OpenCloudOS-Kernel/drivers/cxl/pci.c

1682 lines
44 KiB
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);