ * The context's mutex is locked when an allocated context is returned.
+ *
+ * Return: Allocated context on success, NULL on failure
+ */
+static struct ctx_info *create_context(struct cxlflash_cfg *cfg,
+ struct cxl_context *ctx, int ctxid,
+ int adap_fd, struct file *file,
+ u32 perms)
+{
+ struct device *dev = &cfg->dev->dev;
+ struct afu *afu = cfg->afu;
+ struct ctx_info *ctxi = NULL;
+ struct llun_info **lli = NULL;
+ struct sisl_rht_entry *rhte;
+
+ ctxi = kzalloc(sizeof(*ctxi), GFP_KERNEL);
+ lli = kzalloc((MAX_RHT_PER_CONTEXT * sizeof(*lli)), GFP_KERNEL);
+ if (unlikely(!ctxi || !lli)) {
+ dev_err(dev, "%s: Unable to allocate context!\n", __func__);
+ goto err;
+ }
+
+ rhte = (struct sisl_rht_entry *)get_zeroed_page(GFP_KERNEL);
+ if (unlikely(!rhte)) {
+ dev_err(dev, "%s: Unable to allocate RHT!\n", __func__);
+ goto err;
+ }
+
+ ctxi->rht_lun = lli;
+ ctxi->rht_start = rhte;
+ ctxi->rht_perms = perms;
+
+ ctxi->ctrl_map = &afu->afu_map->ctrls[ctxid].ctrl;
+ ctxi->ctxid = ENCODE_CTXID(ctxi, ctxid);
+ ctxi->lfd = adap_fd;
+ ctxi->pid = current->tgid; /* tgid = pid */
+ ctxi->ctx = ctx;
+ ctxi->file = file;
+ mutex_init(&ctxi->mutex);
+ 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;
+
+err:
+ kfree(lli);
+ kfree(ctxi);
+ ctxi = NULL;
+ goto out;
+}
+
+/**
+ * _cxlflash_disk_detach() - detaches a LUN from a context
+ * @sdev: SCSI device associated with LUN.
+ * @ctxi: Context owning resources.
+ * @detach: Detach ioctl data structure.
+ *
+ * As part of the detach, all per-context resources associated with the LUN
+ * are cleaned up. When detaching the last LUN for a context, the context
+ * itself is cleaned up and released.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+static int _cxlflash_disk_detach(struct scsi_device *sdev,
+ struct ctx_info *ctxi,
+ struct dk_cxlflash_detach *detach)
+{
+ struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata;
+ struct device *dev = &cfg->dev->dev;
+ struct llun_info *lli = sdev->hostdata;
+ struct lun_access *lun_access, *t;
+ struct dk_cxlflash_release rel;
+ bool put_ctx = false;
+
+ int i;
+ int rc = 0;
+ int lfd;
+ u64 ctxid = DECODE_CTXID(detach->context_id),
+ rctxid = detach->context_id;
+
+ dev_dbg(dev, "%s: ctxid=%llu\n", __func__, ctxid);
+
+ if (!ctxi) {
+ ctxi = get_context(cfg, rctxid, lli, CTX_CTRL_ERR_FALLBACK);
+ if (unlikely(!ctxi)) {
+ dev_dbg(dev, "%s: Bad context! (%llu)\n",
+ __func__, ctxid);
+ rc = -EINVAL;
+ goto out;
+ }
+
+ put_ctx = true;
+ }
+
+ /* Cleanup outstanding resources tied to this LUN */
+ if (ctxi->rht_out) {
+ marshal_det_to_rele(detach, &rel);
+ for (i = 0; i < MAX_RHT_PER_CONTEXT; i++) {
+ if (ctxi->rht_lun[i] == lli) {
+ rel.rsrc_handle = i;
+ _cxlflash_disk_release(sdev, ctxi, &rel);
+ }
+
+ /* No need to loop further if we're done */
+ if (ctxi->rht_out == 0)
+ break;
+ }
+ }
+
+ /* Take our LUN out of context, free the node */
+ list_for_each_entry_safe(lun_access, t, &ctxi->luns, list)
+ if (lun_access->lli == lli) {
+ list_del(&lun_access->list);
+ kfree(lun_access);
+ lun_access = NULL;
+ break;
+ }
+
+ /* Tear down context following last LUN cleanup */
+ if (list_empty(&ctxi->luns)) {
+ ctxi->unavail = true;
+ mutex_unlock(&ctxi->mutex);
+ mutex_lock(&cfg->ctx_tbl_list_mutex);
+ mutex_lock(&ctxi->mutex);
+
+ /* Might not have been in error list so conditionally remove */
+ if (!list_empty(&ctxi->list))
+ list_del(&ctxi->list);
+ cfg->ctx_tbl[ctxid] = NULL;
+ mutex_unlock(&cfg->ctx_tbl_list_mutex);
+ mutex_unlock(&ctxi->mutex);
+
+ lfd = ctxi->lfd;
+ destroy_context(cfg, ctxi);
+ ctxi = NULL;
+ put_ctx = false;
+
+ /*
+ * As a last step, clean up external resources when not
+ * already on an external cleanup thread, i.e.: close(adap_fd).
+ *
+ * NOTE: this will free up the context from the CXL services,
+ * allowing it to dole out the same context_id on a future
+ * (or even currently in-flight) disk_attach operation.
+ */
+ if (lfd != -1)
+ sys_close(lfd);
+ }
+
+out:
+ if (put_ctx)
+ put_context(ctxi);
+ dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
+ return rc;
+}
+
+static int cxlflash_disk_detach(struct scsi_device *sdev,
+ struct dk_cxlflash_detach *detach)
+{
+ return _cxlflash_disk_detach(sdev, NULL, detach);
+}
+
+/**
+ * cxlflash_cxl_release() - release handler for adapter file descriptor
+ * @inode: File-system inode associated with fd.
+ * @file: File installed with adapter file descriptor.
+ *
+ * This routine is the release handler for the fops registered with
+ * the CXL services on an initial attach for a context. It is called
+ * when a close is performed on the adapter file descriptor returned
+ * to the user. Programmatically, the user is not required to perform
+ * the close, as it is handled internally via the detach ioctl when
+ * a context is being removed. Note that nothing prevents the user
+ * from performing a close, but the user should be aware that doing
+ * so is considered catastrophic and subsequent usage of the superpipe
+ * API with previously saved off tokens will fail.
+ *
+ * When initiated from an external close (either by the user or via
+ * a process tear down), the routine derives the context reference
+ * and calls detach for each LUN associated with the context. The
+ * final detach operation will cause the context itself to be freed.
+ * Note that the saved off lfd is reset prior to calling detach to
+ * signify that the final detach should not perform a close.
+ *
+ * When initiated from a detach operation as part of the tear down
+ * of a context, the context is first completely freed and then the
+ * close is performed. This routine will fail to derive the context
+ * reference (due to the context having already been freed) and then
+ * call into the CXL release entry point.
+ *
+ * Thus, with exception to when the CXL process element (context id)
+ * lookup fails (a case that should theoretically never occur), every
+ * call into this routine results in a complete freeing of a context.
+ *
+ * As part of the detach, all per-context resources associated with the LUN
+ * are cleaned up. When detaching the last LUN for a context, the context
+ * itself is cleaned up and released.
+ *
+ * Return: 0 on success
+ */
+static int cxlflash_cxl_release(struct inode *inode, struct file *file)
+{
+ struct cxl_context *ctx = cxl_fops_get_context(file);
+ struct cxlflash_cfg *cfg = container_of(file->f_op, struct cxlflash_cfg,
+ cxl_fops);
+ struct device *dev = &cfg->dev->dev;
+ struct ctx_info *ctxi = NULL;
+ struct dk_cxlflash_detach detach = { { 0 }, 0 };
+ struct lun_access *lun_access, *t;
+ enum ctx_ctrl ctrl = CTX_CTRL_ERR_FALLBACK | CTX_CTRL_FILE;
+ int ctxid;
+
+ ctxid = cxl_process_element(ctx);
+ if (unlikely(ctxid < 0)) {
+ dev_err(dev, "%s: Context %p was closed! (%d)\n",
+ __func__, ctx, ctxid);
+ goto out;
+ }
+
+ ctxi = get_context(cfg, ctxid, file, ctrl);
+ if (unlikely(!ctxi)) {
+ ctxi = get_context(cfg, ctxid, file, ctrl | CTX_CTRL_CLONE);
+ if (!ctxi) {
+ dev_dbg(dev, "%s: Context %d already free!\n",
+ __func__, ctxid);
+ goto out_release;
+ }
+
+ dev_dbg(dev, "%s: Another process owns context %d!\n",
+ __func__, ctxid);
+ put_context(ctxi);
+ goto out;
+ }
+
+ dev_dbg(dev, "%s: close(%d) for context %d\n",
+ __func__, ctxi->lfd, ctxid);
+
+ /* Reset the file descriptor to indicate we're on a close() thread */
+ ctxi->lfd = -1;
+ detach.context_id = ctxi->ctxid;
+ list_for_each_entry_safe(lun_access, t, &ctxi->luns, list)
+ _cxlflash_disk_detach(lun_access->sdev, ctxi, &detach);
+out_release:
+ cxl_fd_release(inode, file);
+out:
+ dev_dbg(dev, "%s: returning\n", __func__);
+ return 0;
+}
+
+/**
+ * unmap_context() - clears a previously established mapping
+ * @ctxi: Context owning the mapping.
+ *
+ * This routine is used to switch between the error notification page
+ * (dummy page of all 1's) and the real mapping (established by the CXL
+ * fault handler).
+ */
+static void unmap_context(struct ctx_info *ctxi)
+{
+ unmap_mapping_range(ctxi->file->f_mapping, 0, 0, 1);
+}
+
+/**
+ * get_err_page() - obtains and allocates the error notification page
+ *
+ * Return: error notification page on success, NULL on failure
+ */
+static struct page *get_err_page(void)
+{
+ struct page *err_page = global.err_page;
+
+ if (unlikely(!err_page)) {
+ err_page = alloc_page(GFP_KERNEL);
+ if (unlikely(!err_page)) {
+ pr_err("%s: Unable to allocate err_page!\n", __func__);
+ goto out;
+ }
+
+ memset(page_address(err_page), -1, PAGE_SIZE);
+
+ /* Serialize update w/ other threads to avoid a leak */
+ mutex_lock(&global.mutex);
+ if (likely(!global.err_page))
+ global.err_page = err_page;
+ else {
+ __free_page(err_page);
+ err_page = global.err_page;
+ }
+ mutex_unlock(&global.mutex);
+ }
+
+out:
+ pr_debug("%s: returning err_page=%p\n", __func__, err_page);
+ return err_page;
+}
+
+/**
+ * cxlflash_mmap_fault() - mmap fault handler for adapter file descriptor
+ * @vma: VM area associated with mapping.
+ * @vmf: VM fault associated with current fault.
+ *
+ * To support error notification via MMIO, faults are 'caught' by this routine
+ * that was inserted before passing back the adapter file descriptor on attach.
+ * When a fault occurs, this routine evaluates if error recovery is active and
+ * if so, installs the error page to 'notify' the user about the error state.
+ * During normal operation, the fault is simply handled by the original fault
+ * handler that was installed by CXL services as part of initializing the
+ * adapter file descriptor. The VMA's page protection bits are toggled to
+ * indicate cached/not-cached depending on the memory backing the fault.
+ *
+ * Return: 0 on success, VM_FAULT_SIGBUS on failure
+ */
+static int cxlflash_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+ struct file *file = vma->vm_file;
+ struct cxl_context *ctx = cxl_fops_get_context(file);
+ struct cxlflash_cfg *cfg = container_of(file->f_op, struct cxlflash_cfg,
+ cxl_fops);
+ struct device *dev = &cfg->dev->dev;
+ struct ctx_info *ctxi = NULL;
+ struct page *err_page = NULL;
+ enum ctx_ctrl ctrl = CTX_CTRL_ERR_FALLBACK | CTX_CTRL_FILE;
+ int rc = 0;
+ int ctxid;
+
+ ctxid = cxl_process_element(ctx);
+ if (unlikely(ctxid < 0)) {
+ dev_err(dev, "%s: Context %p was closed! (%d)\n",
+ __func__, ctx, ctxid);
+ goto err;
+ }
+
+ ctxi = get_context(cfg, ctxid, file, ctrl);
+ if (unlikely(!ctxi)) {
+ dev_dbg(dev, "%s: Bad context! (%d)\n", __func__, ctxid);
+ goto err;
+ }
+
+ dev_dbg(dev, "%s: fault(%d) for context %d\n",
+ __func__, ctxi->lfd, ctxid);
+
+ if (likely(!ctxi->err_recovery_active)) {
+ vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+ rc = ctxi->cxl_mmap_vmops->fault(vma, vmf);
+ } else {
+ dev_dbg(dev, "%s: err recovery active, use err_page!\n",
+ __func__);
+
+ err_page = get_err_page();
+ if (unlikely(!err_page)) {
+ dev_err(dev, "%s: Could not obtain error page!\n",
+ __func__);
+ rc = VM_FAULT_RETRY;
+ goto out;
+ }
+
+ get_page(err_page);
+ vmf->page = err_page;
+ vma->vm_page_prot = pgprot_cached(vma->vm_page_prot);
+ }
+
+out:
+ if (likely(ctxi))
+ put_context(ctxi);
+ dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
+ return rc;
+
+err:
+ rc = VM_FAULT_SIGBUS;
+ goto out;
+}
+
+/*
+ * Local MMAP vmops to 'catch' faults
+ */
+static const struct vm_operations_struct cxlflash_mmap_vmops = {
+ .fault = cxlflash_mmap_fault,
+};
+
+/**
+ * cxlflash_cxl_mmap() - mmap handler for adapter file descriptor
+ * @file: File installed with adapter file descriptor.
+ * @vma: VM area associated with mapping.
+ *
+ * Installs local mmap vmops to 'catch' faults for error notification support.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+static int cxlflash_cxl_mmap(struct file *file, struct vm_area_struct *vma)
+{
+ struct cxl_context *ctx = cxl_fops_get_context(file);
+ struct cxlflash_cfg *cfg = container_of(file->f_op, struct cxlflash_cfg,
+ cxl_fops);
+ struct device *dev = &cfg->dev->dev;
+ struct ctx_info *ctxi = NULL;
+ enum ctx_ctrl ctrl = CTX_CTRL_ERR_FALLBACK | CTX_CTRL_FILE;
+ int ctxid;
+ int rc = 0;
+
+ ctxid = cxl_process_element(ctx);
+ if (unlikely(ctxid < 0)) {
+ dev_err(dev, "%s: Context %p was closed! (%d)\n",
+ __func__, ctx, ctxid);
+ rc = -EIO;
+ goto out;
+ }
+
+ ctxi = get_context(cfg, ctxid, file, ctrl);
+ if (unlikely(!ctxi)) {
+ dev_dbg(dev, "%s: Bad context! (%d)\n", __func__, ctxid);
+ rc = -EIO;
+ goto out;
+ }
+
+ dev_dbg(dev, "%s: mmap(%d) for context %d\n",
+ __func__, ctxi->lfd, ctxid);
+
+ rc = cxl_fd_mmap(file, vma);
+ if (likely(!rc)) {
+ /* Insert ourself in the mmap fault handler path */
+ ctxi->cxl_mmap_vmops = vma->vm_ops;
+ vma->vm_ops = &cxlflash_mmap_vmops;
+ }
+
+out:
+ if (likely(ctxi))
+ put_context(ctxi);
+ return rc;
+}
+
+/*
+ * Local fops for adapter file descriptor
+ */
+static const struct file_operations cxlflash_cxl_fops = {
+ .owner = THIS_MODULE,
+ .mmap = cxlflash_cxl_mmap,
+ .release = cxlflash_cxl_release,
+};
+
+/**
+ * cxlflash_mark_contexts_error() - move contexts to error state and list
+ * @cfg: Internal structure associated with the host.
+ *
+ * A context is only moved over to the error list when there are no outstanding
+ * references to it. This ensures that a running operation has completed.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+int cxlflash_mark_contexts_error(struct cxlflash_cfg *cfg)
+{
+ int i, rc = 0;
+ struct ctx_info *ctxi = NULL;
+
+ mutex_lock(&cfg->ctx_tbl_list_mutex);
+
+ for (i = 0; i < MAX_CONTEXT; i++) {
+ ctxi = cfg->ctx_tbl[i];
+ if (ctxi) {
+ mutex_lock(&ctxi->mutex);
+ cfg->ctx_tbl[i] = NULL;
+ list_add(&ctxi->list, &cfg->ctx_err_recovery);
+ ctxi->err_recovery_active = true;
+ ctxi->ctrl_map = NULL;
+ unmap_context(ctxi);
+ mutex_unlock(&ctxi->mutex);
+ }
+ }
+
+ mutex_unlock(&cfg->ctx_tbl_list_mutex);
+ return rc;
+}
+
+/*
+ * Dummy NULL fops
+ */
+static const struct file_operations null_fops = {
+ .owner = THIS_MODULE,
+};
+
+/**
+ * cxlflash_disk_attach() - attach a LUN to a context
+ * @sdev: SCSI device associated with LUN.
+ * @attach: Attach ioctl data structure.
+ *
+ * Creates a context and attaches LUN to it. A LUN can only be attached
+ * one time to a context (subsequent attaches for the same context/LUN pair
+ * are not supported). Additional LUNs can be attached to a context by
+ * specifying the 'reuse' flag defined in the cxlflash_ioctl.h header.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+static int cxlflash_disk_attach(struct scsi_device *sdev,
+ struct dk_cxlflash_attach *attach)
+{
+ struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata;
+ struct device *dev = &cfg->dev->dev;
+ struct afu *afu = cfg->afu;
+ struct llun_info *lli = sdev->hostdata;
+ struct glun_info *gli = lli->parent;
+ struct cxl_ioctl_start_work *work;
+ struct ctx_info *ctxi = NULL;
+ struct lun_access *lun_access = NULL;
+ int rc = 0;
+ u32 perms;
+ int ctxid = -1;
+ u64 rctxid = 0UL;
+ struct file *file;
+
+ struct cxl_context *ctx;
+
+ 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);
+ rc = -EINVAL;
+ goto out;
+ }
+
+ if (gli->max_lba == 0) {
+ dev_dbg(dev, "%s: No capacity info for this LUN (%016llX)\n",
+ __func__, lli->lun_id[sdev->channel]);
+ rc = read_cap16(sdev, lli);
+ if (rc) {
+ dev_err(dev, "%s: Invalid device! (%d)\n",
+ __func__, rc);
+ rc = -ENODEV;
+ goto out;
+ }
+ dev_dbg(dev, "%s: LBA = %016llX\n", __func__, gli->max_lba);
+ dev_dbg(dev, "%s: BLK_LEN = %08X\n", __func__, gli->blk_len);
+ }
+
+ if (attach->hdr.flags & DK_CXLFLASH_ATTACH_REUSE_CONTEXT) {
+ rctxid = attach->context_id;
+ ctxi = get_context(cfg, rctxid, NULL, 0);
+ if (!ctxi) {
+ dev_dbg(dev, "%s: Bad context! (%016llX)\n",
+ __func__, rctxid);
+ rc = -EINVAL;
+ goto out;
+ }
+
+ list_for_each_entry(lun_access, &ctxi->luns, list)
+ if (lun_access->lli == lli) {
+ dev_dbg(dev, "%s: Already attached!\n",
+ __func__);
+ rc = -EINVAL;
+ 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;
+ }
+
+ lun_access->lli = lli;
+ lun_access->sdev = sdev;
+
+ /* Non-NULL context indicates reuse */
+ if (ctxi) {
+ dev_dbg(dev, "%s: Reusing context for LUN! (%016llX)\n",
+ __func__, rctxid);
+ list_add(&lun_access->list, &ctxi->luns);
+ fd = ctxi->lfd;
+ goto out_attach;
+ }
+
+ ctx = cxl_dev_context_init(cfg->dev);
+ if (unlikely(IS_ERR_OR_NULL(ctx))) {
+ dev_err(dev, "%s: Could not initialize context %p\n",
+ __func__, ctx);
+ rc = -ENODEV;
+ goto err0;
+ }
+
+ 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;
+ }
+
+ 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;
+ }
+
+ /* Translate read/write O_* flags from fcntl.h to AFU permission bits */
+ perms = SISL_RHT_PERM(attach->hdr.flags + 1);
+
+ ctxi = create_context(cfg, ctx, ctxid, fd, file, perms);
+ if (unlikely(!ctxi)) {
+ dev_err(dev, "%s: Failed to create context! (%d)\n",
+ __func__, ctxid);
+ goto err2;
+ }
+
+ work = &ctxi->work;
+ work->num_interrupts = attach->num_interrupts;
+ work->flags = CXL_START_WORK_NUM_IRQS;
+
+ rc = cxl_start_work(ctx, work);
+ if (unlikely(rc)) {
+ dev_dbg(dev, "%s: Could not start context rc=%d\n",
+ __func__, rc);
+ goto err3;
+ }
+
+ rc = afu_attach(cfg, ctxi);
+ if (unlikely(rc)) {
+ dev_err(dev, "%s: Could not attach AFU rc %d\n", __func__, rc);
+ goto err4;
+ }
+
+ /*
+ * No error paths after this point. Once the fd is installed it's
+ * visible to user space and can't be undone safely on this thread.
+ * There is no need to worry about a deadlock here because no one
+ * knows about us yet; we can be the only one holding our mutex.
+ */
+ list_add(&lun_access->list, &ctxi->luns);
+ mutex_unlock(&ctxi->mutex);
+ mutex_lock(&cfg->ctx_tbl_list_mutex);
+ mutex_lock(&ctxi->mutex);
+ cfg->ctx_tbl[ctxid] = ctxi;
+ mutex_unlock(&cfg->ctx_tbl_list_mutex);
+ fd_install(fd, file);
+
+out_attach:
+ attach->hdr.return_flags = 0;
+ attach->context_id = ctxi->ctxid;
+ 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;
+
+out:
+ attach->adap_fd = fd;
+
+ if (ctxi)
+ put_context(ctxi);
+
+ dev_dbg(dev, "%s: returning ctxid=%d fd=%d bs=%lld rc=%d llba=%lld\n",
+ __func__, ctxid, fd, attach->block_size, rc, attach->last_lba);
+ return rc;
+
+err4:
+ cxl_stop_context(ctx);
+err3:
+ put_context(ctxi);
+ destroy_context(cfg, ctxi);
+ ctxi = NULL;
+err2:
+ /*
+ * Here, we're overriding the fops with a dummy all-NULL fops because
+ * fput() calls the release fop, which will cause us to mistakenly
+ * call into the CXL code. Rather than try to add yet more complexity
+ * to that routine (cxlflash_cxl_release) we should try to fix the
+ * issue here.
+ */
+ file->f_op = &null_fops;
+ fput(file);
+ put_unused_fd(fd);
+ fd = -1;
+err1:
+ cxl_release_context(ctx);
+err0:
+ kfree(lun_access);
+ goto out;
+}
+
+/**
+ * recover_context() - recovers a context in error
+ * @cfg: Internal structure associated with the host.
+ * @ctxi: Context to release.
+ *
+ * Restablishes the state for a context-in-error.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+static int recover_context(struct cxlflash_cfg *cfg, struct ctx_info *ctxi)
+{
+ struct device *dev = &cfg->dev->dev;
+ int rc = 0;
+ int old_fd, fd = -1;
+ int ctxid = -1;
+ struct file *file;
+ struct cxl_context *ctx;
+ struct afu *afu = cfg->afu;
+
+ ctx = cxl_dev_context_init(cfg->dev);
+ if (unlikely(IS_ERR_OR_NULL(ctx))) {
+ dev_err(dev, "%s: Could not initialize context %p\n",
+ __func__, ctx);
+ rc = -ENODEV;
+ goto out;
+ }
+
+ 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;
+ }
+
+ 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;
+ }
+
+ rc = cxl_start_work(ctx, &ctxi->work);
+ if (unlikely(rc)) {
+ dev_dbg(dev, "%s: Could not start context rc=%d\n",
+ __func__, rc);
+ goto err2;
+ }
+
+ /* Update with new MMIO area based on updated context id */
+ ctxi->ctrl_map = &afu->afu_map->ctrls[ctxid].ctrl;
+
+ rc = afu_attach(cfg, ctxi);
+ if (rc) {
+ dev_err(dev, "%s: Could not attach AFU rc %d\n", __func__, rc);
+ goto err3;
+ }
+
+ /*
+ * No error paths after this point. Once the fd is installed it's
+ * visible to user space and can't be undone safely on this thread.
+ */
+ old_fd = ctxi->lfd;
+ ctxi->ctxid = ENCODE_CTXID(ctxi, ctxid);
+ ctxi->lfd = fd;
+ ctxi->ctx = ctx;
+ ctxi->file = file;
+
+ /*
+ * Put context back in table (note the reinit of the context list);
+ * we must first drop the context's mutex and then acquire it in
+ * order with the table/list mutex to avoid a deadlock - safe to do
+ * here because no one can find us at this moment in time.
+ */
+ mutex_unlock(&ctxi->mutex);
+ mutex_lock(&cfg->ctx_tbl_list_mutex);
+ mutex_lock(&ctxi->mutex);
+ list_del_init(&ctxi->list);
+ cfg->ctx_tbl[ctxid] = ctxi;
+ mutex_unlock(&cfg->ctx_tbl_list_mutex);
+ fd_install(fd, file);
+
+ /* Release the original adapter fd and associated CXL resources */
+ sys_close(old_fd);
+out:
+ dev_dbg(dev, "%s: returning ctxid=%d fd=%d rc=%d\n",
+ __func__, ctxid, fd, rc);
+ return rc;
+
+err3:
+ cxl_stop_context(ctx);
+err2:
+ fput(file);
+ put_unused_fd(fd);
+err1:
+ cxl_release_context(ctx);
+ 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.
+ * @recover: Recover ioctl data structure.
+ *
+ * Only a single recovery is allowed at a time to avoid exhausting CXL
+ * resources (leading to recovery failure) in the event that we're up
+ * against the maximum number of contexts limit. For similar reasons,
+ * a context recovery is retried if there are multiple recoveries taking
+ * place at the same time and the failure was due to CXL services being
+ * unable to keep up.
+ *
+ * Because a user can detect an error condition before the kernel, it is
+ * 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
+ * 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().
+ *
+ * Return: 0 on success, -errno on failure
+ */
+static int cxlflash_afu_recover(struct scsi_device *sdev,
+ struct dk_cxlflash_recover_afu *recover)
+{
+ struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata;
+ struct device *dev = &cfg->dev->dev;
+ struct llun_info *lli = sdev->hostdata;
+ struct afu *afu = cfg->afu;
+ struct ctx_info *ctxi = NULL;
+ struct mutex *mutex = &cfg->ctx_recovery_mutex;
+ u64 ctxid = DECODE_CTXID(recover->context_id),
+ rctxid = recover->context_id;
+ long reg;
+ int lretry = 20; /* up to 2 seconds */
+ int rc = 0;
+
+ atomic_inc(&cfg->recovery_threads);
+ rc = mutex_lock_interruptible(mutex);
+ if (rc)
+ goto out;
+
+ dev_dbg(dev, "%s: reason 0x%016llX rctxid=%016llX\n",
+ __func__, recover->reason, rctxid);
+
+retry:
+ /* Ensure that this process is attached to the context */
+ ctxi = get_context(cfg, rctxid, lli, CTX_CTRL_ERR_FALLBACK);
+ if (unlikely(!ctxi)) {
+ dev_dbg(dev, "%s: Bad context! (%llu)\n", __func__, ctxid);
+ rc = -EINVAL;
+ goto out;
+ }
+
+ if (ctxi->err_recovery_active) {
+retry_recover:
+ rc = recover_context(cfg, ctxi);
+ if (unlikely(rc)) {
+ dev_err(dev, "%s: Recovery failed for context %llu (rc=%d)\n",
+ __func__, ctxid, rc);
+ if ((rc == -ENODEV) &&
+ ((atomic_read(&cfg->recovery_threads) > 1) ||
+ (lretry--))) {
+ dev_dbg(dev, "%s: Going to try again!\n",
+ __func__);
+ mutex_unlock(mutex);
+ msleep(100);
+ rc = mutex_lock_interruptible(mutex);
+ if (rc)
+ goto out;
+ goto retry_recover;
+ }
+
+ goto out;
+ }
+
+ ctxi->err_recovery_active = false;
+ recover->context_id = ctxi->ctxid;
+ recover->adap_fd = ctxi->lfd;
+ recover->mmio_size = sizeof(afu->afu_map->hosts[0].harea);
+ recover->hdr.return_flags |=
+ DK_CXLFLASH_RECOVER_AFU_CONTEXT_RESET;
+ goto out;
+ }
+
+ /* 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);
+ ctxi = NULL;
+ ssleep(1);
+ rc = check_state(cfg);
+ if (unlikely(rc))
+ goto out;
+ goto retry;
+ }
+
+ dev_dbg(dev, "%s: MMIO working, no recovery required!\n", __func__);
+out:
+ if (likely(ctxi))
+ put_context(ctxi);
+ mutex_unlock(mutex);
+ atomic_dec_if_positive(&cfg->recovery_threads);
+ return rc;
+}
+
+/**
+ * process_sense() - evaluates and processes sense data
+ * @sdev: SCSI device associated with LUN.
+ * @verify: Verify ioctl data structure.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+static int process_sense(struct scsi_device *sdev,
+ struct dk_cxlflash_verify *verify)
+{
+ struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata;
+ struct device *dev = &cfg->dev->dev;
+ struct llun_info *lli = sdev->hostdata;
+ struct glun_info *gli = lli->parent;
+ u64 prev_lba = gli->max_lba;
+ struct scsi_sense_hdr sshdr = { 0 };
+ int rc = 0;
+
+ rc = scsi_normalize_sense((const u8 *)&verify->sense_data,
+ DK_CXLFLASH_VERIFY_SENSE_LEN, &sshdr);
+ if (!rc) {
+ dev_err(dev, "%s: Failed to normalize sense data!\n", __func__);
+ rc = -EINVAL;
+ goto out;
+ }
+
+ switch (sshdr.sense_key) {
+ case NO_SENSE:
+ case RECOVERED_ERROR:
+ /* fall through */
+ case NOT_READY:
+ break;
+ case UNIT_ATTENTION:
+ switch (sshdr.asc) {
+ case 0x29: /* Power on Reset or Device Reset */
+ /* fall through */
+ case 0x2A: /* Device settings/capacity changed */
+ rc = read_cap16(sdev, lli);
+ if (rc) {
+ rc = -ENODEV;
+ break;
+ }
+ if (prev_lba != gli->max_lba)
+ dev_dbg(dev, "%s: Capacity changed old=%lld "
+ "new=%lld\n", __func__, prev_lba,
+ gli->max_lba);
+ break;
+ case 0x3F: /* Report LUNs changed, Rescan. */
+ scsi_scan_host(cfg->host);
+ break;
+ default:
+ rc = -EIO;
+ break;
+ }
+ break;
+ default:
+ rc = -EIO;
+ break;
+ }
+out:
+ dev_dbg(dev, "%s: sense_key %x asc %x ascq %x rc %d\n", __func__,
+ sshdr.sense_key, sshdr.asc, sshdr.ascq, rc);
+ return rc;
+}
+
+/**
+ * cxlflash_disk_verify() - verifies a LUN is the same and handle size changes
+ * @sdev: SCSI device associated with LUN.
+ * @verify: Verify ioctl data structure.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+static int cxlflash_disk_verify(struct scsi_device *sdev,
+ struct dk_cxlflash_verify *verify)
+{
+ int rc = 0;
+ struct ctx_info *ctxi = NULL;
+ struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata;
+ struct device *dev = &cfg->dev->dev;
+ struct llun_info *lli = sdev->hostdata;
+ struct glun_info *gli = lli->parent;
+ struct sisl_rht_entry *rhte = NULL;
+ res_hndl_t rhndl = verify->rsrc_handle;
+ u64 ctxid = DECODE_CTXID(verify->context_id),
+ rctxid = verify->context_id;
+ u64 last_lba = 0;
+
+ dev_dbg(dev, "%s: ctxid=%llu rhndl=%016llX, hint=%016llX, "
+ "flags=%016llX\n", __func__, ctxid, verify->rsrc_handle,
+ verify->hint, verify->hdr.flags);
+
+ ctxi = get_context(cfg, rctxid, lli, 0);
+ if (unlikely(!ctxi)) {
+ dev_dbg(dev, "%s: Bad context! (%llu)\n", __func__, ctxid);
+ rc = -EINVAL;
+ goto out;
+ }
+
+ rhte = get_rhte(ctxi, rhndl, lli);
+ if (unlikely(!rhte)) {
+ dev_dbg(dev, "%s: Bad resource handle! (%d)\n",
+ __func__, rhndl);
+ rc = -EINVAL;
+ goto out;
+ }
+
+ /*
+ * Look at the hint/sense to see if it requires us to redrive
+ * inquiry (i.e. the Unit attention is due to the WWN changing).
+ */
+ if (verify->hint & DK_CXLFLASH_VERIFY_HINT_SENSE) {
+ rc = process_sense(sdev, verify);
+ if (unlikely(rc)) {
+ dev_err(dev, "%s: Failed to validate sense data (%d)\n",
+ __func__, rc);
+ goto out;
+ }
+ }
+
+ switch (gli->mode) {
+ case MODE_PHYSICAL:
+ last_lba = gli->max_lba;
+ break;
+ default:
+ WARN(1, "Unsupported LUN mode!");
+ }
+
+ verify->last_lba = last_lba;
+
+out:
+ if (likely(ctxi))
+ put_context(ctxi);
+ dev_dbg(dev, "%s: returning rc=%d llba=%llX\n",
+ __func__, rc, verify->last_lba);
+ return rc;
+}
+
+/**
+ * decode_ioctl() - translates an encoded ioctl to an easily identifiable string
+ * @cmd: The ioctl command to decode.
+ *
+ * Return: A string identifying the decoded ioctl.
+ */
+static char *decode_ioctl(int cmd)
+{
+ switch (cmd) {
+ case DK_CXLFLASH_ATTACH:
+ return __stringify_1(DK_CXLFLASH_ATTACH);
+ case DK_CXLFLASH_USER_DIRECT:
+ return __stringify_1(DK_CXLFLASH_USER_DIRECT);
+ case DK_CXLFLASH_RELEASE:
+ return __stringify_1(DK_CXLFLASH_RELEASE);
+ case DK_CXLFLASH_DETACH:
+ return __stringify_1(DK_CXLFLASH_DETACH);
+ case DK_CXLFLASH_VERIFY:
+ return __stringify_1(DK_CXLFLASH_VERIFY);
+ case DK_CXLFLASH_RECOVER_AFU:
+ return __stringify_1(DK_CXLFLASH_RECOVER_AFU);
+ case DK_CXLFLASH_MANAGE_LUN:
+ return __stringify_1(DK_CXLFLASH_MANAGE_LUN);
+ }
+
+ return "UNKNOWN";
+}
+
+/**
+ * cxlflash_disk_direct_open() - opens a direct (physical) disk
+ * @sdev: SCSI device associated with LUN.
+ * @arg: UDirect ioctl data structure.
+ *
+ * On successful return, the user is informed of the resource handle
+ * to be used to identify the direct lun and the size (in blocks) of
+ * the direct lun in last LBA format.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+static int cxlflash_disk_direct_open(struct scsi_device *sdev, void *arg)
+{
+ struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata;
+ struct device *dev = &cfg->dev->dev;
+ struct afu *afu = cfg->afu;
+ struct llun_info *lli = sdev->hostdata;
+ struct glun_info *gli = lli->parent;
+
+ struct dk_cxlflash_udirect *pphys = (struct dk_cxlflash_udirect *)arg;
+
+ u64 ctxid = DECODE_CTXID(pphys->context_id),
+ rctxid = pphys->context_id;
+ u64 lun_size = 0;
+ u64 last_lba = 0;
+ u64 rsrc_handle = -1;
+ u32 port = CHAN2PORT(sdev->channel);
+
+ int rc = 0;
+
+ struct ctx_info *ctxi = NULL;
+ struct sisl_rht_entry *rhte = NULL;
+
+ pr_debug("%s: ctxid=%llu ls=0x%llx\n", __func__, ctxid, lun_size);
+
+ rc = cxlflash_lun_attach(gli, MODE_PHYSICAL, false);
+ if (unlikely(rc)) {
+ dev_dbg(dev, "%s: Failed to attach to LUN! (PHYSICAL)\n",
+ __func__);
+ goto out;
+ }
+
+ ctxi = get_context(cfg, rctxid, lli, 0);
+ if (unlikely(!ctxi)) {
+ dev_dbg(dev, "%s: Bad context! (%llu)\n", __func__, ctxid);
+ rc = -EINVAL;
+ goto err1;
+ }
+
+ rhte = rhte_checkout(ctxi, lli);
+ if (unlikely(!rhte)) {
+ dev_dbg(dev, "%s: too many opens for this context\n", __func__);
+ rc = -EMFILE; /* too many opens */
+ goto err1;
+ }
+
+ rsrc_handle = (rhte - ctxi->rht_start);
+
+ rht_format1(rhte, lli->lun_id[sdev->channel], ctxi->rht_perms, port);
+ cxlflash_afu_sync(afu, ctxid, rsrc_handle, AFU_LW_SYNC);
+
+ last_lba = gli->max_lba;
+ pphys->hdr.return_flags = 0;
+ pphys->last_lba = last_lba;
+ pphys->rsrc_handle = rsrc_handle;
+
+out:
+ if (likely(ctxi))
+ put_context(ctxi);
+ dev_dbg(dev, "%s: returning handle 0x%llx rc=%d llba %lld\n",
+ __func__, rsrc_handle, rc, last_lba);
+ return rc;
+
+err1:
+ cxlflash_lun_detach(gli);
+ goto out;
+}
+
+/**
+ * ioctl_common() - common IOCTL handler for driver
+ * @sdev: SCSI device associated with LUN.
+ * @cmd: IOCTL command.
+ *
+ * Handles common fencing operations that are valid for multiple ioctls. Always
+ * allow through ioctls that are cleanup oriented in nature, even when operating
+ * in a failed/terminating state.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+static int ioctl_common(struct scsi_device *sdev, int cmd)
+{
+ struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata;
+ struct device *dev = &cfg->dev->dev;
+ struct llun_info *lli = sdev->hostdata;
+ int rc = 0;
+
+ if (unlikely(!lli)) {
+ dev_dbg(dev, "%s: Unknown LUN\n", __func__);
+ rc = -EINVAL;
+ goto out;
+ }
+
+ rc = check_state(cfg);
+ if (unlikely(rc) && (cfg->state == STATE_FAILTERM)) {
+ switch (cmd) {
+ case DK_CXLFLASH_RELEASE:
+ case DK_CXLFLASH_DETACH:
+ dev_dbg(dev, "%s: Command override! (%d)\n",
+ __func__, rc);
+ rc = 0;
+ break;
+ }
+ }
+out:
+ return rc;
+}
+
+/**
+ * cxlflash_ioctl() - IOCTL handler for driver
+ * @sdev: SCSI device associated with LUN.
+ * @cmd: IOCTL command.
+ * @arg: Userspace ioctl data structure.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+int cxlflash_ioctl(struct scsi_device *sdev, int cmd, void __user *arg)
+{
+ typedef int (*sioctl) (struct scsi_device *, void *);
+
+ struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata;
+ struct device *dev = &cfg->dev->dev;
+ struct afu *afu = cfg->afu;
+ struct dk_cxlflash_hdr *hdr;
+ char buf[sizeof(union cxlflash_ioctls)];
+ size_t size = 0;
+ bool known_ioctl = false;
+ int idx;
+ int rc = 0;
+ struct Scsi_Host *shost = sdev->host;
+ sioctl do_ioctl = NULL;
+
+ static const struct {
+ size_t size;
+ sioctl ioctl;
+ } ioctl_tbl[] = { /* NOTE: order matters here */
+ {sizeof(struct dk_cxlflash_attach), (sioctl)cxlflash_disk_attach},
+ {sizeof(struct dk_cxlflash_udirect), cxlflash_disk_direct_open},
+ {sizeof(struct dk_cxlflash_release), (sioctl)cxlflash_disk_release},
+ {sizeof(struct dk_cxlflash_detach), (sioctl)cxlflash_disk_detach},
+ {sizeof(struct dk_cxlflash_verify), (sioctl)cxlflash_disk_verify},
+ {sizeof(struct dk_cxlflash_recover_afu), (sioctl)cxlflash_afu_recover},
+ {sizeof(struct dk_cxlflash_manage_lun), (sioctl)cxlflash_manage_lun},
+ };
+
+ /* Restrict command set to physical support only for internal LUN */
+ if (afu->internal_lun)
+ switch (cmd) {
+ case DK_CXLFLASH_RELEASE:
+ dev_dbg(dev, "%s: %s not supported for lun_mode=%d\n",
+ __func__, decode_ioctl(cmd), afu->internal_lun);
+ rc = -EINVAL;
+ goto cxlflash_ioctl_exit;
+ }
+
+ switch (cmd) {
+ case DK_CXLFLASH_ATTACH:
+ case DK_CXLFLASH_USER_DIRECT:
+ case DK_CXLFLASH_RELEASE:
+ case DK_CXLFLASH_DETACH:
+ case DK_CXLFLASH_VERIFY:
+ case DK_CXLFLASH_RECOVER_AFU:
+ dev_dbg(dev, "%s: %s (%08X) on dev(%d/%d/%d/%llu)\n",
+ __func__, decode_ioctl(cmd), cmd, shost->host_no,
+ sdev->channel, sdev->id, sdev->lun);
+ rc = ioctl_common(sdev, cmd);
+ if (unlikely(rc))
+ goto cxlflash_ioctl_exit;
+
+ /* fall through */
+
+ case DK_CXLFLASH_MANAGE_LUN:
+ known_ioctl = true;
+ idx = _IOC_NR(cmd) - _IOC_NR(DK_CXLFLASH_ATTACH);
+ size = ioctl_tbl[idx].size;
+ do_ioctl = ioctl_tbl[idx].ioctl;
+
+ if (likely(do_ioctl))
+ break;
+
+ /* fall through */
+ default:
+ rc = -EINVAL;
+ goto cxlflash_ioctl_exit;
+ }
+
+ if (unlikely(copy_from_user(&buf, arg, size))) {
+ dev_err(dev, "%s: copy_from_user() fail! "
+ "size=%lu cmd=%d (%s) arg=%p\n",
+ __func__, size, cmd, decode_ioctl(cmd), arg);
+ rc = -EFAULT;
+ goto cxlflash_ioctl_exit;
+ }
+
+ hdr = (struct dk_cxlflash_hdr *)&buf;
+ if (hdr->version != DK_CXLFLASH_VERSION_0) {
+ dev_dbg(dev, "%s: Version %u not supported for %s\n",
+ __func__, hdr->version, decode_ioctl(cmd));
+ rc = -EINVAL;
+ goto cxlflash_ioctl_exit;
+ }
+
+ if (hdr->rsvd[0] || hdr->rsvd[1] || hdr->rsvd[2] || hdr->return_flags) {
+ dev_dbg(dev, "%s: Reserved/rflags populated!\n", __func__);
+ rc = -EINVAL;
+ goto cxlflash_ioctl_exit;
+ }
+
+ rc = do_ioctl(sdev, (void *)&buf);
+ if (likely(!rc))
+ if (unlikely(copy_to_user(arg, &buf, size))) {
+ dev_err(dev, "%s: copy_to_user() fail! "
+ "size=%lu cmd=%d (%s) arg=%p\n",
+ __func__, size, cmd, decode_ioctl(cmd), arg);
+ rc = -EFAULT;
+ }
+
+ /* fall through to exit */
+
+cxlflash_ioctl_exit:
+ if (unlikely(rc && known_ioctl))
+ dev_err(dev, "%s: ioctl %s (%08X) on dev(%d/%d/%d/%llu) "
+ "returned rc %d\n", __func__,
+ decode_ioctl(cmd), cmd, shost->host_no,
+ sdev->channel, sdev->id, sdev->lun, rc);
+ else
+ dev_dbg(dev, "%s: ioctl %s (%08X) on dev(%d/%d/%d/%llu) "
+ "returned rc %d\n", __func__, decode_ioctl(cmd),
+ cmd, shost->host_no, sdev->channel, sdev->id,
+ sdev->lun, rc);
+ return rc;
+}
new file mode 100644
@@ -0,0 +1,132 @@
+/*
+ * 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_SUPERPIPE_H
+#define _CXLFLASH_SUPERPIPE_H
+
+extern struct cxlflash_global global;
+
+/*
+ * Terminology: use afu (and not adapter) to refer to the HW.
+ * Adapter is the entire slot and includes PSL out of which
+ * only the AFU is visible to user space.
+ */
+
+/* Chunk size parms: note sislite minimum chunk size is
+ 0x10000 LBAs corresponding to a NMASK or 16.
+*/
+#define MC_CHUNK_SIZE (1 << MC_RHT_NMASK) /* in LBAs */
+
+#define MC_DISCOVERY_TIMEOUT 5 /* 5 secs */
+
+#define CHAN2PORT(_x) ((_x) + 1)
+
+enum lun_mode {
+ MODE_NONE = 0,
+ MODE_PHYSICAL
+};
+
+/* Global (entire driver, spans adapters) lun_info structure */
+struct glun_info {
+ u64 max_lba; /* from read cap(16) */
+ u32 blk_len; /* from read cap(16) */
+ enum lun_mode mode; /* NONE, PHYSICAL */
+ int users; /* Number of users w/ references to LUN */
+
+ u8 wwid[16];
+
+ struct mutex mutex;
+
+ struct list_head list;
+};
+
+/* Local (per-adapter) lun_info structure */
+struct llun_info {
+ u64 lun_id[CXLFLASH_NUM_FC_PORTS]; /* from REPORT_LUNS */
+ 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 */
+
+ u8 wwid[16]; /* Keep a duplicate copy here? */
+
+ struct glun_info *parent; /* Pointer to entry in global LUN structure */
+ struct scsi_device *sdev;
+ struct list_head list;
+};
+
+struct lun_access {
+ struct llun_info *lli;
+ struct scsi_device *sdev;
+ struct list_head list;
+};
+
+enum ctx_ctrl {
+ CTX_CTRL_CLONE = (1 << 1),
+ CTX_CTRL_ERR = (1 << 2),
+ CTX_CTRL_ERR_FALLBACK = (1 << 3),
+ CTX_CTRL_NOPID = (1 << 4),
+ CTX_CTRL_FILE = (1 << 5)
+};
+
+#define ENCODE_CTXID(_ctx, _id) (((((u64)_ctx) & 0xFFFFFFFF0) << 28) | _id)
+#define DECODE_CTXID(_val) (_val & 0xFFFFFFFF)
+
+struct ctx_info {
+ struct sisl_ctrl_map *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 */
+
+ struct cxl_ioctl_start_work work;
+ u64 ctxid;
+ int lfd;
+ pid_t pid;
+ bool unavail;
+ bool err_recovery_active;
+ struct mutex mutex; /* Context protection */
+ struct cxl_context *ctx;
+ struct list_head luns; /* LUNs attached to this context */
+ const struct vm_operations_struct *cxl_mmap_vmops;
+ struct file *file;
+ struct list_head list; /* Link contexts in error recovery */
+};
+
+struct cxlflash_global {
+ struct mutex mutex;
+ struct list_head gluns;/* list of glun_info structs */
+ struct page *err_page; /* One page of all 0xF for error notification */
+};
+
+int cxlflash_disk_release(struct scsi_device *, struct dk_cxlflash_release *);
+int _cxlflash_disk_release(struct scsi_device *, struct ctx_info *,
+ struct dk_cxlflash_release *);
+
+int cxlflash_lun_attach(struct glun_info *, enum lun_mode, bool);
+void cxlflash_lun_detach(struct glun_info *);
+
+struct ctx_info *get_context(struct cxlflash_cfg *, u64, void *, enum ctx_ctrl);
+void put_context(struct ctx_info *);
+
+struct sisl_rht_entry *get_rhte(struct ctx_info *, res_hndl_t,
+ struct llun_info *);
+
+struct sisl_rht_entry *rhte_checkout(struct ctx_info *, struct llun_info *);
+void rhte_checkin(struct ctx_info *, struct sisl_rht_entry *);
+
+int cxlflash_manage_lun(struct scsi_device *, struct dk_cxlflash_manage_lun *);
+
+#endif /* ifndef _CXLFLASH_SUPERPIPE_H */
@@ -3,3 +3,4 @@ header-y += fc/
header-y += scsi_bsg_fc.h
header-y += scsi_netlink.h
header-y += scsi_netlink_fc.h
+header-y += cxlflash_ioctl.h
new file mode 100644
@@ -0,0 +1,140 @@
+/*
+ * 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_IOCTL_H
+#define _CXLFLASH_IOCTL_H
+
+#include <linux/types.h>
+
+/*
+ * Structure and flag definitions CXL Flash superpipe ioctls
+ */
+
+#define DK_CXLFLASH_VERSION_0 0
+
+struct dk_cxlflash_hdr {
+ __u16 version; /* Version data */
+ __u16 rsvd[3]; /* Reserved for future use */
+ __u64 flags; /* Input flags */
+ __u64 return_flags; /* Returned flags */
+};
+
+/*
+ * Notes:
+ * -----
+ * The 'context_id' field of all ioctl structures contains the context
+ * identifier for a context in the lower 32-bits (upper 32-bits are not
+ * to be used when identifying a context to the AFU). That said, the value
+ * in its entirety (all 64-bits) is to be treated as an opaque cookie and
+ * should be presented as such when issuing ioctls.
+ *
+ * For DK_CXLFLASH_ATTACH ioctl, user specifies read/write access
+ * permissions via the O_RDONLY, O_WRONLY, and O_RDWR flags defined in
+ * the fcntl.h header file.
+ */
+#define DK_CXLFLASH_ATTACH_REUSE_CONTEXT 0x8000000000000000ULL
+
+struct dk_cxlflash_attach {
+ struct dk_cxlflash_hdr hdr; /* Common fields */
+ __u64 num_interrupts; /* Requested number of interrupts */
+ __u64 context_id; /* Returned context */
+ __u64 mmio_size; /* Returned size of MMIO area */
+ __u64 block_size; /* Returned block size, in bytes */
+ __u64 adap_fd; /* Returned adapter file descriptor */
+ __u64 last_lba; /* Returned last LBA on the device */
+ __u64 max_xfer; /* Returned max transfer size, blocks */
+ __u64 reserved[8]; /* Reserved for future use */
+};
+
+struct dk_cxlflash_detach {
+ struct dk_cxlflash_hdr hdr; /* Common fields */
+ __u64 context_id; /* Context to detach */
+ __u64 reserved[8]; /* Reserved for future use */
+};
+
+struct dk_cxlflash_udirect {
+ struct dk_cxlflash_hdr hdr; /* Common fields */
+ __u64 context_id; /* Context to own physical resources */
+ __u64 rsrc_handle; /* Returned resource handle */
+ __u64 last_lba; /* Returned last LBA on the device */
+ __u64 reserved[8]; /* Reserved for future use */
+};
+
+struct dk_cxlflash_release {
+ struct dk_cxlflash_hdr hdr; /* Common fields */
+ __u64 context_id; /* Context owning resources */
+ __u64 rsrc_handle; /* Resource handle to release */
+ __u64 reserved[8]; /* Reserved for future use */
+};
+
+#define DK_CXLFLASH_VERIFY_SENSE_LEN 18
+#define DK_CXLFLASH_VERIFY_HINT_SENSE 0x8000000000000000ULL
+
+struct dk_cxlflash_verify {
+ struct dk_cxlflash_hdr hdr; /* Common fields */
+ __u64 context_id; /* Context owning resources to verify */
+ __u64 rsrc_handle; /* Resource handle of LUN */
+ __u64 hint; /* Reasons for verify */
+ __u64 last_lba; /* Returned last LBA of device */
+ __u8 sense_data[DK_CXLFLASH_VERIFY_SENSE_LEN]; /* SCSI sense data */
+ __u8 pad[6]; /* Pad to next 8-byte boundary */
+ __u64 reserved[8]; /* Reserved for future use */
+};
+
+#define DK_CXLFLASH_RECOVER_AFU_CONTEXT_RESET 0x8000000000000000ULL
+
+struct dk_cxlflash_recover_afu {
+ struct dk_cxlflash_hdr hdr; /* Common fields */
+ __u64 reason; /* Reason for recovery request */
+ __u64 context_id; /* Context to recover / updated ID */
+ __u64 mmio_size; /* Returned size of MMIO area */
+ __u64 adap_fd; /* Returned adapter file descriptor */
+ __u64 reserved[8]; /* Reserved for future use */
+};
+
+#define DK_CXLFLASH_MANAGE_LUN_WWID_LEN 16
+#define DK_CXLFLASH_MANAGE_LUN_ENABLE_SUPERPIPE 0x8000000000000000ULL
+#define DK_CXLFLASH_MANAGE_LUN_DISABLE_SUPERPIPE 0x4000000000000000ULL
+#define DK_CXLFLASH_MANAGE_LUN_ALL_PORTS_ACCESSIBLE 0x2000000000000000ULL
+
+struct dk_cxlflash_manage_lun {
+ struct dk_cxlflash_hdr hdr; /* Common fields */
+ __u8 wwid[DK_CXLFLASH_MANAGE_LUN_WWID_LEN]; /* Page83 WWID, NAA-6 */
+ __u64 reserved[8]; /* Rsvd, future use */
+};
+
+union cxlflash_ioctls {
+ struct dk_cxlflash_attach attach;
+ struct dk_cxlflash_detach detach;
+ struct dk_cxlflash_udirect udirect;
+ struct dk_cxlflash_release release;
+ struct dk_cxlflash_verify verify;
+ struct dk_cxlflash_recover_afu recover_afu;
+ struct dk_cxlflash_manage_lun manage_lun;
+};
+
+#define MAX_CXLFLASH_IOCTL_SZ (sizeof(union cxlflash_ioctls))
+
+#define CXL_MAGIC 0xCA
+#define CXL_IOWR(_n, _s) _IOWR(CXL_MAGIC, _n, struct _s)
+
+#define DK_CXLFLASH_ATTACH CXL_IOWR(0x80, dk_cxlflash_attach)
+#define DK_CXLFLASH_USER_DIRECT CXL_IOWR(0x81, dk_cxlflash_udirect)
+#define DK_CXLFLASH_RELEASE CXL_IOWR(0x82, dk_cxlflash_release)
+#define DK_CXLFLASH_DETACH CXL_IOWR(0x83, dk_cxlflash_detach)
+#define DK_CXLFLASH_VERIFY CXL_IOWR(0x84, dk_cxlflash_verify)
+#define DK_CXLFLASH_RECOVER_AFU CXL_IOWR(0x85, dk_cxlflash_recover_afu)
+#define DK_CXLFLASH_MANAGE_LUN CXL_IOWR(0x86, dk_cxlflash_manage_lun)
+
+#endif /* ifndef _CXLFLASH_IOCTL_H */