Merge tag 'libnvdimm-for-5.15' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdim...

[linux-2.6-microblaze.git] / drivers / cxl / pci.c

// SPDX-License-Identifier: GPL-2.0-only
/* Copyright(c) 2020 Intel Corporation. All rights reserved. */
#include <uapi/linux/cxl_mem.h>
#include <linux/security.h>
#include <linux/debugfs.h>
#include <linux/module.h>
#include <linux/sizes.h>
#include <linux/mutex.h>
#include <linux/list.h>
#include <linux/cdev.h>
#include <linux/idr.h>
#include <linux/pci.h>
#include <linux/io.h>
#include <linux/io-64-nonatomic-lo-hi.h>
#include "pci.h"
#include "cxl.h"
#include "mem.h"

/**
 * DOC: cxl pci
 *
 * This implements the PCI exclusive functionality for a CXL device as it is
 * defined by the Compute Express Link specification. CXL devices may surface
 * certain functionality even if it isn't CXL enabled.
 *
 * The driver has several responsibilities, mainly:
 *  - Create the memX device and register on the CXL bus.
 *  - Enumerate device's register interface and map them.
 *  - Probe the device attributes to establish sysfs interface.
 *  - Provide an IOCTL interface to userspace to communicate with the device for
 *    things like firmware update.
 */

#define cxl_doorbell_busy(cxlm)                                                \
        (readl((cxlm)->regs.mbox + CXLDEV_MBOX_CTRL_OFFSET) &                  \
         CXLDEV_MBOX_CTRL_DOORBELL)

/* CXL 2.0 - 8.2.8.4 */
#define CXL_MAILBOX_TIMEOUT_MS (2 * HZ)

enum opcode {
        CXL_MBOX_OP_INVALID             = 0x0000,
        CXL_MBOX_OP_RAW                 = CXL_MBOX_OP_INVALID,
        CXL_MBOX_OP_GET_FW_INFO         = 0x0200,
        CXL_MBOX_OP_ACTIVATE_FW         = 0x0202,
        CXL_MBOX_OP_GET_SUPPORTED_LOGS  = 0x0400,
        CXL_MBOX_OP_GET_LOG             = 0x0401,
        CXL_MBOX_OP_IDENTIFY            = 0x4000,
        CXL_MBOX_OP_GET_PARTITION_INFO  = 0x4100,
        CXL_MBOX_OP_SET_PARTITION_INFO  = 0x4101,
        CXL_MBOX_OP_GET_LSA             = 0x4102,
        CXL_MBOX_OP_SET_LSA             = 0x4103,
        CXL_MBOX_OP_GET_HEALTH_INFO     = 0x4200,
        CXL_MBOX_OP_GET_ALERT_CONFIG    = 0x4201,
        CXL_MBOX_OP_SET_ALERT_CONFIG    = 0x4202,
        CXL_MBOX_OP_GET_SHUTDOWN_STATE  = 0x4203,
        CXL_MBOX_OP_SET_SHUTDOWN_STATE  = 0x4204,
        CXL_MBOX_OP_GET_POISON          = 0x4300,
        CXL_MBOX_OP_INJECT_POISON       = 0x4301,
        CXL_MBOX_OP_CLEAR_POISON        = 0x4302,
        CXL_MBOX_OP_GET_SCAN_MEDIA_CAPS = 0x4303,
        CXL_MBOX_OP_SCAN_MEDIA          = 0x4304,
        CXL_MBOX_OP_GET_SCAN_MEDIA      = 0x4305,
        CXL_MBOX_OP_MAX                 = 0x10000
};

/**
 * struct mbox_cmd - A command to be submitted to hardware.
 * @opcode: (input) The command set and command submitted to hardware.
 * @payload_in: (input) Pointer to the input payload.
 * @payload_out: (output) Pointer to the output payload. Must be allocated by
 *               the caller.
 * @size_in: (input) Number of bytes to load from @payload_in.
 * @size_out: (input) Max number of bytes loaded into @payload_out.
 *            (output) Number of bytes generated by the device. For fixed size
 *            outputs commands this is always expected to be deterministic. For
 *            variable sized output commands, it tells the exact number of bytes
 *            written.
 * @return_code: (output) Error code returned from hardware.
 *
 * This is the primary mechanism used to send commands to the hardware.
 * All the fields except @payload_* correspond exactly to the fields described in
 * Command Register section of the CXL 2.0 8.2.8.4.5. @payload_in and
 * @payload_out are written to, and read from the Command Payload Registers
 * defined in CXL 2.0 8.2.8.4.8.
 */
struct mbox_cmd {
        u16 opcode;
        void *payload_in;
        void *payload_out;
        size_t size_in;
        size_t size_out;
        u16 return_code;
#define CXL_MBOX_SUCCESS 0
};

static int cxl_mem_major;
static DEFINE_IDA(cxl_memdev_ida);
static DECLARE_RWSEM(cxl_memdev_rwsem);
static struct dentry *cxl_debugfs;
static bool cxl_raw_allow_all;

enum {
        CEL_UUID,
        VENDOR_DEBUG_UUID,
};

/* See CXL 2.0 Table 170. Get Log Input Payload */
static const uuid_t log_uuid[] = {
        [CEL_UUID] = UUID_INIT(0xda9c0b5, 0xbf41, 0x4b78, 0x8f, 0x79, 0x96,
                               0xb1, 0x62, 0x3b, 0x3f, 0x17),
        [VENDOR_DEBUG_UUID] = UUID_INIT(0xe1819d9, 0x11a9, 0x400c, 0x81, 0x1f,
                                        0xd6, 0x07, 0x19, 0x40, 0x3d, 0x86),
};

/**
 * struct cxl_mem_command - Driver representation of a memory device command
 * @info: Command information as it exists for the UAPI
 * @opcode: The actual bits used for the mailbox protocol
 * @flags: Set of flags effecting driver behavior.
 *
 *  * %CXL_CMD_FLAG_FORCE_ENABLE: In cases of error, commands with this flag
 *    will be enabled by the driver regardless of what hardware may have
 *    advertised.
 *
 * The cxl_mem_command is the driver's internal representation of commands that
 * are supported by the driver. Some of these commands may not be supported by
 * the hardware. The driver will use @info to validate the fields passed in by
 * the user then submit the @opcode to the hardware.
 *
 * See struct cxl_command_info.
 */
struct cxl_mem_command {
        struct cxl_command_info info;
        enum opcode opcode;
        u32 flags;
#define CXL_CMD_FLAG_NONE 0
#define CXL_CMD_FLAG_FORCE_ENABLE BIT(0)
};

#define CXL_CMD(_id, sin, sout, _flags)                                        \
        [CXL_MEM_COMMAND_ID_##_id] = {                                         \
        .info = {                                                              \
                        .id = CXL_MEM_COMMAND_ID_##_id,                        \
                        .size_in = sin,                                        \
                        .size_out = sout,                                      \
                },                                                             \
        .opcode = CXL_MBOX_OP_##_id,                                           \
        .flags = _flags,                                                       \
        }

/*
 * This table defines the supported mailbox commands for the driver. This table
 * is made up of a UAPI structure. Non-negative values as parameters in the
 * table will be validated against the user's input. For example, if size_in is
 * 0, and the user passed in 1, it is an error.
 */
static struct cxl_mem_command mem_commands[CXL_MEM_COMMAND_ID_MAX] = {
        CXL_CMD(IDENTIFY, 0, 0x43, CXL_CMD_FLAG_FORCE_ENABLE),
#ifdef CONFIG_CXL_MEM_RAW_COMMANDS
        CXL_CMD(RAW, ~0, ~0, 0),
#endif
        CXL_CMD(GET_SUPPORTED_LOGS, 0, ~0, CXL_CMD_FLAG_FORCE_ENABLE),
        CXL_CMD(GET_FW_INFO, 0, 0x50, 0),
        CXL_CMD(GET_PARTITION_INFO, 0, 0x20, 0),
        CXL_CMD(GET_LSA, 0x8, ~0, 0),
        CXL_CMD(GET_HEALTH_INFO, 0, 0x12, 0),
        CXL_CMD(GET_LOG, 0x18, ~0, CXL_CMD_FLAG_FORCE_ENABLE),
        CXL_CMD(SET_PARTITION_INFO, 0x0a, 0, 0),
        CXL_CMD(SET_LSA, ~0, 0, 0),
        CXL_CMD(GET_ALERT_CONFIG, 0, 0x10, 0),
        CXL_CMD(SET_ALERT_CONFIG, 0xc, 0, 0),
        CXL_CMD(GET_SHUTDOWN_STATE, 0, 0x1, 0),
        CXL_CMD(SET_SHUTDOWN_STATE, 0x1, 0, 0),
        CXL_CMD(GET_POISON, 0x10, ~0, 0),
        CXL_CMD(INJECT_POISON, 0x8, 0, 0),
        CXL_CMD(CLEAR_POISON, 0x48, 0, 0),
        CXL_CMD(GET_SCAN_MEDIA_CAPS, 0x10, 0x4, 0),
        CXL_CMD(SCAN_MEDIA, 0x11, 0, 0),
        CXL_CMD(GET_SCAN_MEDIA, 0, ~0, 0),
};

/*
 * Commands that RAW doesn't permit. The rationale for each:
 *
 * CXL_MBOX_OP_ACTIVATE_FW: Firmware activation requires adjustment /
 * coordination of transaction timeout values at the root bridge level.
 *
 * CXL_MBOX_OP_SET_PARTITION_INFO: The device memory map may change live
 * and needs to be coordinated with HDM updates.
 *
 * CXL_MBOX_OP_SET_LSA: The label storage area may be cached by the
 * driver and any writes from userspace invalidates those contents.
 *
 * CXL_MBOX_OP_SET_SHUTDOWN_STATE: Set shutdown state assumes no writes
 * to the device after it is marked clean, userspace can not make that
 * assertion.
 *
 * CXL_MBOX_OP_[GET_]SCAN_MEDIA: The kernel provides a native error list that
 * is kept up to date with patrol notifications and error management.
 */
static u16 cxl_disabled_raw_commands[] = {
        CXL_MBOX_OP_ACTIVATE_FW,
        CXL_MBOX_OP_SET_PARTITION_INFO,
        CXL_MBOX_OP_SET_LSA,
        CXL_MBOX_OP_SET_SHUTDOWN_STATE,
        CXL_MBOX_OP_SCAN_MEDIA,
        CXL_MBOX_OP_GET_SCAN_MEDIA,
};

/*
 * Command sets that RAW doesn't permit. All opcodes in this set are
 * disabled because they pass plain text security payloads over the
 * user/kernel boundary. This functionality is intended to be wrapped
 * behind the keys ABI which allows for encrypted payloads in the UAPI
 */
static u8 security_command_sets[] = {
        0x44, /* Sanitize */
        0x45, /* Persistent Memory Data-at-rest Security */
        0x46, /* Security Passthrough */
};

#define cxl_for_each_cmd(cmd)                                                  \
        for ((cmd) = &mem_commands[0];                                         \
             ((cmd) - mem_commands) < ARRAY_SIZE(mem_commands); (cmd)++)

#define cxl_cmd_count ARRAY_SIZE(mem_commands)

static int cxl_mem_wait_for_doorbell(struct cxl_mem *cxlm)
{
        const unsigned long start = jiffies;
        unsigned long end = start;

        while (cxl_doorbell_busy(cxlm)) {
                end = jiffies;

                if (time_after(end, start + CXL_MAILBOX_TIMEOUT_MS)) {
                        /* Check again in case preempted before timeout test */
                        if (!cxl_doorbell_busy(cxlm))
                                break;
                        return -ETIMEDOUT;
                }
                cpu_relax();
        }

        dev_dbg(&cxlm->pdev->dev, "Doorbell wait took %dms",
                jiffies_to_msecs(end) - jiffies_to_msecs(start));
        return 0;
}

static bool cxl_is_security_command(u16 opcode)
{
        int i;

        for (i = 0; i < ARRAY_SIZE(security_command_sets); i++)
                if (security_command_sets[i] == (opcode >> 8))
                        return true;
        return false;
}

static void cxl_mem_mbox_timeout(struct cxl_mem *cxlm,
                                 struct mbox_cmd *mbox_cmd)
{
        struct device *dev = &cxlm->pdev->dev;

        dev_dbg(dev, "Mailbox command (opcode: %#x size: %zub) timed out\n",
                mbox_cmd->opcode, mbox_cmd->size_in);
}

/**
 * __cxl_mem_mbox_send_cmd() - Execute a mailbox command
 * @cxlm: The CXL memory device to communicate with.
 * @mbox_cmd: Command to send to the memory device.
 *
 * Context: Any context. Expects mbox_mutex to be held.
 * Return: -ETIMEDOUT if timeout occurred waiting for completion. 0 on success.
 *         Caller should check the return code in @mbox_cmd to make sure it
 *         succeeded.
 *
 * This is a generic form of the CXL mailbox send command thus only using the
 * registers defined by the mailbox capability ID - CXL 2.0 8.2.8.4. Memory
 * devices, and perhaps other types of CXL devices may have further information
 * available upon error conditions. Driver facilities wishing to send mailbox
 * commands should use the wrapper command.
 *
 * The CXL spec allows for up to two mailboxes. The intention is for the primary
 * mailbox to be OS controlled and the secondary mailbox to be used by system
 * firmware. This allows the OS and firmware to communicate with the device and
 * not need to coordinate with each other. The driver only uses the primary
 * mailbox.
 */
static int __cxl_mem_mbox_send_cmd(struct cxl_mem *cxlm,
                                   struct mbox_cmd *mbox_cmd)
{
        void __iomem *payload = cxlm->regs.mbox + CXLDEV_MBOX_PAYLOAD_OFFSET;
        u64 cmd_reg, status_reg;
        size_t out_len;
        int rc;

        lockdep_assert_held(&cxlm->mbox_mutex);

        /*
         * Here are the steps from 8.2.8.4 of the CXL 2.0 spec.
         *   1. Caller reads MB Control Register to verify doorbell is clear
         *   2. Caller writes Command Register
         *   3. Caller writes Command Payload Registers if input payload is non-empty
         *   4. Caller writes MB Control Register to set doorbell
         *   5. Caller either polls for doorbell to be clear or waits for interrupt if configured
         *   6. Caller reads MB Status Register to fetch Return code
         *   7. If command successful, Caller reads Command Register to get Payload Length
         *   8. If output payload is non-empty, host reads Command Payload Registers
         *
         * Hardware is free to do whatever it wants before the doorbell is rung,
         * and isn't allowed to change anything after it clears the doorbell. As
         * such, steps 2 and 3 can happen in any order, and steps 6, 7, 8 can
         * also happen in any order (though some orders might not make sense).
         */

        /* #1 */
        if (cxl_doorbell_busy(cxlm)) {
                dev_err_ratelimited(&cxlm->pdev->dev,
                                    "Mailbox re-busy after acquiring\n");
                return -EBUSY;
        }

        cmd_reg = FIELD_PREP(CXLDEV_MBOX_CMD_COMMAND_OPCODE_MASK,
                             mbox_cmd->opcode);
        if (mbox_cmd->size_in) {
                if (WARN_ON(!mbox_cmd->payload_in))
                        return -EINVAL;

                cmd_reg |= FIELD_PREP(CXLDEV_MBOX_CMD_PAYLOAD_LENGTH_MASK,
                                      mbox_cmd->size_in);
                memcpy_toio(payload, mbox_cmd->payload_in, mbox_cmd->size_in);
        }

        /* #2, #3 */
        writeq(cmd_reg, cxlm->regs.mbox + CXLDEV_MBOX_CMD_OFFSET);

        /* #4 */
        dev_dbg(&cxlm->pdev->dev, "Sending command\n");
        writel(CXLDEV_MBOX_CTRL_DOORBELL,
               cxlm->regs.mbox + CXLDEV_MBOX_CTRL_OFFSET);

        /* #5 */
        rc = cxl_mem_wait_for_doorbell(cxlm);
        if (rc == -ETIMEDOUT) {
                cxl_mem_mbox_timeout(cxlm, mbox_cmd);
                return rc;
        }

        /* #6 */
        status_reg = readq(cxlm->regs.mbox + CXLDEV_MBOX_STATUS_OFFSET);
        mbox_cmd->return_code =
                FIELD_GET(CXLDEV_MBOX_STATUS_RET_CODE_MASK, status_reg);

        if (mbox_cmd->return_code != 0) {
                dev_dbg(&cxlm->pdev->dev, "Mailbox operation had an error\n");
                return 0;
        }

        /* #7 */
        cmd_reg = readq(cxlm->regs.mbox + CXLDEV_MBOX_CMD_OFFSET);
        out_len = FIELD_GET(CXLDEV_MBOX_CMD_PAYLOAD_LENGTH_MASK, cmd_reg);

        /* #8 */
        if (out_len && mbox_cmd->payload_out) {
                /*
                 * Sanitize the copy. If hardware misbehaves, out_len per the
                 * spec can actually be greater than the max allowed size (21
                 * bits available but spec defined 1M max). The caller also may
                 * have requested less data than the hardware supplied even
                 * within spec.
                 */
                size_t n = min3(mbox_cmd->size_out, cxlm->payload_size, out_len);

                memcpy_fromio(mbox_cmd->payload_out, payload, n);
                mbox_cmd->size_out = n;
        } else {
                mbox_cmd->size_out = 0;
        }

        return 0;
}

/**
 * cxl_mem_mbox_get() - Acquire exclusive access to the mailbox.
 * @cxlm: The memory device to gain access to.
 *
 * Context: Any context. Takes the mbox_mutex.
 * Return: 0 if exclusive access was acquired.
 */
static int cxl_mem_mbox_get(struct cxl_mem *cxlm)
{
        struct device *dev = &cxlm->pdev->dev;
        u64 md_status;
        int rc;

        mutex_lock_io(&cxlm->mbox_mutex);

        /*
         * XXX: There is some amount of ambiguity in the 2.0 version of the spec
         * around the mailbox interface ready (8.2.8.5.1.1).  The purpose of the
         * bit is to allow firmware running on the device to notify the driver
         * that it's ready to receive commands. It is unclear if the bit needs
         * to be read for each transaction mailbox, ie. the firmware can switch
         * it on and off as needed. Second, there is no defined timeout for
         * mailbox ready, like there is for the doorbell interface.
         *
         * Assumptions:
         * 1. The firmware might toggle the Mailbox Interface Ready bit, check
         *    it for every command.
         *
         * 2. If the doorbell is clear, the firmware should have first set the
         *    Mailbox Interface Ready bit. Therefore, waiting for the doorbell
         *    to be ready is sufficient.
         */
        rc = cxl_mem_wait_for_doorbell(cxlm);
        if (rc) {
                dev_warn(dev, "Mailbox interface not ready\n");
                goto out;
        }

        md_status = readq(cxlm->regs.memdev + CXLMDEV_STATUS_OFFSET);
        if (!(md_status & CXLMDEV_MBOX_IF_READY && CXLMDEV_READY(md_status))) {
                dev_err(dev, "mbox: reported doorbell ready, but not mbox ready\n");
                rc = -EBUSY;
                goto out;
        }

        /*
         * Hardware shouldn't allow a ready status but also have failure bits
         * set. Spit out an error, this should be a bug report
         */
        rc = -EFAULT;
        if (md_status & CXLMDEV_DEV_FATAL) {
                dev_err(dev, "mbox: reported ready, but fatal\n");
                goto out;
        }
        if (md_status & CXLMDEV_FW_HALT) {
                dev_err(dev, "mbox: reported ready, but halted\n");
                goto out;
        }
        if (CXLMDEV_RESET_NEEDED(md_status)) {
                dev_err(dev, "mbox: reported ready, but reset needed\n");
                goto out;
        }

        /* with lock held */
        return 0;

out:
        mutex_unlock(&cxlm->mbox_mutex);
        return rc;
}

/**
 * cxl_mem_mbox_put() - Release exclusive access to the mailbox.
 * @cxlm: The CXL memory device to communicate with.
 *
 * Context: Any context. Expects mbox_mutex to be held.
 */
static void cxl_mem_mbox_put(struct cxl_mem *cxlm)
{
        mutex_unlock(&cxlm->mbox_mutex);
}

/**
 * handle_mailbox_cmd_from_user() - Dispatch a mailbox command for userspace.
 * @cxlm: The CXL memory device to communicate with.
 * @cmd: The validated command.
 * @in_payload: Pointer to userspace's input payload.
 * @out_payload: Pointer to userspace's output payload.
 * @size_out: (Input) Max payload size to copy out.
 *            (Output) Payload size hardware generated.
 * @retval: Hardware generated return code from the operation.
 *
 * Return:
 *  * %0        - Mailbox transaction succeeded. This implies the mailbox
 *                protocol completed successfully not that the operation itself
 *                was successful.
 *  * %-ENOMEM  - Couldn't allocate a bounce buffer.
 *  * %-EFAULT  - Something happened with copy_to/from_user.
 *  * %-EINTR   - Mailbox acquisition interrupted.
 *  * %-EXXX    - Transaction level failures.
 *
 * Creates the appropriate mailbox command and dispatches it on behalf of a
 * userspace request. The input and output payloads are copied between
 * userspace.
 *
 * See cxl_send_cmd().
 */
static int handle_mailbox_cmd_from_user(struct cxl_mem *cxlm,
                                        const struct cxl_mem_command *cmd,
                                        u64 in_payload, u64 out_payload,
                                        s32 *size_out, u32 *retval)
{
        struct device *dev = &cxlm->pdev->dev;
        struct mbox_cmd mbox_cmd = {
                .opcode = cmd->opcode,
                .size_in = cmd->info.size_in,
                .size_out = cmd->info.size_out,
        };
        int rc;

        if (cmd->info.size_out) {
                mbox_cmd.payload_out = kvzalloc(cmd->info.size_out, GFP_KERNEL);
                if (!mbox_cmd.payload_out)
                        return -ENOMEM;
        }

        if (cmd->info.size_in) {
                mbox_cmd.payload_in = vmemdup_user(u64_to_user_ptr(in_payload),
                                                   cmd->info.size_in);
                if (IS_ERR(mbox_cmd.payload_in)) {
                        kvfree(mbox_cmd.payload_out);
                        return PTR_ERR(mbox_cmd.payload_in);
                }
        }

        rc = cxl_mem_mbox_get(cxlm);
        if (rc)
                goto out;

        dev_dbg(dev,
                "Submitting %s command for user\n"
                "\topcode: %x\n"
                "\tsize: %ub\n",
                cxl_command_names[cmd->info.id].name, mbox_cmd.opcode,
                cmd->info.size_in);

        dev_WARN_ONCE(dev, cmd->info.id == CXL_MEM_COMMAND_ID_RAW,
                      "raw command path used\n");

        rc = __cxl_mem_mbox_send_cmd(cxlm, &mbox_cmd);
        cxl_mem_mbox_put(cxlm);
        if (rc)
                goto out;

        /*
         * @size_out contains the max size that's allowed to be written back out
         * to userspace. While the payload may have written more output than
         * this it will have to be ignored.
         */
        if (mbox_cmd.size_out) {
                dev_WARN_ONCE(dev, mbox_cmd.size_out > *size_out,
                              "Invalid return size\n");
                if (copy_to_user(u64_to_user_ptr(out_payload),
                                 mbox_cmd.payload_out, mbox_cmd.size_out)) {
                        rc = -EFAULT;
                        goto out;
                }
        }

        *size_out = mbox_cmd.size_out;
        *retval = mbox_cmd.return_code;

out:
        kvfree(mbox_cmd.payload_in);
        kvfree(mbox_cmd.payload_out);
        return rc;
}

static bool cxl_mem_raw_command_allowed(u16 opcode)
{
        int i;

        if (!IS_ENABLED(CONFIG_CXL_MEM_RAW_COMMANDS))
                return false;

        if (security_locked_down(LOCKDOWN_NONE))
                return false;

        if (cxl_raw_allow_all)
                return true;

        if (cxl_is_security_command(opcode))
                return false;

        for (i = 0; i < ARRAY_SIZE(cxl_disabled_raw_commands); i++)
                if (cxl_disabled_raw_commands[i] == opcode)
                        return false;

        return true;
}

/**
 * cxl_validate_cmd_from_user() - Check fields for CXL_MEM_SEND_COMMAND.
 * @cxlm: &struct cxl_mem device whose mailbox will be used.
 * @send_cmd: &struct cxl_send_command copied in from userspace.
 * @out_cmd: Sanitized and populated &struct cxl_mem_command.
 *
 * Return:
 *  * %0        - @out_cmd is ready to send.
 *  * %-ENOTTY  - Invalid command specified.
 *  * %-EINVAL  - Reserved fields or invalid values were used.
 *  * %-ENOMEM  - Input or output buffer wasn't sized properly.
 *  * %-EPERM   - Attempted to use a protected command.
 *
 * The result of this command is a fully validated command in @out_cmd that is
 * safe to send to the hardware.
 *
 * See handle_mailbox_cmd_from_user()
 */
static int cxl_validate_cmd_from_user(struct cxl_mem *cxlm,
                                      const struct cxl_send_command *send_cmd,
                                      struct cxl_mem_command *out_cmd)
{
        const struct cxl_command_info *info;
        struct cxl_mem_command *c;

        if (send_cmd->id == 0 || send_cmd->id >= CXL_MEM_COMMAND_ID_MAX)
                return -ENOTTY;

        /*
         * The user can never specify an input payload larger than what hardware
         * supports, but output can be arbitrarily large (simply write out as
         * much data as the hardware provides).
         */
        if (send_cmd->in.size > cxlm->payload_size)
                return -EINVAL;

        /*
         * Checks are bypassed for raw commands but a WARN/taint will occur
         * later in the callchain
         */
        if (send_cmd->id == CXL_MEM_COMMAND_ID_RAW) {
                const struct cxl_mem_command temp = {
                        .info = {
                                .id = CXL_MEM_COMMAND_ID_RAW,
                                .flags = 0,
                                .size_in = send_cmd->in.size,
                                .size_out = send_cmd->out.size,
                        },
                        .opcode = send_cmd->raw.opcode
                };

                if (send_cmd->raw.rsvd)
                        return -EINVAL;

                /*
                 * Unlike supported commands, the output size of RAW commands
                 * gets passed along without further checking, so it must be
                 * validated here.
                 */
                if (send_cmd->out.size > cxlm->payload_size)
                        return -EINVAL;

                if (!cxl_mem_raw_command_allowed(send_cmd->raw.opcode))
                        return -EPERM;

                memcpy(out_cmd, &temp, sizeof(temp));

                return 0;
        }

        if (send_cmd->flags & ~CXL_MEM_COMMAND_FLAG_MASK)
                return -EINVAL;

        if (send_cmd->rsvd)
                return -EINVAL;

        if (send_cmd->in.rsvd || send_cmd->out.rsvd)
                return -EINVAL;

        /* Convert user's command into the internal representation */
        c = &mem_commands[send_cmd->id];
        info = &c->info;

        /* Check that the command is enabled for hardware */
        if (!test_bit(info->id, cxlm->enabled_cmds))
                return -ENOTTY;

        /* Check the input buffer is the expected size */
        if (info->size_in >= 0 && info->size_in != send_cmd->in.size)
                return -ENOMEM;

        /* Check the output buffer is at least large enough */
        if (info->size_out >= 0 && send_cmd->out.size < info->size_out)
                return -ENOMEM;

        memcpy(out_cmd, c, sizeof(*c));
        out_cmd->info.size_in = send_cmd->in.size;
        /*
         * XXX: out_cmd->info.size_out will be controlled by the driver, and the
         * specified number of bytes @send_cmd->out.size will be copied back out
         * to userspace.
         */

        return 0;
}

static int cxl_query_cmd(struct cxl_memdev *cxlmd,
                         struct cxl_mem_query_commands __user *q)
{
        struct device *dev = &cxlmd->dev;
        struct cxl_mem_command *cmd;
        u32 n_commands;
        int j = 0;

        dev_dbg(dev, "Query IOCTL\n");

        if (get_user(n_commands, &q->n_commands))
                return -EFAULT;

        /* returns the total number if 0 elements are requested. */
        if (n_commands == 0)
                return put_user(cxl_cmd_count, &q->n_commands);

        /*
         * otherwise, return max(n_commands, total commands) cxl_command_info
         * structures.
         */
        cxl_for_each_cmd(cmd) {
                const struct cxl_command_info *info = &cmd->info;

                if (copy_to_user(&q->commands[j++], info, sizeof(*info)))
                        return -EFAULT;

                if (j == n_commands)
                        break;
        }

        return 0;
}

static int cxl_send_cmd(struct cxl_memdev *cxlmd,
                        struct cxl_send_command __user *s)
{
        struct cxl_mem *cxlm = cxlmd->cxlm;
        struct device *dev = &cxlmd->dev;
        struct cxl_send_command send;
        struct cxl_mem_command c;
        int rc;

        dev_dbg(dev, "Send IOCTL\n");

        if (copy_from_user(&send, s, sizeof(send)))
                return -EFAULT;

        rc = cxl_validate_cmd_from_user(cxlmd->cxlm, &send, &c);
        if (rc)
                return rc;

        /* Prepare to handle a full payload for variable sized output */
        if (c.info.size_out < 0)
                c.info.size_out = cxlm->payload_size;

        rc = handle_mailbox_cmd_from_user(cxlm, &c, send.in.payload,
                                          send.out.payload, &send.out.size,
                                          &send.retval);
        if (rc)
                return rc;

        if (copy_to_user(s, &send, sizeof(send)))
                return -EFAULT;

        return 0;
}

static long __cxl_memdev_ioctl(struct cxl_memdev *cxlmd, unsigned int cmd,
                               unsigned long arg)
{
        switch (cmd) {
        case CXL_MEM_QUERY_COMMANDS:
                return cxl_query_cmd(cxlmd, (void __user *)arg);
        case CXL_MEM_SEND_COMMAND:
                return cxl_send_cmd(cxlmd, (void __user *)arg);
        default:
                return -ENOTTY;
        }
}

static long cxl_memdev_ioctl(struct file *file, unsigned int cmd,
                             unsigned long arg)
{
        struct cxl_memdev *cxlmd = file->private_data;
        int rc = -ENXIO;

        down_read(&cxl_memdev_rwsem);
        if (cxlmd->cxlm)
                rc = __cxl_memdev_ioctl(cxlmd, cmd, arg);
        up_read(&cxl_memdev_rwsem);

        return rc;
}

static int cxl_memdev_open(struct inode *inode, struct file *file)
{
        struct cxl_memdev *cxlmd =
                container_of(inode->i_cdev, typeof(*cxlmd), cdev);

        get_device(&cxlmd->dev);
        file->private_data = cxlmd;

        return 0;
}

static int cxl_memdev_release_file(struct inode *inode, struct file *file)
{
        struct cxl_memdev *cxlmd =
                container_of(inode->i_cdev, typeof(*cxlmd), cdev);

        put_device(&cxlmd->dev);

        return 0;
}

static const struct file_operations cxl_memdev_fops = {
        .owner = THIS_MODULE,
        .unlocked_ioctl = cxl_memdev_ioctl,
        .open = cxl_memdev_open,
        .release = cxl_memdev_release_file,
        .compat_ioctl = compat_ptr_ioctl,
        .llseek = noop_llseek,
};

static inline struct cxl_mem_command *cxl_mem_find_command(u16 opcode)
{
        struct cxl_mem_command *c;

        cxl_for_each_cmd(c)
                if (c->opcode == opcode)
                        return c;

        return NULL;
}

/**
 * cxl_mem_mbox_send_cmd() - Send a mailbox command to a memory device.
 * @cxlm: The CXL memory device to communicate with.
 * @opcode: Opcode for the mailbox command.
 * @in: The input payload for the mailbox command.
 * @in_size: The length of the input payload
 * @out: Caller allocated buffer for the output.
 * @out_size: Expected size of output.
 *
 * Context: Any context. Will acquire and release mbox_mutex.
 * Return:
 *  * %>=0      - Number of bytes returned in @out.
 *  * %-E2BIG   - Payload is too large for hardware.
 *  * %-EBUSY   - Couldn't acquire exclusive mailbox access.
 *  * %-EFAULT  - Hardware error occurred.
 *  * %-ENXIO   - Command completed, but device reported an error.
 *  * %-EIO     - Unexpected output size.
 *
 * Mailbox commands may execute successfully yet the device itself reported an
 * error. While this distinction can be useful for commands from userspace, the
 * kernel will only be able to use results when both are successful.
 *
 * See __cxl_mem_mbox_send_cmd()
 */
static int cxl_mem_mbox_send_cmd(struct cxl_mem *cxlm, u16 opcode,
                                 void *in, size_t in_size,
                                 void *out, size_t out_size)
{
        const struct cxl_mem_command *cmd = cxl_mem_find_command(opcode);
        struct mbox_cmd mbox_cmd = {
                .opcode = opcode,
                .payload_in = in,
                .size_in = in_size,
                .size_out = out_size,
                .payload_out = out,
        };
        int rc;

        if (out_size > cxlm->payload_size)
                return -E2BIG;

        rc = cxl_mem_mbox_get(cxlm);
        if (rc)
                return rc;

        rc = __cxl_mem_mbox_send_cmd(cxlm, &mbox_cmd);
        cxl_mem_mbox_put(cxlm);
        if (rc)
                return rc;

        /* TODO: Map return code to proper kernel style errno */
        if (mbox_cmd.return_code != CXL_MBOX_SUCCESS)
                return -ENXIO;

        /*
         * Variable sized commands can't be validated and so it's up to the
         * caller to do that if they wish.
         */
        if (cmd->info.size_out >= 0 && mbox_cmd.size_out != out_size)
                return -EIO;

        return 0;
}

static int cxl_mem_setup_mailbox(struct cxl_mem *cxlm)
{
        const int cap = readl(cxlm->regs.mbox + CXLDEV_MBOX_CAPS_OFFSET);

        cxlm->payload_size =
                1 << FIELD_GET(CXLDEV_MBOX_CAP_PAYLOAD_SIZE_MASK, cap);

        /*
         * CXL 2.0 8.2.8.4.3 Mailbox Capabilities Register
         *
         * If the size is too small, mandatory commands will not work and so
         * there's no point in going forward. If the size is too large, there's
         * no harm is soft limiting it.
         */
        cxlm->payload_size = min_t(size_t, cxlm->payload_size, SZ_1M);
        if (cxlm->payload_size < 256) {
                dev_err(&cxlm->pdev->dev, "Mailbox is too small (%zub)",
                        cxlm->payload_size);
                return -ENXIO;
        }

        dev_dbg(&cxlm->pdev->dev, "Mailbox payload sized %zu",
                cxlm->payload_size);

        return 0;
}

static struct cxl_mem *cxl_mem_create(struct pci_dev *pdev)
{
        struct device *dev = &pdev->dev;
        struct cxl_mem *cxlm;

        cxlm = devm_kzalloc(dev, sizeof(*cxlm), GFP_KERNEL);
        if (!cxlm) {
                dev_err(dev, "No memory available\n");
                return ERR_PTR(-ENOMEM);
        }

        mutex_init(&cxlm->mbox_mutex);
        cxlm->pdev = pdev;
        cxlm->enabled_cmds =
                devm_kmalloc_array(dev, BITS_TO_LONGS(cxl_cmd_count),
                                   sizeof(unsigned long),
                                   GFP_KERNEL | __GFP_ZERO);
        if (!cxlm->enabled_cmds) {
                dev_err(dev, "No memory available for bitmap\n");
                return ERR_PTR(-ENOMEM);
        }

        return cxlm;
}

static void __iomem *cxl_mem_map_regblock(struct cxl_mem *cxlm,
                                          u8 bar, u64 offset)
{
        struct pci_dev *pdev = cxlm->pdev;
        struct device *dev = &pdev->dev;
        void __iomem *addr;

        /* Basic sanity check that BAR is big enough */
        if (pci_resource_len(pdev, bar) < offset) {
                dev_err(dev, "BAR%d: %pr: too small (offset: %#llx)\n", bar,
                        &pdev->resource[bar], (unsigned long long)offset);
                return IOMEM_ERR_PTR(-ENXIO);
        }

        addr = pci_iomap(pdev, bar, 0);
        if (!addr) {
                dev_err(dev, "failed to map registers\n");
                return addr;
        }

        dev_dbg(dev, "Mapped CXL Memory Device resource bar %u @ %#llx\n",
                bar, offset);

        return addr;
}

static void cxl_mem_unmap_regblock(struct cxl_mem *cxlm, void __iomem *base)
{
        pci_iounmap(cxlm->pdev, base);
}

static int cxl_mem_dvsec(struct pci_dev *pdev, int dvsec)
{
        int pos;

        pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_DVSEC);
        if (!pos)
                return 0;

        while (pos) {
                u16 vendor, id;

                pci_read_config_word(pdev, pos + PCI_DVSEC_HEADER1, &vendor);
                pci_read_config_word(pdev, pos + PCI_DVSEC_HEADER2, &id);
                if (vendor == PCI_DVSEC_VENDOR_ID_CXL && dvsec == id)
                        return pos;

                pos = pci_find_next_ext_capability(pdev, pos,
                                                   PCI_EXT_CAP_ID_DVSEC);
        }

        return 0;
}

static int cxl_probe_regs(struct cxl_mem *cxlm, void __iomem *base,
                          struct cxl_register_map *map)
{
        struct pci_dev *pdev = cxlm->pdev;
        struct device *dev = &pdev->dev;
        struct cxl_component_reg_map *comp_map;
        struct cxl_device_reg_map *dev_map;

        switch (map->reg_type) {
        case CXL_REGLOC_RBI_COMPONENT:
                comp_map = &map->component_map;
                cxl_probe_component_regs(dev, base, comp_map);
                if (!comp_map->hdm_decoder.valid) {
                        dev_err(dev, "HDM decoder registers not found\n");
                        return -ENXIO;
                }

                dev_dbg(dev, "Set up component registers\n");
                break;
        case CXL_REGLOC_RBI_MEMDEV:
                dev_map = &map->device_map;
                cxl_probe_device_regs(dev, base, dev_map);
                if (!dev_map->status.valid || !dev_map->mbox.valid ||
                    !dev_map->memdev.valid) {
                        dev_err(dev, "registers not found: %s%s%s\n",
                                !dev_map->status.valid ? "status " : "",
                                !dev_map->mbox.valid ? "status " : "",
                                !dev_map->memdev.valid ? "status " : "");
                        return -ENXIO;
                }

                dev_dbg(dev, "Probing device registers...\n");
                break;
        default:
                break;
        }

        return 0;
}

static int cxl_map_regs(struct cxl_mem *cxlm, struct cxl_register_map *map)
{
        struct pci_dev *pdev = cxlm->pdev;
        struct device *dev = &pdev->dev;

        switch (map->reg_type) {
        case CXL_REGLOC_RBI_COMPONENT:
                cxl_map_component_regs(pdev, &cxlm->regs.component, map);
                dev_dbg(dev, "Mapping component registers...\n");
                break;
        case CXL_REGLOC_RBI_MEMDEV:
                cxl_map_device_regs(pdev, &cxlm->regs.device_regs, map);
                dev_dbg(dev, "Probing device registers...\n");
                break;
        default:
                break;
        }

        return 0;
}

static void cxl_decode_register_block(u32 reg_lo, u32 reg_hi,
                                      u8 *bar, u64 *offset, u8 *reg_type)
{
        *offset = ((u64)reg_hi << 32) | (reg_lo & CXL_REGLOC_ADDR_MASK);
        *bar = FIELD_GET(CXL_REGLOC_BIR_MASK, reg_lo);
        *reg_type = FIELD_GET(CXL_REGLOC_RBI_MASK, reg_lo);
}

/**
 * cxl_mem_setup_regs() - Setup necessary MMIO.
 * @cxlm: The CXL memory device to communicate with.
 *
 * Return: 0 if all necessary registers mapped.
 *
 * A memory device is required by spec to implement a certain set of MMIO
 * regions. The purpose of this function is to enumerate and map those
 * registers.
 */
static int cxl_mem_setup_regs(struct cxl_mem *cxlm)
{
        struct pci_dev *pdev = cxlm->pdev;
        struct device *dev = &pdev->dev;
        u32 regloc_size, regblocks;
        void __iomem *base;
        int regloc, i;
        struct cxl_register_map *map, *n;
        LIST_HEAD(register_maps);
        int ret = 0;

        regloc = cxl_mem_dvsec(pdev, PCI_DVSEC_ID_CXL_REGLOC_DVSEC_ID);
        if (!regloc) {
                dev_err(dev, "register location dvsec not found\n");
                return -ENXIO;
        }

        if (pci_request_mem_regions(pdev, pci_name(pdev)))
                return -ENODEV;

        /* Get the size of the Register Locator DVSEC */
        pci_read_config_dword(pdev, regloc + PCI_DVSEC_HEADER1, &regloc_size);
        regloc_size = FIELD_GET(PCI_DVSEC_HEADER1_LENGTH_MASK, regloc_size);

        regloc += PCI_DVSEC_ID_CXL_REGLOC_BLOCK1_OFFSET;
        regblocks = (regloc_size - PCI_DVSEC_ID_CXL_REGLOC_BLOCK1_OFFSET) / 8;

        for (i = 0; i < regblocks; i++, regloc += 8) {
                u32 reg_lo, reg_hi;
                u8 reg_type;
                u64 offset;
                u8 bar;

                map = kzalloc(sizeof(*map), GFP_KERNEL);
                if (!map) {
                        ret = -ENOMEM;
                        goto free_maps;
                }

                list_add(&map->list, &register_maps);

                pci_read_config_dword(pdev, regloc, &reg_lo);
                pci_read_config_dword(pdev, regloc + 4, &reg_hi);

                cxl_decode_register_block(reg_lo, reg_hi, &bar, &offset,
                                          &reg_type);

                dev_dbg(dev, "Found register block in bar %u @ 0x%llx of type %u\n",
                        bar, offset, reg_type);

                base = cxl_mem_map_regblock(cxlm, bar, offset);
                if (!base) {
                        ret = -ENOMEM;
                        goto free_maps;
                }

                map->barno = bar;
                map->block_offset = offset;
                map->reg_type = reg_type;

                ret = cxl_probe_regs(cxlm, base + offset, map);

                /* Always unmap the regblock regardless of probe success */
                cxl_mem_unmap_regblock(cxlm, base);

                if (ret)
                        goto free_maps;
        }

        pci_release_mem_regions(pdev);

        list_for_each_entry(map, &register_maps, list) {
                ret = cxl_map_regs(cxlm, map);
                if (ret)
                        goto free_maps;
        }

free_maps:
        list_for_each_entry_safe(map, n, &register_maps, list) {
                list_del(&map->list);
                kfree(map);
        }

        return ret;
}

static struct cxl_memdev *to_cxl_memdev(struct device *dev)
{
        return container_of(dev, struct cxl_memdev, dev);
}

static void cxl_memdev_release(struct device *dev)
{
        struct cxl_memdev *cxlmd = to_cxl_memdev(dev);

        ida_free(&cxl_memdev_ida, cxlmd->id);
        kfree(cxlmd);
}

static char *cxl_memdev_devnode(struct device *dev, umode_t *mode, kuid_t *uid,
                                kgid_t *gid)
{
        return kasprintf(GFP_KERNEL, "cxl/%s", dev_name(dev));
}

static ssize_t firmware_version_show(struct device *dev,
                                     struct device_attribute *attr, char *buf)
{
        struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
        struct cxl_mem *cxlm = cxlmd->cxlm;

        return sysfs_emit(buf, "%.16s\n", cxlm->firmware_version);
}
static DEVICE_ATTR_RO(firmware_version);

static ssize_t payload_max_show(struct device *dev,
                                struct device_attribute *attr, char *buf)
{
        struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
        struct cxl_mem *cxlm = cxlmd->cxlm;

        return sysfs_emit(buf, "%zu\n", cxlm->payload_size);
}
static DEVICE_ATTR_RO(payload_max);

static ssize_t label_storage_size_show(struct device *dev,
                                struct device_attribute *attr, char *buf)
{
        struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
        struct cxl_mem *cxlm = cxlmd->cxlm;

        return sysfs_emit(buf, "%zu\n", cxlm->lsa_size);
}
static DEVICE_ATTR_RO(label_storage_size);

static ssize_t ram_size_show(struct device *dev, struct device_attribute *attr,
                             char *buf)
{
        struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
        struct cxl_mem *cxlm = cxlmd->cxlm;
        unsigned long long len = range_len(&cxlm->ram_range);

        return sysfs_emit(buf, "%#llx\n", len);
}

static struct device_attribute dev_attr_ram_size =
        __ATTR(size, 0444, ram_size_show, NULL);

static ssize_t pmem_size_show(struct device *dev, struct device_attribute *attr,
                              char *buf)
{
        struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
        struct cxl_mem *cxlm = cxlmd->cxlm;
        unsigned long long len = range_len(&cxlm->pmem_range);

        return sysfs_emit(buf, "%#llx\n", len);
}

static struct device_attribute dev_attr_pmem_size =
        __ATTR(size, 0444, pmem_size_show, NULL);

static struct attribute *cxl_memdev_attributes[] = {
        &dev_attr_firmware_version.attr,
        &dev_attr_payload_max.attr,
        &dev_attr_label_storage_size.attr,
        NULL,
};

static struct attribute *cxl_memdev_pmem_attributes[] = {
        &dev_attr_pmem_size.attr,
        NULL,
};

static struct attribute *cxl_memdev_ram_attributes[] = {
        &dev_attr_ram_size.attr,
        NULL,
};

static struct attribute_group cxl_memdev_attribute_group = {
        .attrs = cxl_memdev_attributes,
};

static struct attribute_group cxl_memdev_ram_attribute_group = {
        .name = "ram",
        .attrs = cxl_memdev_ram_attributes,
};

static struct attribute_group cxl_memdev_pmem_attribute_group = {
        .name = "pmem",
        .attrs = cxl_memdev_pmem_attributes,
};

static const struct attribute_group *cxl_memdev_attribute_groups[] = {
        &cxl_memdev_attribute_group,
        &cxl_memdev_ram_attribute_group,
        &cxl_memdev_pmem_attribute_group,
        NULL,
};

static const struct device_type cxl_memdev_type = {
        .name = "cxl_memdev",
        .release = cxl_memdev_release,
        .devnode = cxl_memdev_devnode,
        .groups = cxl_memdev_attribute_groups,
};

static void cxl_memdev_shutdown(struct cxl_memdev *cxlmd)
{
        down_write(&cxl_memdev_rwsem);
        cxlmd->cxlm = NULL;
        up_write(&cxl_memdev_rwsem);
}

static void cxl_memdev_unregister(void *_cxlmd)
{
        struct cxl_memdev *cxlmd = _cxlmd;
        struct device *dev = &cxlmd->dev;

        cdev_device_del(&cxlmd->cdev, dev);
        cxl_memdev_shutdown(cxlmd);
        put_device(dev);
}

static struct cxl_memdev *cxl_memdev_alloc(struct cxl_mem *cxlm)
{
        struct pci_dev *pdev = cxlm->pdev;
        struct cxl_memdev *cxlmd;
        struct device *dev;
        struct cdev *cdev;
        int rc;

        cxlmd = kzalloc(sizeof(*cxlmd), GFP_KERNEL);
        if (!cxlmd)
                return ERR_PTR(-ENOMEM);

        rc = ida_alloc_range(&cxl_memdev_ida, 0, CXL_MEM_MAX_DEVS, GFP_KERNEL);
        if (rc < 0)
                goto err;
        cxlmd->id = rc;

        dev = &cxlmd->dev;
        device_initialize(dev);
        dev->parent = &pdev->dev;
        dev->bus = &cxl_bus_type;
        dev->devt = MKDEV(cxl_mem_major, cxlmd->id);
        dev->type = &cxl_memdev_type;
        device_set_pm_not_required(dev);

        cdev = &cxlmd->cdev;
        cdev_init(cdev, &cxl_memdev_fops);
        return cxlmd;

err:
        kfree(cxlmd);
        return ERR_PTR(rc);
}

static struct cxl_memdev *devm_cxl_add_memdev(struct device *host,
                                              struct cxl_mem *cxlm)
{
        struct cxl_memdev *cxlmd;
        struct device *dev;
        struct cdev *cdev;
        int rc;

        cxlmd = cxl_memdev_alloc(cxlm);
        if (IS_ERR(cxlmd))
                return cxlmd;

        dev = &cxlmd->dev;
        rc = dev_set_name(dev, "mem%d", cxlmd->id);
        if (rc)
                goto err;

        /*
         * Activate ioctl operations, no cxl_memdev_rwsem manipulation
         * needed as this is ordered with cdev_add() publishing the device.
         */
        cxlmd->cxlm = cxlm;

        cdev = &cxlmd->cdev;
        rc = cdev_device_add(cdev, dev);
        if (rc)
                goto err;

        rc = devm_add_action_or_reset(host, cxl_memdev_unregister, cxlmd);
        if (rc)
                return ERR_PTR(rc);
        return cxlmd;

err:
        /*
         * The cdev was briefly live, shutdown any ioctl operations that
         * saw that state.
         */
        cxl_memdev_shutdown(cxlmd);
        put_device(dev);
        return ERR_PTR(rc);
}

static int cxl_xfer_log(struct cxl_mem *cxlm, uuid_t *uuid, u32 size, u8 *out)
{
        u32 remaining = size;
        u32 offset = 0;

        while (remaining) {
                u32 xfer_size = min_t(u32, remaining, cxlm->payload_size);
                struct cxl_mbox_get_log {
                        uuid_t uuid;
                        __le32 offset;
                        __le32 length;
                } __packed log = {
                        .uuid = *uuid,
                        .offset = cpu_to_le32(offset),
                        .length = cpu_to_le32(xfer_size)
                };
                int rc;

                rc = cxl_mem_mbox_send_cmd(cxlm, CXL_MBOX_OP_GET_LOG, &log,
                                           sizeof(log), out, xfer_size);
                if (rc < 0)
                        return rc;

                out += xfer_size;
                remaining -= xfer_size;
                offset += xfer_size;
        }

        return 0;
}

/**
 * cxl_walk_cel() - Walk through the Command Effects Log.
 * @cxlm: Device.
 * @size: Length of the Command Effects Log.
 * @cel: CEL
 *
 * Iterate over each entry in the CEL and determine if the driver supports the
 * command. If so, the command is enabled for the device and can be used later.
 */
static void cxl_walk_cel(struct cxl_mem *cxlm, size_t size, u8 *cel)
{
        struct cel_entry {
                __le16 opcode;
                __le16 effect;
        } __packed * cel_entry;
        const int cel_entries = size / sizeof(*cel_entry);
        int i;

        cel_entry = (struct cel_entry *)cel;

        for (i = 0; i < cel_entries; i++) {
                u16 opcode = le16_to_cpu(cel_entry[i].opcode);
                struct cxl_mem_command *cmd = cxl_mem_find_command(opcode);

                if (!cmd) {
                        dev_dbg(&cxlm->pdev->dev,
                                "Opcode 0x%04x unsupported by driver", opcode);
                        continue;
                }

                set_bit(cmd->info.id, cxlm->enabled_cmds);
        }
}

struct cxl_mbox_get_supported_logs {
        __le16 entries;
        u8 rsvd[6];
        struct gsl_entry {
                uuid_t uuid;
                __le32 size;
        } __packed entry[];
} __packed;

static struct cxl_mbox_get_supported_logs *cxl_get_gsl(struct cxl_mem *cxlm)
{
        struct cxl_mbox_get_supported_logs *ret;
        int rc;

        ret = kvmalloc(cxlm->payload_size, GFP_KERNEL);
        if (!ret)
                return ERR_PTR(-ENOMEM);

        rc = cxl_mem_mbox_send_cmd(cxlm, CXL_MBOX_OP_GET_SUPPORTED_LOGS, NULL,
                                   0, ret, cxlm->payload_size);
        if (rc < 0) {
                kvfree(ret);
                return ERR_PTR(rc);
        }

        return ret;
}

/**
 * cxl_mem_enumerate_cmds() - Enumerate commands for a device.
 * @cxlm: The device.
 *
 * Returns 0 if enumerate completed successfully.
 *
 * CXL devices have optional support for certain commands. This function will
 * determine the set of supported commands for the hardware and update the
 * enabled_cmds bitmap in the @cxlm.
 */
static int cxl_mem_enumerate_cmds(struct cxl_mem *cxlm)
{
        struct cxl_mbox_get_supported_logs *gsl;
        struct device *dev = &cxlm->pdev->dev;
        struct cxl_mem_command *cmd;
        int i, rc;

        gsl = cxl_get_gsl(cxlm);
        if (IS_ERR(gsl))
                return PTR_ERR(gsl);

        rc = -ENOENT;
        for (i = 0; i < le16_to_cpu(gsl->entries); i++) {
                u32 size = le32_to_cpu(gsl->entry[i].size);
                uuid_t uuid = gsl->entry[i].uuid;
                u8 *log;

                dev_dbg(dev, "Found LOG type %pU of size %d", &uuid, size);

                if (!uuid_equal(&uuid, &log_uuid[CEL_UUID]))
                        continue;

                log = kvmalloc(size, GFP_KERNEL);
                if (!log) {
                        rc = -ENOMEM;
                        goto out;
                }

                rc = cxl_xfer_log(cxlm, &uuid, size, log);
                if (rc) {
                        kvfree(log);
                        goto out;
                }

                cxl_walk_cel(cxlm, size, log);
                kvfree(log);

                /* In case CEL was bogus, enable some default commands. */
                cxl_for_each_cmd(cmd)
                        if (cmd->flags & CXL_CMD_FLAG_FORCE_ENABLE)
                                set_bit(cmd->info.id, cxlm->enabled_cmds);

                /* Found the required CEL */
                rc = 0;
        }

out:
        kvfree(gsl);
        return rc;
}

/**
 * cxl_mem_identify() - Send the IDENTIFY command to the device.
 * @cxlm: The device to identify.
 *
 * Return: 0 if identify was executed successfully.
 *
 * This will dispatch the identify command to the device and on success populate
 * structures to be exported to sysfs.
 */
static int cxl_mem_identify(struct cxl_mem *cxlm)
{
        /* See CXL 2.0 Table 175 Identify Memory Device Output Payload */
        struct cxl_mbox_identify {
                char fw_revision[0x10];
                __le64 total_capacity;
                __le64 volatile_capacity;
                __le64 persistent_capacity;
                __le64 partition_align;
                __le16 info_event_log_size;
                __le16 warning_event_log_size;
                __le16 failure_event_log_size;
                __le16 fatal_event_log_size;
                __le32 lsa_size;
                u8 poison_list_max_mer[3];
                __le16 inject_poison_limit;
                u8 poison_caps;
                u8 qos_telemetry_caps;
        } __packed id;
        int rc;

        rc = cxl_mem_mbox_send_cmd(cxlm, CXL_MBOX_OP_IDENTIFY, NULL, 0, &id,
                                   sizeof(id));
        if (rc < 0)
                return rc;

        /*
         * TODO: enumerate DPA map, as 'ram' and 'pmem' do not alias.
         * For now, only the capacity is exported in sysfs
         */
        cxlm->ram_range.start = 0;
        cxlm->ram_range.end = le64_to_cpu(id.volatile_capacity) * SZ_256M - 1;

        cxlm->pmem_range.start = 0;
        cxlm->pmem_range.end =
                le64_to_cpu(id.persistent_capacity) * SZ_256M - 1;

        cxlm->lsa_size = le32_to_cpu(id.lsa_size);
        memcpy(cxlm->firmware_version, id.fw_revision, sizeof(id.fw_revision));

        return 0;
}

static int cxl_mem_probe(struct pci_dev *pdev, const struct pci_device_id *id)
{
        struct cxl_memdev *cxlmd;
        struct cxl_mem *cxlm;
        int rc;

        rc = pcim_enable_device(pdev);
        if (rc)
                return rc;

        cxlm = cxl_mem_create(pdev);
        if (IS_ERR(cxlm))
                return PTR_ERR(cxlm);

        rc = cxl_mem_setup_regs(cxlm);
        if (rc)
                return rc;

        rc = cxl_mem_setup_mailbox(cxlm);
        if (rc)
                return rc;

        rc = cxl_mem_enumerate_cmds(cxlm);
        if (rc)
                return rc;

        rc = cxl_mem_identify(cxlm);
        if (rc)
                return rc;

        cxlmd = devm_cxl_add_memdev(&pdev->dev, cxlm);
        if (IS_ERR(cxlmd))
                return PTR_ERR(cxlmd);

        if (range_len(&cxlm->pmem_range) && IS_ENABLED(CONFIG_CXL_PMEM))
                rc = devm_cxl_add_nvdimm(&pdev->dev, cxlmd);

        return rc;
}

static const struct pci_device_id cxl_mem_pci_tbl[] = {
        /* PCI class code for CXL.mem Type-3 Devices */
        { PCI_DEVICE_CLASS((PCI_CLASS_MEMORY_CXL << 8 | CXL_MEMORY_PROGIF), ~0)},
        { /* terminate list */ },
};
MODULE_DEVICE_TABLE(pci, cxl_mem_pci_tbl);

static struct pci_driver cxl_mem_driver = {
        .name                   = KBUILD_MODNAME,
        .id_table               = cxl_mem_pci_tbl,
        .probe                  = cxl_mem_probe,
        .driver = {
                .probe_type     = PROBE_PREFER_ASYNCHRONOUS,
        },
};

static __init int cxl_mem_init(void)
{
        struct dentry *mbox_debugfs;
        dev_t devt;
        int rc;

        /* Double check the anonymous union trickery in struct cxl_regs */
        BUILD_BUG_ON(offsetof(struct cxl_regs, memdev) !=
                     offsetof(struct cxl_regs, device_regs.memdev));

        rc = alloc_chrdev_region(&devt, 0, CXL_MEM_MAX_DEVS, "cxl");
        if (rc)
                return rc;

        cxl_mem_major = MAJOR(devt);

        rc = pci_register_driver(&cxl_mem_driver);
        if (rc) {
                unregister_chrdev_region(MKDEV(cxl_mem_major, 0),
                                         CXL_MEM_MAX_DEVS);
                return rc;
        }

        cxl_debugfs = debugfs_create_dir("cxl", NULL);
        mbox_debugfs = debugfs_create_dir("mbox", cxl_debugfs);
        debugfs_create_bool("raw_allow_all", 0600, mbox_debugfs,
                            &cxl_raw_allow_all);

        return 0;
}

static __exit void cxl_mem_exit(void)
{
        debugfs_remove_recursive(cxl_debugfs);
        pci_unregister_driver(&cxl_mem_driver);
        unregister_chrdev_region(MKDEV(cxl_mem_major, 0), CXL_MEM_MAX_DEVS);
}

MODULE_LICENSE("GPL v2");
module_init(cxl_mem_init);
module_exit(cxl_mem_exit);
MODULE_IMPORT_NS(CXL);