diff options
author | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-11 08:27:49 +0000 |
---|---|---|
committer | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-11 08:27:49 +0000 |
commit | ace9429bb58fd418f0c81d4c2835699bddf6bde6 (patch) | |
tree | b2d64bc10158fdd5497876388cd68142ca374ed3 /drivers/platform/x86/intel/speed_select_if | |
parent | Initial commit. (diff) | |
download | linux-ace9429bb58fd418f0c81d4c2835699bddf6bde6.tar.xz linux-ace9429bb58fd418f0c81d4c2835699bddf6bde6.zip |
Adding upstream version 6.6.15.upstream/6.6.15
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'drivers/platform/x86/intel/speed_select_if')
10 files changed, 3125 insertions, 0 deletions
diff --git a/drivers/platform/x86/intel/speed_select_if/Kconfig b/drivers/platform/x86/intel/speed_select_if/Kconfig new file mode 100644 index 0000000000..4eb3ad299d --- /dev/null +++ b/drivers/platform/x86/intel/speed_select_if/Kconfig @@ -0,0 +1,21 @@ +menu "Intel Speed Select Technology interface support" + depends on PCI + depends on X86_64 || COMPILE_TEST + +config INTEL_SPEED_SELECT_TPMI + tristate + +config INTEL_SPEED_SELECT_INTERFACE + tristate "Intel(R) Speed Select Technology interface drivers" + select INTEL_SPEED_SELECT_TPMI if INTEL_TPMI + help + This config enables the Intel(R) Speed Select Technology interface + drivers. The Intel(R) speed select technology features are non + architectural and only supported on specific Xeon(R) servers. + These drivers provide interface to directly communicate with hardware + via MMIO and Mail boxes to enumerate and control all the speed select + features. + + Enable this config, if there is a need to enable and control the + Intel(R) Speed Select Technology features from the user space. +endmenu diff --git a/drivers/platform/x86/intel/speed_select_if/Makefile b/drivers/platform/x86/intel/speed_select_if/Makefile new file mode 100644 index 0000000000..1d878a36d0 --- /dev/null +++ b/drivers/platform/x86/intel/speed_select_if/Makefile @@ -0,0 +1,12 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Makefile - Intel Speed Select Interface drivers +# Copyright (c) 2019, Intel Corporation. +# + +obj-$(CONFIG_INTEL_SPEED_SELECT_INTERFACE) += isst_if_common.o +obj-$(CONFIG_INTEL_SPEED_SELECT_INTERFACE) += isst_if_mmio.o +obj-$(CONFIG_INTEL_SPEED_SELECT_INTERFACE) += isst_if_mbox_pci.o +obj-$(CONFIG_INTEL_SPEED_SELECT_INTERFACE) += isst_if_mbox_msr.o +obj-$(CONFIG_INTEL_SPEED_SELECT_TPMI) += isst_tpmi_core.o +obj-$(CONFIG_INTEL_SPEED_SELECT_TPMI) += isst_tpmi.o diff --git a/drivers/platform/x86/intel/speed_select_if/isst_if_common.c b/drivers/platform/x86/intel/speed_select_if/isst_if_common.c new file mode 100644 index 0000000000..08df949460 --- /dev/null +++ b/drivers/platform/x86/intel/speed_select_if/isst_if_common.c @@ -0,0 +1,840 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Intel Speed Select Interface: Common functions + * Copyright (c) 2019, Intel Corporation. + * All rights reserved. + * + * Author: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com> + */ + +#include <linux/cpufeature.h> +#include <linux/cpuhotplug.h> +#include <linux/fs.h> +#include <linux/hashtable.h> +#include <linux/miscdevice.h> +#include <linux/module.h> +#include <linux/pci.h> +#include <linux/sched/signal.h> +#include <linux/slab.h> +#include <linux/uaccess.h> +#include <uapi/linux/isst_if.h> + +#include <asm/cpu_device_id.h> +#include <asm/intel-family.h> + +#include "isst_if_common.h" + +#define MSR_THREAD_ID_INFO 0x53 +#define MSR_PM_LOGICAL_ID 0x54 +#define MSR_CPU_BUS_NUMBER 0x128 + +static struct isst_if_cmd_cb punit_callbacks[ISST_IF_DEV_MAX]; + +static int punit_msr_white_list[] = { + MSR_TURBO_RATIO_LIMIT, + MSR_CONFIG_TDP_CONTROL, + MSR_TURBO_RATIO_LIMIT1, + MSR_TURBO_RATIO_LIMIT2, + MSR_PM_LOGICAL_ID, +}; + +struct isst_valid_cmd_ranges { + u16 cmd; + u16 sub_cmd_beg; + u16 sub_cmd_end; +}; + +struct isst_cmd_set_req_type { + u16 cmd; + u16 sub_cmd; + u16 param; +}; + +static const struct isst_valid_cmd_ranges isst_valid_cmds[] = { + {0xD0, 0x00, 0x03}, + {0x7F, 0x00, 0x0C}, + {0x7F, 0x10, 0x12}, + {0x7F, 0x20, 0x23}, + {0x94, 0x03, 0x03}, + {0x95, 0x03, 0x03}, +}; + +static const struct isst_cmd_set_req_type isst_cmd_set_reqs[] = { + {0xD0, 0x00, 0x08}, + {0xD0, 0x01, 0x08}, + {0xD0, 0x02, 0x08}, + {0xD0, 0x03, 0x08}, + {0x7F, 0x02, 0x00}, + {0x7F, 0x08, 0x00}, + {0x95, 0x03, 0x03}, +}; + +struct isst_cmd { + struct hlist_node hnode; + u64 data; + u32 cmd; + int cpu; + int mbox_cmd_type; + u32 param; +}; + +static bool isst_hpm_support; + +static DECLARE_HASHTABLE(isst_hash, 8); +static DEFINE_MUTEX(isst_hash_lock); + +static int isst_store_new_cmd(int cmd, u32 cpu, int mbox_cmd_type, u32 param, + u32 data) +{ + struct isst_cmd *sst_cmd; + + sst_cmd = kmalloc(sizeof(*sst_cmd), GFP_KERNEL); + if (!sst_cmd) + return -ENOMEM; + + sst_cmd->cpu = cpu; + sst_cmd->cmd = cmd; + sst_cmd->mbox_cmd_type = mbox_cmd_type; + sst_cmd->param = param; + sst_cmd->data = data; + + hash_add(isst_hash, &sst_cmd->hnode, sst_cmd->cmd); + + return 0; +} + +static void isst_delete_hash(void) +{ + struct isst_cmd *sst_cmd; + struct hlist_node *tmp; + int i; + + hash_for_each_safe(isst_hash, i, tmp, sst_cmd, hnode) { + hash_del(&sst_cmd->hnode); + kfree(sst_cmd); + } +} + +/** + * isst_store_cmd() - Store command to a hash table + * @cmd: Mailbox command. + * @sub_cmd: Mailbox sub-command or MSR id. + * @cpu: Target CPU for the command + * @mbox_cmd_type: Mailbox or MSR command. + * @param: Mailbox parameter. + * @data: Mailbox request data or MSR data. + * + * Stores the command to a hash table if there is no such command already + * stored. If already stored update the latest parameter and data for the + * command. + * + * Return: Return result of store to hash table, 0 for success, others for + * failure. + */ +int isst_store_cmd(int cmd, int sub_cmd, u32 cpu, int mbox_cmd_type, + u32 param, u64 data) +{ + struct isst_cmd *sst_cmd; + int full_cmd, ret; + + full_cmd = (cmd & GENMASK_ULL(15, 0)) << 16; + full_cmd |= (sub_cmd & GENMASK_ULL(15, 0)); + mutex_lock(&isst_hash_lock); + hash_for_each_possible(isst_hash, sst_cmd, hnode, full_cmd) { + if (sst_cmd->cmd == full_cmd && sst_cmd->cpu == cpu && + sst_cmd->mbox_cmd_type == mbox_cmd_type) { + sst_cmd->param = param; + sst_cmd->data = data; + mutex_unlock(&isst_hash_lock); + return 0; + } + } + + ret = isst_store_new_cmd(full_cmd, cpu, mbox_cmd_type, param, data); + mutex_unlock(&isst_hash_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(isst_store_cmd); + +static void isst_mbox_resume_command(struct isst_if_cmd_cb *cb, + struct isst_cmd *sst_cmd) +{ + struct isst_if_mbox_cmd mbox_cmd; + int wr_only; + + mbox_cmd.command = (sst_cmd->cmd & GENMASK_ULL(31, 16)) >> 16; + mbox_cmd.sub_command = sst_cmd->cmd & GENMASK_ULL(15, 0); + mbox_cmd.parameter = sst_cmd->param; + mbox_cmd.req_data = sst_cmd->data; + mbox_cmd.logical_cpu = sst_cmd->cpu; + (cb->cmd_callback)((u8 *)&mbox_cmd, &wr_only, 1); +} + +/** + * isst_resume_common() - Process Resume request + * + * On resume replay all mailbox commands and MSRs. + * + * Return: None. + */ +void isst_resume_common(void) +{ + struct isst_cmd *sst_cmd; + int i; + + hash_for_each(isst_hash, i, sst_cmd, hnode) { + struct isst_if_cmd_cb *cb; + + if (sst_cmd->mbox_cmd_type) { + cb = &punit_callbacks[ISST_IF_DEV_MBOX]; + if (cb->registered) + isst_mbox_resume_command(cb, sst_cmd); + } else { + wrmsrl_safe_on_cpu(sst_cmd->cpu, sst_cmd->cmd, + sst_cmd->data); + } + } +} +EXPORT_SYMBOL_GPL(isst_resume_common); + +static void isst_restore_msr_local(int cpu) +{ + struct isst_cmd *sst_cmd; + int i; + + mutex_lock(&isst_hash_lock); + for (i = 0; i < ARRAY_SIZE(punit_msr_white_list); ++i) { + if (!punit_msr_white_list[i]) + break; + + hash_for_each_possible(isst_hash, sst_cmd, hnode, + punit_msr_white_list[i]) { + if (!sst_cmd->mbox_cmd_type && sst_cmd->cpu == cpu) + wrmsrl_safe(sst_cmd->cmd, sst_cmd->data); + } + } + mutex_unlock(&isst_hash_lock); +} + +/** + * isst_if_mbox_cmd_invalid() - Check invalid mailbox commands + * @cmd: Pointer to the command structure to verify. + * + * Invalid command to PUNIT to may result in instability of the platform. + * This function has a whitelist of commands, which are allowed. + * + * Return: Return true if the command is invalid, else false. + */ +bool isst_if_mbox_cmd_invalid(struct isst_if_mbox_cmd *cmd) +{ + int i; + + if (cmd->logical_cpu >= nr_cpu_ids) + return true; + + for (i = 0; i < ARRAY_SIZE(isst_valid_cmds); ++i) { + if (cmd->command == isst_valid_cmds[i].cmd && + (cmd->sub_command >= isst_valid_cmds[i].sub_cmd_beg && + cmd->sub_command <= isst_valid_cmds[i].sub_cmd_end)) { + return false; + } + } + + return true; +} +EXPORT_SYMBOL_GPL(isst_if_mbox_cmd_invalid); + +/** + * isst_if_mbox_cmd_set_req() - Check mailbox command is a set request + * @cmd: Pointer to the command structure to verify. + * + * Check if the given mail box level is set request and not a get request. + * + * Return: Return true if the command is set_req, else false. + */ +bool isst_if_mbox_cmd_set_req(struct isst_if_mbox_cmd *cmd) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(isst_cmd_set_reqs); ++i) { + if (cmd->command == isst_cmd_set_reqs[i].cmd && + cmd->sub_command == isst_cmd_set_reqs[i].sub_cmd && + cmd->parameter == isst_cmd_set_reqs[i].param) { + return true; + } + } + + return false; +} +EXPORT_SYMBOL_GPL(isst_if_mbox_cmd_set_req); + +static int isst_if_api_version; + +static int isst_if_get_platform_info(void __user *argp) +{ + struct isst_if_platform_info info; + + info.api_version = isst_if_api_version; + info.driver_version = ISST_IF_DRIVER_VERSION; + info.max_cmds_per_ioctl = ISST_IF_CMD_LIMIT; + info.mbox_supported = punit_callbacks[ISST_IF_DEV_MBOX].registered; + info.mmio_supported = punit_callbacks[ISST_IF_DEV_MMIO].registered; + + if (copy_to_user(argp, &info, sizeof(info))) + return -EFAULT; + + return 0; +} + +#define ISST_MAX_BUS_NUMBER 2 + +struct isst_if_cpu_info { + /* For BUS 0 and BUS 1 only, which we need for PUNIT interface */ + int bus_info[ISST_MAX_BUS_NUMBER]; + struct pci_dev *pci_dev[ISST_MAX_BUS_NUMBER]; + int punit_cpu_id; + int numa_node; +}; + +struct isst_if_pkg_info { + struct pci_dev *pci_dev[ISST_MAX_BUS_NUMBER]; +}; + +static struct isst_if_cpu_info *isst_cpu_info; +static struct isst_if_pkg_info *isst_pkg_info; + +static struct pci_dev *_isst_if_get_pci_dev(int cpu, int bus_no, int dev, int fn) +{ + struct pci_dev *matched_pci_dev = NULL; + struct pci_dev *pci_dev = NULL; + struct pci_dev *_pci_dev = NULL; + int no_matches = 0, pkg_id; + int bus_number; + + if (bus_no < 0 || bus_no >= ISST_MAX_BUS_NUMBER || cpu < 0 || + cpu >= nr_cpu_ids || cpu >= num_possible_cpus()) + return NULL; + + pkg_id = topology_physical_package_id(cpu); + + bus_number = isst_cpu_info[cpu].bus_info[bus_no]; + if (bus_number < 0) + return NULL; + + for_each_pci_dev(_pci_dev) { + int node; + + if (_pci_dev->bus->number != bus_number || + _pci_dev->devfn != PCI_DEVFN(dev, fn)) + continue; + + ++no_matches; + if (!matched_pci_dev) + matched_pci_dev = _pci_dev; + + node = dev_to_node(&_pci_dev->dev); + if (node == NUMA_NO_NODE) { + pr_info_once("Fail to get numa node for CPU:%d bus:%d dev:%d fn:%d\n", + cpu, bus_no, dev, fn); + continue; + } + + if (node == isst_cpu_info[cpu].numa_node) { + isst_pkg_info[pkg_id].pci_dev[bus_no] = _pci_dev; + + pci_dev = _pci_dev; + break; + } + } + + /* + * If there is no numa matched pci_dev, then there can be following cases: + * 1. CONFIG_NUMA is not defined: In this case if there is only single device + * match, then we don't need numa information. Simply return last match. + * Othewise return NULL. + * 2. NUMA information is not exposed via _SEG method. In this case it is similar + * to case 1. + * 3. Numa information doesn't match with CPU numa node and more than one match + * return NULL. + */ + if (!pci_dev && no_matches == 1) + pci_dev = matched_pci_dev; + + /* Return pci_dev pointer for any matched CPU in the package */ + if (!pci_dev) + pci_dev = isst_pkg_info[pkg_id].pci_dev[bus_no]; + + return pci_dev; +} + +/** + * isst_if_get_pci_dev() - Get the PCI device instance for a CPU + * @cpu: Logical CPU number. + * @bus_no: The bus number assigned by the hardware. + * @dev: The device number assigned by the hardware. + * @fn: The function number assigned by the hardware. + * + * Using cached bus information, find out the PCI device for a bus number, + * device and function. + * + * Return: Return pci_dev pointer or NULL. + */ +struct pci_dev *isst_if_get_pci_dev(int cpu, int bus_no, int dev, int fn) +{ + struct pci_dev *pci_dev; + + if (bus_no < 0 || bus_no >= ISST_MAX_BUS_NUMBER || cpu < 0 || + cpu >= nr_cpu_ids || cpu >= num_possible_cpus()) + return NULL; + + pci_dev = isst_cpu_info[cpu].pci_dev[bus_no]; + + if (pci_dev && pci_dev->devfn == PCI_DEVFN(dev, fn)) + return pci_dev; + + return _isst_if_get_pci_dev(cpu, bus_no, dev, fn); +} +EXPORT_SYMBOL_GPL(isst_if_get_pci_dev); + +static int isst_if_cpu_online(unsigned int cpu) +{ + u64 data; + int ret; + + isst_cpu_info[cpu].numa_node = cpu_to_node(cpu); + + ret = rdmsrl_safe(MSR_CPU_BUS_NUMBER, &data); + if (ret) { + /* This is not a fatal error on MSR mailbox only I/F */ + isst_cpu_info[cpu].bus_info[0] = -1; + isst_cpu_info[cpu].bus_info[1] = -1; + } else { + isst_cpu_info[cpu].bus_info[0] = data & 0xff; + isst_cpu_info[cpu].bus_info[1] = (data >> 8) & 0xff; + isst_cpu_info[cpu].pci_dev[0] = _isst_if_get_pci_dev(cpu, 0, 0, 1); + isst_cpu_info[cpu].pci_dev[1] = _isst_if_get_pci_dev(cpu, 1, 30, 1); + } + + if (isst_hpm_support) { + + ret = rdmsrl_safe(MSR_PM_LOGICAL_ID, &data); + if (!ret) + goto set_punit_id; + } + + ret = rdmsrl_safe(MSR_THREAD_ID_INFO, &data); + if (ret) { + isst_cpu_info[cpu].punit_cpu_id = -1; + return ret; + } + +set_punit_id: + isst_cpu_info[cpu].punit_cpu_id = data; + + isst_restore_msr_local(cpu); + + return 0; +} + +static int isst_if_online_id; + +static int isst_if_cpu_info_init(void) +{ + int ret; + + isst_cpu_info = kcalloc(num_possible_cpus(), + sizeof(*isst_cpu_info), + GFP_KERNEL); + if (!isst_cpu_info) + return -ENOMEM; + + isst_pkg_info = kcalloc(topology_max_packages(), + sizeof(*isst_pkg_info), + GFP_KERNEL); + if (!isst_pkg_info) { + kfree(isst_cpu_info); + return -ENOMEM; + } + + ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, + "platform/x86/isst-if:online", + isst_if_cpu_online, NULL); + if (ret < 0) { + kfree(isst_pkg_info); + kfree(isst_cpu_info); + return ret; + } + + isst_if_online_id = ret; + + return 0; +} + +static void isst_if_cpu_info_exit(void) +{ + cpuhp_remove_state(isst_if_online_id); + kfree(isst_pkg_info); + kfree(isst_cpu_info); +}; + +static long isst_if_proc_phyid_req(u8 *cmd_ptr, int *write_only, int resume) +{ + struct isst_if_cpu_map *cpu_map; + + cpu_map = (struct isst_if_cpu_map *)cmd_ptr; + if (cpu_map->logical_cpu >= nr_cpu_ids || + cpu_map->logical_cpu >= num_possible_cpus()) + return -EINVAL; + + *write_only = 0; + cpu_map->physical_cpu = isst_cpu_info[cpu_map->logical_cpu].punit_cpu_id; + + return 0; +} + +static bool match_punit_msr_white_list(int msr) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(punit_msr_white_list); ++i) { + if (punit_msr_white_list[i] == msr) + return true; + } + + return false; +} + +static long isst_if_msr_cmd_req(u8 *cmd_ptr, int *write_only, int resume) +{ + struct isst_if_msr_cmd *msr_cmd; + int ret; + + msr_cmd = (struct isst_if_msr_cmd *)cmd_ptr; + + if (!match_punit_msr_white_list(msr_cmd->msr)) + return -EINVAL; + + if (msr_cmd->logical_cpu >= nr_cpu_ids) + return -EINVAL; + + if (msr_cmd->read_write) { + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + ret = wrmsrl_safe_on_cpu(msr_cmd->logical_cpu, + msr_cmd->msr, + msr_cmd->data); + *write_only = 1; + if (!ret && !resume) + ret = isst_store_cmd(0, msr_cmd->msr, + msr_cmd->logical_cpu, + 0, 0, msr_cmd->data); + } else { + u64 data; + + ret = rdmsrl_safe_on_cpu(msr_cmd->logical_cpu, + msr_cmd->msr, &data); + if (!ret) { + msr_cmd->data = data; + *write_only = 0; + } + } + + + return ret; +} + +static long isst_if_exec_multi_cmd(void __user *argp, struct isst_if_cmd_cb *cb) +{ + unsigned char __user *ptr; + u32 cmd_count; + u8 *cmd_ptr; + long ret; + int i; + + /* Each multi command has u32 command count as the first field */ + if (copy_from_user(&cmd_count, argp, sizeof(cmd_count))) + return -EFAULT; + + if (!cmd_count || cmd_count > ISST_IF_CMD_LIMIT) + return -EINVAL; + + cmd_ptr = kmalloc(cb->cmd_size, GFP_KERNEL); + if (!cmd_ptr) + return -ENOMEM; + + /* cb->offset points to start of the command after the command count */ + ptr = argp + cb->offset; + + for (i = 0; i < cmd_count; ++i) { + int wr_only; + + if (signal_pending(current)) { + ret = -EINTR; + break; + } + + if (copy_from_user(cmd_ptr, ptr, cb->cmd_size)) { + ret = -EFAULT; + break; + } + + ret = cb->cmd_callback(cmd_ptr, &wr_only, 0); + if (ret) + break; + + if (!wr_only && copy_to_user(ptr, cmd_ptr, cb->cmd_size)) { + ret = -EFAULT; + break; + } + + ptr += cb->cmd_size; + } + + kfree(cmd_ptr); + + return i ? i : ret; +} + +static long isst_if_def_ioctl(struct file *file, unsigned int cmd, + unsigned long arg) +{ + void __user *argp = (void __user *)arg; + struct isst_if_cmd_cb cmd_cb; + struct isst_if_cmd_cb *cb; + long ret = -ENOTTY; + int i; + + switch (cmd) { + case ISST_IF_GET_PLATFORM_INFO: + ret = isst_if_get_platform_info(argp); + break; + case ISST_IF_GET_PHY_ID: + cmd_cb.cmd_size = sizeof(struct isst_if_cpu_map); + cmd_cb.offset = offsetof(struct isst_if_cpu_maps, cpu_map); + cmd_cb.cmd_callback = isst_if_proc_phyid_req; + ret = isst_if_exec_multi_cmd(argp, &cmd_cb); + break; + case ISST_IF_IO_CMD: + cb = &punit_callbacks[ISST_IF_DEV_MMIO]; + if (cb->registered) + ret = isst_if_exec_multi_cmd(argp, cb); + break; + case ISST_IF_MBOX_COMMAND: + cb = &punit_callbacks[ISST_IF_DEV_MBOX]; + if (cb->registered) + ret = isst_if_exec_multi_cmd(argp, cb); + break; + case ISST_IF_MSR_COMMAND: + cmd_cb.cmd_size = sizeof(struct isst_if_msr_cmd); + cmd_cb.offset = offsetof(struct isst_if_msr_cmds, msr_cmd); + cmd_cb.cmd_callback = isst_if_msr_cmd_req; + ret = isst_if_exec_multi_cmd(argp, &cmd_cb); + break; + default: + for (i = 0; i < ISST_IF_DEV_MAX; ++i) { + struct isst_if_cmd_cb *cb = &punit_callbacks[i]; + int ret; + + if (cb->def_ioctl) { + ret = cb->def_ioctl(file, cmd, arg); + if (!ret) + return ret; + } + } + break; + } + + return ret; +} + +/* Lock to prevent module registration when already opened by user space */ +static DEFINE_MUTEX(punit_misc_dev_open_lock); +/* Lock to allow one shared misc device for all ISST interfaces */ +static DEFINE_MUTEX(punit_misc_dev_reg_lock); +static int misc_usage_count; +static int misc_device_ret; +static int misc_device_open; + +static int isst_if_open(struct inode *inode, struct file *file) +{ + int i, ret = 0; + + /* Fail open, if a module is going away */ + mutex_lock(&punit_misc_dev_open_lock); + for (i = 0; i < ISST_IF_DEV_MAX; ++i) { + struct isst_if_cmd_cb *cb = &punit_callbacks[i]; + + if (cb->registered && !try_module_get(cb->owner)) { + ret = -ENODEV; + break; + } + } + if (ret) { + int j; + + for (j = 0; j < i; ++j) { + struct isst_if_cmd_cb *cb; + + cb = &punit_callbacks[j]; + if (cb->registered) + module_put(cb->owner); + } + } else { + misc_device_open++; + } + mutex_unlock(&punit_misc_dev_open_lock); + + return ret; +} + +static int isst_if_relase(struct inode *inode, struct file *f) +{ + int i; + + mutex_lock(&punit_misc_dev_open_lock); + misc_device_open--; + for (i = 0; i < ISST_IF_DEV_MAX; ++i) { + struct isst_if_cmd_cb *cb = &punit_callbacks[i]; + + if (cb->registered) + module_put(cb->owner); + } + mutex_unlock(&punit_misc_dev_open_lock); + + return 0; +} + +static const struct file_operations isst_if_char_driver_ops = { + .open = isst_if_open, + .unlocked_ioctl = isst_if_def_ioctl, + .release = isst_if_relase, +}; + +static struct miscdevice isst_if_char_driver = { + .minor = MISC_DYNAMIC_MINOR, + .name = "isst_interface", + .fops = &isst_if_char_driver_ops, +}; + +static const struct x86_cpu_id hpm_cpu_ids[] = { + X86_MATCH_INTEL_FAM6_MODEL(GRANITERAPIDS_X, NULL), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_CRESTMONT_X, NULL), + {} +}; + +static int isst_misc_reg(void) +{ + mutex_lock(&punit_misc_dev_reg_lock); + if (misc_device_ret) + goto unlock_exit; + + if (!misc_usage_count) { + const struct x86_cpu_id *id; + + id = x86_match_cpu(hpm_cpu_ids); + if (id) + isst_hpm_support = true; + + misc_device_ret = isst_if_cpu_info_init(); + if (misc_device_ret) + goto unlock_exit; + + misc_device_ret = misc_register(&isst_if_char_driver); + if (misc_device_ret) { + isst_if_cpu_info_exit(); + goto unlock_exit; + } + } + misc_usage_count++; + +unlock_exit: + mutex_unlock(&punit_misc_dev_reg_lock); + + return misc_device_ret; +} + +static void isst_misc_unreg(void) +{ + mutex_lock(&punit_misc_dev_reg_lock); + if (misc_usage_count) + misc_usage_count--; + if (!misc_usage_count && !misc_device_ret) { + misc_deregister(&isst_if_char_driver); + isst_if_cpu_info_exit(); + } + mutex_unlock(&punit_misc_dev_reg_lock); +} + +/** + * isst_if_cdev_register() - Register callback for IOCTL + * @device_type: The device type this callback handling. + * @cb: Callback structure. + * + * This function registers a callback to device type. On very first call + * it will register a misc device, which is used for user kernel interface. + * Other calls simply increment ref count. Registry will fail, if the user + * already opened misc device for operation. Also if the misc device + * creation failed, then it will not try again and all callers will get + * failure code. + * + * Return: Return the return value from the misc creation device or -EINVAL + * for unsupported device type. + */ +int isst_if_cdev_register(int device_type, struct isst_if_cmd_cb *cb) +{ + int ret; + + if (device_type >= ISST_IF_DEV_MAX) + return -EINVAL; + + mutex_lock(&punit_misc_dev_open_lock); + /* Device is already open, we don't want to add new callbacks */ + if (misc_device_open) { + mutex_unlock(&punit_misc_dev_open_lock); + return -EAGAIN; + } + if (!cb->api_version) + cb->api_version = ISST_IF_API_VERSION; + if (cb->api_version > isst_if_api_version) + isst_if_api_version = cb->api_version; + memcpy(&punit_callbacks[device_type], cb, sizeof(*cb)); + punit_callbacks[device_type].registered = 1; + mutex_unlock(&punit_misc_dev_open_lock); + + ret = isst_misc_reg(); + if (ret) { + /* + * No need of mutex as the misc device register failed + * as no one can open device yet. Hence no contention. + */ + punit_callbacks[device_type].registered = 0; + return ret; + } + return 0; +} +EXPORT_SYMBOL_GPL(isst_if_cdev_register); + +/** + * isst_if_cdev_unregister() - Unregister callback for IOCTL + * @device_type: The device type to unregister. + * + * This function unregisters the previously registered callback. If this + * is the last callback unregistering, then misc device is removed. + * + * Return: None. + */ +void isst_if_cdev_unregister(int device_type) +{ + isst_misc_unreg(); + mutex_lock(&punit_misc_dev_open_lock); + punit_callbacks[device_type].def_ioctl = NULL; + punit_callbacks[device_type].registered = 0; + if (device_type == ISST_IF_DEV_MBOX) + isst_delete_hash(); + mutex_unlock(&punit_misc_dev_open_lock); +} +EXPORT_SYMBOL_GPL(isst_if_cdev_unregister); + +MODULE_LICENSE("GPL v2"); diff --git a/drivers/platform/x86/intel/speed_select_if/isst_if_common.h b/drivers/platform/x86/intel/speed_select_if/isst_if_common.h new file mode 100644 index 0000000000..1004f2c9cc --- /dev/null +++ b/drivers/platform/x86/intel/speed_select_if/isst_if_common.h @@ -0,0 +1,79 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Intel Speed Select Interface: Drivers Internal defines + * Copyright (c) 2019, Intel Corporation. + * All rights reserved. + * + * Author: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com> + */ + +#ifndef __ISST_IF_COMMON_H +#define __ISST_IF_COMMON_H + +#define PCI_DEVICE_ID_INTEL_RAPL_PRIO_DEVID_0 0x3451 +#define PCI_DEVICE_ID_INTEL_CFG_MBOX_DEVID_0 0x3459 + +#define PCI_DEVICE_ID_INTEL_RAPL_PRIO_DEVID_1 0x3251 +#define PCI_DEVICE_ID_INTEL_CFG_MBOX_DEVID_1 0x3259 + +/* + * Validate maximum commands in a single request. + * This is enough to handle command to every core in one ioctl, or all + * possible message id to one CPU. Limit is also helpful for resonse time + * per IOCTL request, as PUNIT may take different times to process each + * request and may hold for long for too many commands. + */ +#define ISST_IF_CMD_LIMIT 64 + +#define ISST_IF_API_VERSION 0x01 +#define ISST_IF_DRIVER_VERSION 0x01 + +#define ISST_IF_DEV_MBOX 0 +#define ISST_IF_DEV_MMIO 1 +#define ISST_IF_DEV_TPMI 2 +#define ISST_IF_DEV_MAX 3 + +/** + * struct isst_if_cmd_cb - Used to register a IOCTL handler + * @registered: Used by the common code to store registry. Caller don't + * to touch this field + * @cmd_size: The command size of the individual command in IOCTL + * @offset: Offset to the first valid member in command structure. + * This will be the offset of the start of the command + * after command count field + * @api_version: API version supported for this target. 0, if none. + * @owner: Registered module owner + * @cmd_callback: Callback function to handle IOCTL. The callback has the + * command pointer with data for command. There is a pointer + * called write_only, which when set, will not copy the + * response to user ioctl buffer. The "resume" argument + * can be used to avoid storing the command for replay + * during system resume + * @def_ioctl: Default IOCTL handler callback, if there is no match in + * the existing list of IOCTL handled by the common handler. + * + * This structure is used to register an handler for IOCTL. To avoid + * code duplication common code handles all the IOCTL command read/write + * including handling multiple command in single IOCTL. The caller just + * need to execute a command via the registered callback. + */ +struct isst_if_cmd_cb { + int registered; + int cmd_size; + int offset; + int api_version; + struct module *owner; + long (*cmd_callback)(u8 *ptr, int *write_only, int resume); + long (*def_ioctl)(struct file *file, unsigned int cmd, unsigned long arg); +}; + +/* Internal interface functions */ +int isst_if_cdev_register(int type, struct isst_if_cmd_cb *cb); +void isst_if_cdev_unregister(int type); +struct pci_dev *isst_if_get_pci_dev(int cpu, int bus, int dev, int fn); +bool isst_if_mbox_cmd_set_req(struct isst_if_mbox_cmd *mbox_cmd); +bool isst_if_mbox_cmd_invalid(struct isst_if_mbox_cmd *cmd); +int isst_store_cmd(int cmd, int sub_command, u32 cpu, int mbox_cmd, + u32 param, u64 data); +void isst_resume_common(void); +#endif diff --git a/drivers/platform/x86/intel/speed_select_if/isst_if_mbox_msr.c b/drivers/platform/x86/intel/speed_select_if/isst_if_mbox_msr.c new file mode 100644 index 0000000000..1b6eab0710 --- /dev/null +++ b/drivers/platform/x86/intel/speed_select_if/isst_if_mbox_msr.c @@ -0,0 +1,214 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Intel Speed Select Interface: Mbox via MSR Interface + * Copyright (c) 2019, Intel Corporation. + * All rights reserved. + * + * Author: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com> + */ + +#include <linux/module.h> +#include <linux/cpuhotplug.h> +#include <linux/pci.h> +#include <linux/sched/signal.h> +#include <linux/slab.h> +#include <linux/suspend.h> +#include <linux/topology.h> +#include <linux/uaccess.h> +#include <uapi/linux/isst_if.h> +#include <asm/cpu_device_id.h> +#include <asm/intel-family.h> + +#include "isst_if_common.h" + +#define MSR_OS_MAILBOX_INTERFACE 0xB0 +#define MSR_OS_MAILBOX_DATA 0xB1 +#define MSR_OS_MAILBOX_BUSY_BIT 31 + +/* + * Based on experiments count is never more than 1, as the MSR overhead + * is enough to finish the command. So here this is the worst case number. + */ +#define OS_MAILBOX_RETRY_COUNT 3 + +static int isst_if_send_mbox_cmd(u8 command, u8 sub_command, u32 parameter, + u32 command_data, u32 *response_data) +{ + u32 retries; + u64 data; + int ret; + + /* Poll for rb bit == 0 */ + retries = OS_MAILBOX_RETRY_COUNT; + do { + rdmsrl(MSR_OS_MAILBOX_INTERFACE, data); + if (data & BIT_ULL(MSR_OS_MAILBOX_BUSY_BIT)) { + ret = -EBUSY; + continue; + } + ret = 0; + break; + } while (--retries); + + if (ret) + return ret; + + /* Write DATA register */ + wrmsrl(MSR_OS_MAILBOX_DATA, command_data); + + /* Write command register */ + data = BIT_ULL(MSR_OS_MAILBOX_BUSY_BIT) | + (parameter & GENMASK_ULL(13, 0)) << 16 | + (sub_command << 8) | + command; + wrmsrl(MSR_OS_MAILBOX_INTERFACE, data); + + /* Poll for rb bit == 0 */ + retries = OS_MAILBOX_RETRY_COUNT; + do { + rdmsrl(MSR_OS_MAILBOX_INTERFACE, data); + if (data & BIT_ULL(MSR_OS_MAILBOX_BUSY_BIT)) { + ret = -EBUSY; + continue; + } + + if (data & 0xff) + return -ENXIO; + + if (response_data) { + rdmsrl(MSR_OS_MAILBOX_DATA, data); + *response_data = data; + } + ret = 0; + break; + } while (--retries); + + return ret; +} + +struct msrl_action { + int err; + struct isst_if_mbox_cmd *mbox_cmd; +}; + +/* revisit, smp_call_function_single should be enough for atomic mailbox! */ +static void msrl_update_func(void *info) +{ + struct msrl_action *act = info; + + act->err = isst_if_send_mbox_cmd(act->mbox_cmd->command, + act->mbox_cmd->sub_command, + act->mbox_cmd->parameter, + act->mbox_cmd->req_data, + &act->mbox_cmd->resp_data); +} + +static long isst_if_mbox_proc_cmd(u8 *cmd_ptr, int *write_only, int resume) +{ + struct msrl_action action; + int ret; + + action.mbox_cmd = (struct isst_if_mbox_cmd *)cmd_ptr; + + if (isst_if_mbox_cmd_invalid(action.mbox_cmd)) + return -EINVAL; + + if (isst_if_mbox_cmd_set_req(action.mbox_cmd) && + !capable(CAP_SYS_ADMIN)) + return -EPERM; + + /* + * To complete mailbox command, we need to access two MSRs. + * So we don't want race to complete a mailbox transcation. + * Here smp_call ensures that msrl_update_func() has no race + * and also with wait flag, wait for completion. + * smp_call_function_single is using get_cpu() and put_cpu(). + */ + ret = smp_call_function_single(action.mbox_cmd->logical_cpu, + msrl_update_func, &action, 1); + if (ret) + return ret; + + if (!action.err && !resume && isst_if_mbox_cmd_set_req(action.mbox_cmd)) + action.err = isst_store_cmd(action.mbox_cmd->command, + action.mbox_cmd->sub_command, + action.mbox_cmd->logical_cpu, 1, + action.mbox_cmd->parameter, + action.mbox_cmd->req_data); + *write_only = 0; + + return action.err; +} + + +static int isst_pm_notify(struct notifier_block *nb, + unsigned long mode, void *_unused) +{ + switch (mode) { + case PM_POST_HIBERNATION: + case PM_POST_RESTORE: + case PM_POST_SUSPEND: + isst_resume_common(); + break; + default: + break; + } + return 0; +} + +static struct notifier_block isst_pm_nb = { + .notifier_call = isst_pm_notify, +}; + +static const struct x86_cpu_id isst_if_cpu_ids[] = { + X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_X, NULL), + {} +}; +MODULE_DEVICE_TABLE(x86cpu, isst_if_cpu_ids); + +static int __init isst_if_mbox_init(void) +{ + struct isst_if_cmd_cb cb; + const struct x86_cpu_id *id; + u64 data; + int ret; + + id = x86_match_cpu(isst_if_cpu_ids); + if (!id) + return -ENODEV; + + /* Check presence of mailbox MSRs */ + ret = rdmsrl_safe(MSR_OS_MAILBOX_INTERFACE, &data); + if (ret) + return ret; + + ret = rdmsrl_safe(MSR_OS_MAILBOX_DATA, &data); + if (ret) + return ret; + + memset(&cb, 0, sizeof(cb)); + cb.cmd_size = sizeof(struct isst_if_mbox_cmd); + cb.offset = offsetof(struct isst_if_mbox_cmds, mbox_cmd); + cb.cmd_callback = isst_if_mbox_proc_cmd; + cb.owner = THIS_MODULE; + ret = isst_if_cdev_register(ISST_IF_DEV_MBOX, &cb); + if (ret) + return ret; + + ret = register_pm_notifier(&isst_pm_nb); + if (ret) + isst_if_cdev_unregister(ISST_IF_DEV_MBOX); + + return ret; +} +module_init(isst_if_mbox_init) + +static void __exit isst_if_mbox_exit(void) +{ + unregister_pm_notifier(&isst_pm_nb); + isst_if_cdev_unregister(ISST_IF_DEV_MBOX); +} +module_exit(isst_if_mbox_exit) + +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("Intel speed select interface mailbox driver"); diff --git a/drivers/platform/x86/intel/speed_select_if/isst_if_mbox_pci.c b/drivers/platform/x86/intel/speed_select_if/isst_if_mbox_pci.c new file mode 100644 index 0000000000..df1fc6c719 --- /dev/null +++ b/drivers/platform/x86/intel/speed_select_if/isst_if_mbox_pci.c @@ -0,0 +1,227 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Intel Speed Select Interface: Mbox via PCI Interface + * Copyright (c) 2019, Intel Corporation. + * All rights reserved. + * + * Author: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com> + */ + +#include <linux/cpufeature.h> +#include <linux/module.h> +#include <linux/pci.h> +#include <linux/sched/signal.h> +#include <linux/uaccess.h> +#include <uapi/linux/isst_if.h> + +#include "isst_if_common.h" + +#define PUNIT_MAILBOX_DATA 0xA0 +#define PUNIT_MAILBOX_INTERFACE 0xA4 +#define PUNIT_MAILBOX_BUSY_BIT 31 + +/* + * The average time to complete mailbox commands is less than 40us. Most of + * the commands complete in few micro seconds. But the same firmware handles + * requests from all power management features. + * We can create a scenario where we flood the firmware with requests then + * the mailbox response can be delayed for 100s of micro seconds. So define + * two timeouts. One for average case and one for long. + * If the firmware is taking more than average, just call cond_resched(). + */ +#define OS_MAILBOX_TIMEOUT_AVG_US 40 +#define OS_MAILBOX_TIMEOUT_MAX_US 1000 + +struct isst_if_device { + struct mutex mutex; +}; + +static int isst_if_mbox_cmd(struct pci_dev *pdev, + struct isst_if_mbox_cmd *mbox_cmd) +{ + s64 tm_delta = 0; + ktime_t tm; + u32 data; + int ret; + + /* Poll for rb bit == 0 */ + tm = ktime_get(); + do { + ret = pci_read_config_dword(pdev, PUNIT_MAILBOX_INTERFACE, + &data); + if (ret) + return ret; + + if (data & BIT_ULL(PUNIT_MAILBOX_BUSY_BIT)) { + ret = -EBUSY; + tm_delta = ktime_us_delta(ktime_get(), tm); + if (tm_delta > OS_MAILBOX_TIMEOUT_AVG_US) + cond_resched(); + continue; + } + ret = 0; + break; + } while (tm_delta < OS_MAILBOX_TIMEOUT_MAX_US); + + if (ret) + return ret; + + /* Write DATA register */ + ret = pci_write_config_dword(pdev, PUNIT_MAILBOX_DATA, + mbox_cmd->req_data); + if (ret) + return ret; + + /* Write command register */ + data = BIT_ULL(PUNIT_MAILBOX_BUSY_BIT) | + (mbox_cmd->parameter & GENMASK_ULL(13, 0)) << 16 | + (mbox_cmd->sub_command << 8) | + mbox_cmd->command; + + ret = pci_write_config_dword(pdev, PUNIT_MAILBOX_INTERFACE, data); + if (ret) + return ret; + + /* Poll for rb bit == 0 */ + tm_delta = 0; + tm = ktime_get(); + do { + ret = pci_read_config_dword(pdev, PUNIT_MAILBOX_INTERFACE, + &data); + if (ret) + return ret; + + if (data & BIT_ULL(PUNIT_MAILBOX_BUSY_BIT)) { + ret = -EBUSY; + tm_delta = ktime_us_delta(ktime_get(), tm); + if (tm_delta > OS_MAILBOX_TIMEOUT_AVG_US) + cond_resched(); + continue; + } + + if (data & 0xff) + return -ENXIO; + + ret = pci_read_config_dword(pdev, PUNIT_MAILBOX_DATA, &data); + if (ret) + return ret; + + mbox_cmd->resp_data = data; + ret = 0; + break; + } while (tm_delta < OS_MAILBOX_TIMEOUT_MAX_US); + + return ret; +} + +static long isst_if_mbox_proc_cmd(u8 *cmd_ptr, int *write_only, int resume) +{ + struct isst_if_mbox_cmd *mbox_cmd; + struct isst_if_device *punit_dev; + struct pci_dev *pdev; + int ret; + + mbox_cmd = (struct isst_if_mbox_cmd *)cmd_ptr; + + if (isst_if_mbox_cmd_invalid(mbox_cmd)) + return -EINVAL; + + if (isst_if_mbox_cmd_set_req(mbox_cmd) && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + pdev = isst_if_get_pci_dev(mbox_cmd->logical_cpu, 1, 30, 1); + if (!pdev) + return -EINVAL; + + punit_dev = pci_get_drvdata(pdev); + if (!punit_dev) + return -EINVAL; + + /* + * Basically we are allowing one complete mailbox transaction on + * a mapped PCI device at a time. + */ + mutex_lock(&punit_dev->mutex); + ret = isst_if_mbox_cmd(pdev, mbox_cmd); + if (!ret && !resume && isst_if_mbox_cmd_set_req(mbox_cmd)) + ret = isst_store_cmd(mbox_cmd->command, + mbox_cmd->sub_command, + mbox_cmd->logical_cpu, 1, + mbox_cmd->parameter, + mbox_cmd->req_data); + mutex_unlock(&punit_dev->mutex); + if (ret) + return ret; + + *write_only = 0; + + return 0; +} + +static const struct pci_device_id isst_if_mbox_ids[] = { + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_CFG_MBOX_DEVID_0)}, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_CFG_MBOX_DEVID_1)}, + { 0 }, +}; +MODULE_DEVICE_TABLE(pci, isst_if_mbox_ids); + +static int isst_if_mbox_probe(struct pci_dev *pdev, + const struct pci_device_id *ent) +{ + struct isst_if_device *punit_dev; + struct isst_if_cmd_cb cb; + int ret; + + punit_dev = devm_kzalloc(&pdev->dev, sizeof(*punit_dev), GFP_KERNEL); + if (!punit_dev) + return -ENOMEM; + + ret = pcim_enable_device(pdev); + if (ret) + return ret; + + mutex_init(&punit_dev->mutex); + pci_set_drvdata(pdev, punit_dev); + + memset(&cb, 0, sizeof(cb)); + cb.cmd_size = sizeof(struct isst_if_mbox_cmd); + cb.offset = offsetof(struct isst_if_mbox_cmds, mbox_cmd); + cb.cmd_callback = isst_if_mbox_proc_cmd; + cb.owner = THIS_MODULE; + ret = isst_if_cdev_register(ISST_IF_DEV_MBOX, &cb); + + if (ret) + mutex_destroy(&punit_dev->mutex); + + return ret; +} + +static void isst_if_mbox_remove(struct pci_dev *pdev) +{ + struct isst_if_device *punit_dev; + + punit_dev = pci_get_drvdata(pdev); + isst_if_cdev_unregister(ISST_IF_DEV_MBOX); + mutex_destroy(&punit_dev->mutex); +} + +static int __maybe_unused isst_if_resume(struct device *device) +{ + isst_resume_common(); + return 0; +} + +static SIMPLE_DEV_PM_OPS(isst_if_pm_ops, NULL, isst_if_resume); + +static struct pci_driver isst_if_pci_driver = { + .name = "isst_if_mbox_pci", + .id_table = isst_if_mbox_ids, + .probe = isst_if_mbox_probe, + .remove = isst_if_mbox_remove, + .driver.pm = &isst_if_pm_ops, +}; + +module_pci_driver(isst_if_pci_driver); + +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("Intel speed select interface pci mailbox driver"); diff --git a/drivers/platform/x86/intel/speed_select_if/isst_if_mmio.c b/drivers/platform/x86/intel/speed_select_if/isst_if_mmio.c new file mode 100644 index 0000000000..ff49025ec0 --- /dev/null +++ b/drivers/platform/x86/intel/speed_select_if/isst_if_mmio.c @@ -0,0 +1,200 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Intel Speed Select Interface: MMIO Interface + * Copyright (c) 2019, Intel Corporation. + * All rights reserved. + * + * Author: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com> + */ + +#include <linux/module.h> +#include <linux/pci.h> +#include <linux/sched/signal.h> +#include <linux/uaccess.h> +#include <uapi/linux/isst_if.h> + +#include "isst_if_common.h" + +struct isst_mmio_range { + int beg; + int end; +}; + +static struct isst_mmio_range mmio_range_devid_0[] = { + {0x04, 0x14}, + {0x20, 0xD0}, +}; + +static struct isst_mmio_range mmio_range_devid_1[] = { + {0x04, 0x14}, + {0x20, 0x11C}, +}; + +struct isst_if_device { + void __iomem *punit_mmio; + u32 range_0[5]; + u32 range_1[64]; + struct isst_mmio_range *mmio_range; + struct mutex mutex; +}; + +static long isst_if_mmio_rd_wr(u8 *cmd_ptr, int *write_only, int resume) +{ + struct isst_if_device *punit_dev; + struct isst_if_io_reg *io_reg; + struct pci_dev *pdev; + + io_reg = (struct isst_if_io_reg *)cmd_ptr; + + if (io_reg->reg % 4) + return -EINVAL; + + if (io_reg->read_write && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + pdev = isst_if_get_pci_dev(io_reg->logical_cpu, 0, 0, 1); + if (!pdev) + return -EINVAL; + + punit_dev = pci_get_drvdata(pdev); + if (!punit_dev) + return -EINVAL; + + if (io_reg->reg < punit_dev->mmio_range[0].beg || + io_reg->reg > punit_dev->mmio_range[1].end) + return -EINVAL; + + /* + * Ensure that operation is complete on a PCI device to avoid read + * write race by using per PCI device mutex. + */ + mutex_lock(&punit_dev->mutex); + if (io_reg->read_write) { + writel(io_reg->value, punit_dev->punit_mmio+io_reg->reg); + *write_only = 1; + } else { + io_reg->value = readl(punit_dev->punit_mmio+io_reg->reg); + *write_only = 0; + } + mutex_unlock(&punit_dev->mutex); + + return 0; +} + +static const struct pci_device_id isst_if_ids[] = { + { PCI_DEVICE_DATA(INTEL, RAPL_PRIO_DEVID_0, &mmio_range_devid_0)}, + { PCI_DEVICE_DATA(INTEL, RAPL_PRIO_DEVID_1, &mmio_range_devid_1)}, + { 0 }, +}; +MODULE_DEVICE_TABLE(pci, isst_if_ids); + +static int isst_if_probe(struct pci_dev *pdev, const struct pci_device_id *ent) +{ + struct isst_if_device *punit_dev; + struct isst_if_cmd_cb cb; + u32 mmio_base, pcu_base; + u64 base_addr; + int ret; + + punit_dev = devm_kzalloc(&pdev->dev, sizeof(*punit_dev), GFP_KERNEL); + if (!punit_dev) + return -ENOMEM; + + ret = pcim_enable_device(pdev); + if (ret) + return ret; + + ret = pci_read_config_dword(pdev, 0xD0, &mmio_base); + if (ret) + return ret; + + ret = pci_read_config_dword(pdev, 0xFC, &pcu_base); + if (ret) + return ret; + + pcu_base &= GENMASK(10, 0); + base_addr = (u64)mmio_base << 23 | (u64) pcu_base << 12; + punit_dev->punit_mmio = devm_ioremap(&pdev->dev, base_addr, 256); + if (!punit_dev->punit_mmio) + return -ENOMEM; + + mutex_init(&punit_dev->mutex); + pci_set_drvdata(pdev, punit_dev); + punit_dev->mmio_range = (struct isst_mmio_range *) ent->driver_data; + + memset(&cb, 0, sizeof(cb)); + cb.cmd_size = sizeof(struct isst_if_io_reg); + cb.offset = offsetof(struct isst_if_io_regs, io_reg); + cb.cmd_callback = isst_if_mmio_rd_wr; + cb.owner = THIS_MODULE; + ret = isst_if_cdev_register(ISST_IF_DEV_MMIO, &cb); + if (ret) + mutex_destroy(&punit_dev->mutex); + + return ret; +} + +static void isst_if_remove(struct pci_dev *pdev) +{ + struct isst_if_device *punit_dev; + + punit_dev = pci_get_drvdata(pdev); + isst_if_cdev_unregister(ISST_IF_DEV_MMIO); + mutex_destroy(&punit_dev->mutex); +} + +static int __maybe_unused isst_if_suspend(struct device *device) +{ + struct isst_if_device *punit_dev = dev_get_drvdata(device); + int i; + + for (i = 0; i < ARRAY_SIZE(punit_dev->range_0); ++i) + punit_dev->range_0[i] = readl(punit_dev->punit_mmio + + punit_dev->mmio_range[0].beg + 4 * i); + for (i = 0; i < ARRAY_SIZE(punit_dev->range_1); ++i) { + u32 addr; + + addr = punit_dev->mmio_range[1].beg + 4 * i; + if (addr > punit_dev->mmio_range[1].end) + break; + punit_dev->range_1[i] = readl(punit_dev->punit_mmio + addr); + } + + return 0; +} + +static int __maybe_unused isst_if_resume(struct device *device) +{ + struct isst_if_device *punit_dev = dev_get_drvdata(device); + int i; + + for (i = 0; i < ARRAY_SIZE(punit_dev->range_0); ++i) + writel(punit_dev->range_0[i], punit_dev->punit_mmio + + punit_dev->mmio_range[0].beg + 4 * i); + for (i = 0; i < ARRAY_SIZE(punit_dev->range_1); ++i) { + u32 addr; + + addr = punit_dev->mmio_range[1].beg + 4 * i; + if (addr > punit_dev->mmio_range[1].end) + break; + + writel(punit_dev->range_1[i], punit_dev->punit_mmio + addr); + } + + return 0; +} + +static SIMPLE_DEV_PM_OPS(isst_if_pm_ops, isst_if_suspend, isst_if_resume); + +static struct pci_driver isst_if_pci_driver = { + .name = "isst_if_pci", + .id_table = isst_if_ids, + .probe = isst_if_probe, + .remove = isst_if_remove, + .driver.pm = &isst_if_pm_ops, +}; + +module_pci_driver(isst_if_pci_driver); + +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("Intel speed select interface mmio driver"); diff --git a/drivers/platform/x86/intel/speed_select_if/isst_tpmi.c b/drivers/platform/x86/intel/speed_select_if/isst_tpmi.c new file mode 100644 index 0000000000..1797219153 --- /dev/null +++ b/drivers/platform/x86/intel/speed_select_if/isst_tpmi.c @@ -0,0 +1,72 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * isst_tpmi.c: SST TPMI interface + * + * Copyright (c) 2023, Intel Corporation. + * All Rights Reserved. + * + */ + +#include <linux/auxiliary_bus.h> +#include <linux/module.h> +#include <linux/intel_tpmi.h> + +#include "isst_tpmi_core.h" + +static int intel_sst_probe(struct auxiliary_device *auxdev, const struct auxiliary_device_id *id) +{ + int ret; + + ret = tpmi_sst_init(); + if (ret) + return ret; + + ret = tpmi_sst_dev_add(auxdev); + if (ret) + tpmi_sst_exit(); + + return ret; +} + +static void intel_sst_remove(struct auxiliary_device *auxdev) +{ + tpmi_sst_dev_remove(auxdev); + tpmi_sst_exit(); +} + +static int intel_sst_suspend(struct device *dev) +{ + tpmi_sst_dev_suspend(to_auxiliary_dev(dev)); + + return 0; +} + +static int intel_sst_resume(struct device *dev) +{ + tpmi_sst_dev_resume(to_auxiliary_dev(dev)); + + return 0; +} + +static DEFINE_SIMPLE_DEV_PM_OPS(intel_sst_pm, intel_sst_suspend, intel_sst_resume); + +static const struct auxiliary_device_id intel_sst_id_table[] = { + { .name = "intel_vsec.tpmi-sst" }, + {} +}; +MODULE_DEVICE_TABLE(auxiliary, intel_sst_id_table); + +static struct auxiliary_driver intel_sst_aux_driver = { + .id_table = intel_sst_id_table, + .remove = intel_sst_remove, + .probe = intel_sst_probe, + .driver = { + .pm = pm_sleep_ptr(&intel_sst_pm), + }, +}; + +module_auxiliary_driver(intel_sst_aux_driver); + +MODULE_IMPORT_NS(INTEL_TPMI_SST); +MODULE_DESCRIPTION("Intel TPMI SST Driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c b/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c new file mode 100644 index 0000000000..63faa2ea83 --- /dev/null +++ b/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c @@ -0,0 +1,1442 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * isst_tpmi.c: SST TPMI interface core + * + * Copyright (c) 2023, Intel Corporation. + * All Rights Reserved. + * + * This information will be useful to understand flows: + * In the current generation of platforms, TPMI is supported via OOB + * PCI device. This PCI device has one instance per CPU package. + * There is a unique TPMI ID for SST. Each TPMI ID also has multiple + * entries, representing per power domain information. + * + * There is one dev file for complete SST information and control same as the + * prior generation of hardware. User spaces don't need to know how the + * information is presented by the hardware. The TPMI core module implements + * the hardware mapping. + */ + +#include <linux/auxiliary_bus.h> +#include <linux/delay.h> +#include <linux/intel_tpmi.h> +#include <linux/fs.h> +#include <linux/io.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <uapi/linux/isst_if.h> + +#include "isst_tpmi_core.h" +#include "isst_if_common.h" + +/* Supported SST hardware version by this driver */ +#define ISST_HEADER_VERSION 1 + +/* + * Used to indicate if value read from MMIO needs to get multiplied + * to get to a standard unit or not. + */ +#define SST_MUL_FACTOR_NONE 1 + +/* Define 100 as a scaling factor frequency ratio to frequency conversion */ +#define SST_MUL_FACTOR_FREQ 100 + +/* All SST regs are 64 bit size */ +#define SST_REG_SIZE 8 + +/** + * struct sst_header - SST main header + * @interface_version: Version number for this interface + * @cap_mask: Bitmask of the supported sub features. 1=the sub feature is enabled. + * 0=disabled. + * Bit[8]= SST_CP enable (1), disable (0) + * bit[9]= SST_PP enable (1), disable (0) + * other bits are reserved for future use + * @cp_offset: Qword (8 bytes) offset to the SST_CP register bank + * @pp_offset: Qword (8 bytes) offset to the SST_PP register bank + * @reserved: Reserved for future use + * + * This register allows SW to discover SST capability and the offsets to SST-CP + * and SST-PP register banks. + */ +struct sst_header { + u8 interface_version; + u8 cap_mask; + u8 cp_offset; + u8 pp_offset; + u32 reserved; +} __packed; + +/** + * struct cp_header - SST-CP (core-power) header + * @feature_id: 0=SST-CP, 1=SST-PP, 2=SST-BF, 3=SST-TF + * @feature_rev: Interface Version number for this SST feature + * @ratio_unit: Frequency ratio unit. 00: 100MHz. All others are reserved + * @reserved: Reserved for future use + * + * This structure is used store SST-CP header. This is packed to the same + * format as defined in the specifications. + */ +struct cp_header { + u64 feature_id :4; + u64 feature_rev :8; + u64 ratio_unit :2; + u64 reserved :50; +} __packed; + +/** + * struct pp_header - SST-PP (Perf profile) header + * @feature_id: 0=SST-CP, 1=SST-PP, 2=SST-BF, 3=SST-TF + * @feature_rev: Interface Version number for this SST feature + * @level_en_mask: SST-PP level enable/disable fuse mask + * @allowed_level_mask: Allowed level mask used for dynamic config level switching + * @reserved0: Reserved for future use + * @ratio_unit: Frequency ratio unit. 00: 100MHz. All others are reserved + * @block_size: Size of PP block in Qword unit (8 bytes) + * @dynamic_switch: If set (1), dynamic switching of SST PP is supported + * @memory_ratio_unit: Memory Controller frequency ratio unit. 00: 100MHz, others reserved + * @reserved1: Reserved for future use + * + * This structure is used store SST-PP header. This is packed to the same + * format as defined in the specifications. + */ +struct pp_header { + u64 feature_id :4; + u64 feature_rev :8; + u64 level_en_mask :8; + u64 allowed_level_mask :8; + u64 reserved0 :4; + u64 ratio_unit :2; + u64 block_size :8; + u64 dynamic_switch :1; + u64 memory_ratio_unit :2; + u64 reserved1 :19; +} __packed; + +/** + * struct feature_offset - Offsets to SST-PP features + * @pp_offset: Qword offset within PP level for the SST_PP register bank + * @bf_offset: Qword offset within PP level for the SST_BF register bank + * @tf_offset: Qword offset within PP level for the SST_TF register bank + * @reserved: Reserved for future use + * + * This structure is used store offsets for SST features in the register bank. + * This is packed to the same format as defined in the specifications. + */ +struct feature_offset { + u64 pp_offset :8; + u64 bf_offset :8; + u64 tf_offset :8; + u64 reserved :40; +} __packed; + +/** + * struct levels_offset - Offsets to each SST PP level + * @sst_pp_level0_offset: Qword offset to the register block of PP level 0 + * @sst_pp_level1_offset: Qword offset to the register block of PP level 1 + * @sst_pp_level2_offset: Qword offset to the register block of PP level 2 + * @sst_pp_level3_offset: Qword offset to the register block of PP level 3 + * @sst_pp_level4_offset: Qword offset to the register block of PP level 4 + * @reserved: Reserved for future use + * + * This structure is used store offsets of SST PP levels in the register bank. + * This is packed to the same format as defined in the specifications. + */ +struct levels_offset { + u64 sst_pp_level0_offset :8; + u64 sst_pp_level1_offset :8; + u64 sst_pp_level2_offset :8; + u64 sst_pp_level3_offset :8; + u64 sst_pp_level4_offset :8; + u64 reserved :24; +} __packed; + +/** + * struct pp_control_offset - Offsets for SST PP controls + * @perf_level: A SST-PP level that SW intends to switch to + * @perf_level_lock: SST-PP level select lock. 0 - unlocked. 1 - locked till next reset + * @resvd0: Reserved for future use + * @current_state: Bit mask to control the enable(1)/disable(0) state of each feature + * of the current PP level, bit 0 = BF, bit 1 = TF, bit 2-7 = reserved + * @reserved: Reserved for future use + * + * This structure is used store offsets of SST PP controls in the register bank. + * This is packed to the same format as defined in the specifications. + */ +struct pp_control_offset { + u64 perf_level :3; + u64 perf_level_lock :1; + u64 resvd0 :4; + u64 current_state :8; + u64 reserved :48; +} __packed; + +/** + * struct pp_status_offset - Offsets for SST PP status fields + * @sst_pp_level: Returns the current SST-PP level + * @sst_pp_lock: Returns the lock bit setting of perf_level_lock in pp_control_offset + * @error_type: Returns last error of SST-PP level change request. 0: no error, + * 1: level change not allowed, others: reserved + * @feature_state: Bit mask to indicate the enable(1)/disable(0) state of each feature of the + * current PP level. bit 0 = BF, bit 1 = TF, bit 2-7 reserved + * @reserved0: Reserved for future use + * @feature_error_type: Returns last error of the specific feature. Three error_type bits per + * feature. i.e. ERROR_TYPE[2:0] for BF, ERROR_TYPE[5:3] for TF, etc. + * 0x0: no error, 0x1: The specific feature is not supported by the hardware. + * 0x2-0x6: Reserved. 0x7: feature state change is not allowed. + * @reserved1: Reserved for future use + * + * This structure is used store offsets of SST PP status in the register bank. + * This is packed to the same format as defined in the specifications. + */ +struct pp_status_offset { + u64 sst_pp_level :3; + u64 sst_pp_lock :1; + u64 error_type :4; + u64 feature_state :8; + u64 reserved0 :16; + u64 feature_error_type : 24; + u64 reserved1 :8; +} __packed; + +/** + * struct perf_level - Used to store perf level and mmio offset + * @mmio_offset: mmio offset for a perf level + * @level: perf level for this offset + * + * This structure is used store final mmio offset of each perf level from the + * SST base mmio offset. + */ +struct perf_level { + int mmio_offset; + int level; +}; + +/** + * struct tpmi_per_power_domain_info - Store per power_domain SST info + * @package_id: Package id for this power_domain + * @power_domain_id: Power domain id, Each entry from the SST-TPMI instance is a power_domain. + * @max_level: Max possible PP level possible for this power_domain + * @ratio_unit: Ratio unit for converting to MHz + * @avx_levels: Number of AVX levels + * @pp_block_size: Block size from PP header + * @sst_header: Store SST header for this power_domain + * @cp_header: Store SST-CP header for this power_domain + * @pp_header: Store SST-PP header for this power_domain + * @perf_levels: Pointer to each perf level to map level to mmio offset + * @feature_offsets: Store feature offsets for each PP-level + * @control_offset: Store the control offset for each PP-level + * @status_offset: Store the status offset for each PP-level + * @sst_base: Mapped SST base IO memory + * @auxdev: Auxiliary device instance enumerated this instance + * @saved_sst_cp_control: Save SST-CP control configuration to store restore for suspend/resume + * @saved_clos_configs: Save SST-CP CLOS configuration to store restore for suspend/resume + * @saved_clos_assocs: Save SST-CP CLOS association to store restore for suspend/resume + * @saved_pp_control: Save SST-PP control information to store restore for suspend/resume + * + * This structure is used store complete SST information for a power_domain. This information + * is used to read/write request for any SST IOCTL. Each physical CPU package can have multiple + * power_domains. Each power domain describes its own SST information and has its own controls. + */ +struct tpmi_per_power_domain_info { + int package_id; + int power_domain_id; + int max_level; + int ratio_unit; + int avx_levels; + int pp_block_size; + struct sst_header sst_header; + struct cp_header cp_header; + struct pp_header pp_header; + struct perf_level *perf_levels; + struct feature_offset feature_offsets; + struct pp_control_offset control_offset; + struct pp_status_offset status_offset; + void __iomem *sst_base; + struct auxiliary_device *auxdev; + u64 saved_sst_cp_control; + u64 saved_clos_configs[4]; + u64 saved_clos_assocs[4]; + u64 saved_pp_control; +}; + +/** + * struct tpmi_sst_struct - Store sst info for a package + * @package_id: Package id for this aux device instance + * @number_of_power_domains: Number of power_domains pointed by power_domain_info pointer + * @power_domain_info: Pointer to power domains information + * + * This structure is used store full SST information for a package. + * Each package has a unique OOB PCI device, which enumerates TPMI. + * Each Package will have multiple power_domains. + */ +struct tpmi_sst_struct { + int package_id; + int number_of_power_domains; + struct tpmi_per_power_domain_info *power_domain_info; +}; + +/** + * struct tpmi_sst_common_struct - Store all SST instances + * @max_index: Maximum instances currently present + * @sst_inst: Pointer to per package instance + * + * Stores every SST Package instance. + */ +struct tpmi_sst_common_struct { + int max_index; + struct tpmi_sst_struct **sst_inst; +}; + +/* + * Each IOCTL request is processed under this lock. Also used to protect + * registration functions and common data structures. + */ +static DEFINE_MUTEX(isst_tpmi_dev_lock); + +/* Usage count to track, number of TPMI SST instances registered to this core. */ +static int isst_core_usage_count; + +/* Stores complete SST information for every package and power_domain */ +static struct tpmi_sst_common_struct isst_common; + +#define SST_MAX_AVX_LEVELS 3 + +#define SST_PP_OFFSET_0 8 +#define SST_PP_OFFSET_1 16 +#define SST_PP_OFFSET_SIZE 8 + +static int sst_add_perf_profiles(struct auxiliary_device *auxdev, + struct tpmi_per_power_domain_info *pd_info, + int levels) +{ + u64 perf_level_offsets; + int i; + + pd_info->perf_levels = devm_kcalloc(&auxdev->dev, levels, + sizeof(struct perf_level), + GFP_KERNEL); + if (!pd_info->perf_levels) + return 0; + + pd_info->ratio_unit = pd_info->pp_header.ratio_unit; + pd_info->avx_levels = SST_MAX_AVX_LEVELS; + pd_info->pp_block_size = pd_info->pp_header.block_size; + + /* Read PP Offset 0: Get feature offset with PP level */ + *((u64 *)&pd_info->feature_offsets) = readq(pd_info->sst_base + + pd_info->sst_header.pp_offset + + SST_PP_OFFSET_0); + + perf_level_offsets = readq(pd_info->sst_base + pd_info->sst_header.pp_offset + + SST_PP_OFFSET_1); + + for (i = 0; i < levels; ++i) { + u64 offset; + + offset = perf_level_offsets & (0xffULL << (i * SST_PP_OFFSET_SIZE)); + offset >>= (i * 8); + offset &= 0xff; + offset *= 8; /* Convert to byte from QWORD offset */ + pd_info->perf_levels[i].mmio_offset = pd_info->sst_header.pp_offset + offset; + } + + return 0; +} + +static int sst_main(struct auxiliary_device *auxdev, struct tpmi_per_power_domain_info *pd_info) +{ + int i, mask, levels; + + *((u64 *)&pd_info->sst_header) = readq(pd_info->sst_base); + pd_info->sst_header.cp_offset *= 8; + pd_info->sst_header.pp_offset *= 8; + + if (pd_info->sst_header.interface_version != ISST_HEADER_VERSION) { + dev_err(&auxdev->dev, "SST: Unsupported version:%x\n", + pd_info->sst_header.interface_version); + return -ENODEV; + } + + /* Read SST CP Header */ + *((u64 *)&pd_info->cp_header) = readq(pd_info->sst_base + pd_info->sst_header.cp_offset); + + /* Read PP header */ + *((u64 *)&pd_info->pp_header) = readq(pd_info->sst_base + pd_info->sst_header.pp_offset); + + /* Force level_en_mask level 0 */ + pd_info->pp_header.level_en_mask |= 0x01; + + mask = 0x01; + levels = 0; + for (i = 0; i < 8; ++i) { + if (pd_info->pp_header.level_en_mask & mask) + levels = i; + mask <<= 1; + } + pd_info->max_level = levels; + sst_add_perf_profiles(auxdev, pd_info, levels + 1); + + return 0; +} + +/* + * Map a package and power_domain id to SST information structure unique for a power_domain. + * The caller should call under isst_tpmi_dev_lock. + */ +static struct tpmi_per_power_domain_info *get_instance(int pkg_id, int power_domain_id) +{ + struct tpmi_per_power_domain_info *power_domain_info; + struct tpmi_sst_struct *sst_inst; + + if (pkg_id < 0 || pkg_id > isst_common.max_index || + pkg_id >= topology_max_packages()) + return NULL; + + sst_inst = isst_common.sst_inst[pkg_id]; + if (!sst_inst) + return NULL; + + if (power_domain_id < 0 || power_domain_id >= sst_inst->number_of_power_domains) + return NULL; + + power_domain_info = &sst_inst->power_domain_info[power_domain_id]; + + if (power_domain_info && !power_domain_info->sst_base) + return NULL; + + return power_domain_info; +} + +static bool disable_dynamic_sst_features(void) +{ + u64 value; + + rdmsrl(MSR_PM_ENABLE, value); + return !(value & 0x1); +} + +#define _read_cp_info(name_str, name, offset, start, width, mult_factor)\ +{\ + u64 val, mask;\ + \ + val = readq(power_domain_info->sst_base + power_domain_info->sst_header.cp_offset +\ + (offset));\ + mask = GENMASK_ULL((start + width - 1), start);\ + val &= mask; \ + val >>= start;\ + name = (val * mult_factor);\ +} + +#define _write_cp_info(name_str, name, offset, start, width, div_factor)\ +{\ + u64 val, mask;\ + \ + val = readq(power_domain_info->sst_base +\ + power_domain_info->sst_header.cp_offset + (offset));\ + mask = GENMASK_ULL((start + width - 1), start);\ + val &= ~mask;\ + val |= (name / div_factor) << start;\ + writeq(val, power_domain_info->sst_base + power_domain_info->sst_header.cp_offset +\ + (offset));\ +} + +#define SST_CP_CONTROL_OFFSET 8 +#define SST_CP_STATUS_OFFSET 16 + +#define SST_CP_ENABLE_START 0 +#define SST_CP_ENABLE_WIDTH 1 + +#define SST_CP_PRIORITY_TYPE_START 1 +#define SST_CP_PRIORITY_TYPE_WIDTH 1 + +static long isst_if_core_power_state(void __user *argp) +{ + struct tpmi_per_power_domain_info *power_domain_info; + struct isst_core_power core_power; + + if (disable_dynamic_sst_features()) + return -EFAULT; + + if (copy_from_user(&core_power, argp, sizeof(core_power))) + return -EFAULT; + + power_domain_info = get_instance(core_power.socket_id, core_power.power_domain_id); + if (!power_domain_info) + return -EINVAL; + + if (core_power.get_set) { + _write_cp_info("cp_enable", core_power.enable, SST_CP_CONTROL_OFFSET, + SST_CP_ENABLE_START, SST_CP_ENABLE_WIDTH, SST_MUL_FACTOR_NONE) + _write_cp_info("cp_prio_type", core_power.priority_type, SST_CP_CONTROL_OFFSET, + SST_CP_PRIORITY_TYPE_START, SST_CP_PRIORITY_TYPE_WIDTH, + SST_MUL_FACTOR_NONE) + } else { + /* get */ + _read_cp_info("cp_enable", core_power.enable, SST_CP_STATUS_OFFSET, + SST_CP_ENABLE_START, SST_CP_ENABLE_WIDTH, SST_MUL_FACTOR_NONE) + _read_cp_info("cp_prio_type", core_power.priority_type, SST_CP_STATUS_OFFSET, + SST_CP_PRIORITY_TYPE_START, SST_CP_PRIORITY_TYPE_WIDTH, + SST_MUL_FACTOR_NONE) + core_power.supported = !!(power_domain_info->sst_header.cap_mask & BIT(0)); + if (copy_to_user(argp, &core_power, sizeof(core_power))) + return -EFAULT; + } + + return 0; +} + +#define SST_CLOS_CONFIG_0_OFFSET 24 + +#define SST_CLOS_CONFIG_PRIO_START 4 +#define SST_CLOS_CONFIG_PRIO_WIDTH 4 + +#define SST_CLOS_CONFIG_MIN_START 8 +#define SST_CLOS_CONFIG_MIN_WIDTH 8 + +#define SST_CLOS_CONFIG_MAX_START 16 +#define SST_CLOS_CONFIG_MAX_WIDTH 8 + +static long isst_if_clos_param(void __user *argp) +{ + struct tpmi_per_power_domain_info *power_domain_info; + struct isst_clos_param clos_param; + + if (copy_from_user(&clos_param, argp, sizeof(clos_param))) + return -EFAULT; + + power_domain_info = get_instance(clos_param.socket_id, clos_param.power_domain_id); + if (!power_domain_info) + return -EINVAL; + + if (clos_param.get_set) { + _write_cp_info("clos.min_freq", clos_param.min_freq_mhz, + (SST_CLOS_CONFIG_0_OFFSET + clos_param.clos * SST_REG_SIZE), + SST_CLOS_CONFIG_MIN_START, SST_CLOS_CONFIG_MIN_WIDTH, + SST_MUL_FACTOR_FREQ); + _write_cp_info("clos.max_freq", clos_param.max_freq_mhz, + (SST_CLOS_CONFIG_0_OFFSET + clos_param.clos * SST_REG_SIZE), + SST_CLOS_CONFIG_MAX_START, SST_CLOS_CONFIG_MAX_WIDTH, + SST_MUL_FACTOR_FREQ); + _write_cp_info("clos.prio", clos_param.prop_prio, + (SST_CLOS_CONFIG_0_OFFSET + clos_param.clos * SST_REG_SIZE), + SST_CLOS_CONFIG_PRIO_START, SST_CLOS_CONFIG_PRIO_WIDTH, + SST_MUL_FACTOR_NONE); + } else { + /* get */ + _read_cp_info("clos.min_freq", clos_param.min_freq_mhz, + (SST_CLOS_CONFIG_0_OFFSET + clos_param.clos * SST_REG_SIZE), + SST_CLOS_CONFIG_MIN_START, SST_CLOS_CONFIG_MIN_WIDTH, + SST_MUL_FACTOR_FREQ) + _read_cp_info("clos.max_freq", clos_param.max_freq_mhz, + (SST_CLOS_CONFIG_0_OFFSET + clos_param.clos * SST_REG_SIZE), + SST_CLOS_CONFIG_MAX_START, SST_CLOS_CONFIG_MAX_WIDTH, + SST_MUL_FACTOR_FREQ) + _read_cp_info("clos.prio", clos_param.prop_prio, + (SST_CLOS_CONFIG_0_OFFSET + clos_param.clos * SST_REG_SIZE), + SST_CLOS_CONFIG_PRIO_START, SST_CLOS_CONFIG_PRIO_WIDTH, + SST_MUL_FACTOR_NONE) + + if (copy_to_user(argp, &clos_param, sizeof(clos_param))) + return -EFAULT; + } + + return 0; +} + +#define SST_CLOS_ASSOC_0_OFFSET 56 +#define SST_CLOS_ASSOC_CPUS_PER_REG 16 +#define SST_CLOS_ASSOC_BITS_PER_CPU 4 + +static long isst_if_clos_assoc(void __user *argp) +{ + struct isst_if_clos_assoc_cmds assoc_cmds; + unsigned char __user *ptr; + int i; + + /* Each multi command has u16 command count as the first field */ + if (copy_from_user(&assoc_cmds, argp, sizeof(assoc_cmds))) + return -EFAULT; + + if (!assoc_cmds.cmd_count || assoc_cmds.cmd_count > ISST_IF_CMD_LIMIT) + return -EINVAL; + + ptr = argp + offsetof(struct isst_if_clos_assoc_cmds, assoc_info); + for (i = 0; i < assoc_cmds.cmd_count; ++i) { + struct tpmi_per_power_domain_info *power_domain_info; + struct isst_if_clos_assoc clos_assoc; + int punit_id, punit_cpu_no, pkg_id; + struct tpmi_sst_struct *sst_inst; + int offset, shift, cpu; + u64 val, mask, clos; + + if (copy_from_user(&clos_assoc, ptr, sizeof(clos_assoc))) + return -EFAULT; + + if (clos_assoc.socket_id > topology_max_packages()) + return -EINVAL; + + cpu = clos_assoc.logical_cpu; + clos = clos_assoc.clos; + + if (assoc_cmds.punit_cpu_map) + punit_cpu_no = cpu; + else + return -EOPNOTSUPP; + + if (punit_cpu_no < 0) + return -EINVAL; + + punit_id = clos_assoc.power_domain_id; + pkg_id = clos_assoc.socket_id; + + sst_inst = isst_common.sst_inst[pkg_id]; + + if (clos_assoc.power_domain_id > sst_inst->number_of_power_domains) + return -EINVAL; + + power_domain_info = &sst_inst->power_domain_info[punit_id]; + + offset = SST_CLOS_ASSOC_0_OFFSET + + (punit_cpu_no / SST_CLOS_ASSOC_CPUS_PER_REG) * SST_REG_SIZE; + shift = punit_cpu_no % SST_CLOS_ASSOC_CPUS_PER_REG; + shift *= SST_CLOS_ASSOC_BITS_PER_CPU; + + val = readq(power_domain_info->sst_base + + power_domain_info->sst_header.cp_offset + offset); + if (assoc_cmds.get_set) { + mask = GENMASK_ULL((shift + SST_CLOS_ASSOC_BITS_PER_CPU - 1), shift); + val &= ~mask; + val |= (clos << shift); + writeq(val, power_domain_info->sst_base + + power_domain_info->sst_header.cp_offset + offset); + } else { + val >>= shift; + clos_assoc.clos = val & GENMASK(SST_CLOS_ASSOC_BITS_PER_CPU - 1, 0); + if (copy_to_user(ptr, &clos_assoc, sizeof(clos_assoc))) + return -EFAULT; + } + + ptr += sizeof(clos_assoc); + } + + return 0; +} + +#define _read_pp_info(name_str, name, offset, start, width, mult_factor)\ +{\ + u64 val, _mask;\ + \ + val = readq(power_domain_info->sst_base + power_domain_info->sst_header.pp_offset +\ + (offset));\ + _mask = GENMASK_ULL((start + width - 1), start);\ + val &= _mask;\ + val >>= start;\ + name = (val * mult_factor);\ +} + +#define _write_pp_info(name_str, name, offset, start, width, div_factor)\ +{\ + u64 val, _mask;\ + \ + val = readq(power_domain_info->sst_base + power_domain_info->sst_header.pp_offset +\ + (offset));\ + _mask = GENMASK((start + width - 1), start);\ + val &= ~_mask;\ + val |= (name / div_factor) << start;\ + writeq(val, power_domain_info->sst_base + power_domain_info->sst_header.pp_offset +\ + (offset));\ +} + +#define _read_bf_level_info(name_str, name, level, offset, start, width, mult_factor)\ +{\ + u64 val, _mask;\ + \ + val = readq(power_domain_info->sst_base +\ + power_domain_info->perf_levels[level].mmio_offset +\ + (power_domain_info->feature_offsets.bf_offset * 8) + (offset));\ + _mask = GENMASK_ULL((start + width - 1), start);\ + val &= _mask; \ + val >>= start;\ + name = (val * mult_factor);\ +} + +#define _read_tf_level_info(name_str, name, level, offset, start, width, mult_factor)\ +{\ + u64 val, _mask;\ + \ + val = readq(power_domain_info->sst_base +\ + power_domain_info->perf_levels[level].mmio_offset +\ + (power_domain_info->feature_offsets.tf_offset * 8) + (offset));\ + _mask = GENMASK_ULL((start + width - 1), start);\ + val &= _mask; \ + val >>= start;\ + name = (val * mult_factor);\ +} + +#define SST_PP_STATUS_OFFSET 32 + +#define SST_PP_LEVEL_START 0 +#define SST_PP_LEVEL_WIDTH 3 + +#define SST_PP_LOCK_START 3 +#define SST_PP_LOCK_WIDTH 1 + +#define SST_PP_FEATURE_STATE_START 8 +#define SST_PP_FEATURE_STATE_WIDTH 8 + +#define SST_BF_FEATURE_SUPPORTED_START 12 +#define SST_BF_FEATURE_SUPPORTED_WIDTH 1 + +#define SST_TF_FEATURE_SUPPORTED_START 12 +#define SST_TF_FEATURE_SUPPORTED_WIDTH 1 + +static int isst_if_get_perf_level(void __user *argp) +{ + struct isst_perf_level_info perf_level; + struct tpmi_per_power_domain_info *power_domain_info; + + if (copy_from_user(&perf_level, argp, sizeof(perf_level))) + return -EFAULT; + + power_domain_info = get_instance(perf_level.socket_id, perf_level.power_domain_id); + if (!power_domain_info) + return -EINVAL; + + perf_level.max_level = power_domain_info->max_level; + perf_level.level_mask = power_domain_info->pp_header.allowed_level_mask; + perf_level.feature_rev = power_domain_info->pp_header.feature_rev; + _read_pp_info("current_level", perf_level.current_level, SST_PP_STATUS_OFFSET, + SST_PP_LEVEL_START, SST_PP_LEVEL_WIDTH, SST_MUL_FACTOR_NONE) + _read_pp_info("locked", perf_level.locked, SST_PP_STATUS_OFFSET, + SST_PP_LOCK_START, SST_PP_LEVEL_WIDTH, SST_MUL_FACTOR_NONE) + _read_pp_info("feature_state", perf_level.feature_state, SST_PP_STATUS_OFFSET, + SST_PP_FEATURE_STATE_START, SST_PP_FEATURE_STATE_WIDTH, SST_MUL_FACTOR_NONE) + perf_level.enabled = !!(power_domain_info->sst_header.cap_mask & BIT(1)); + + _read_bf_level_info("bf_support", perf_level.sst_bf_support, 0, 0, + SST_BF_FEATURE_SUPPORTED_START, SST_BF_FEATURE_SUPPORTED_WIDTH, + SST_MUL_FACTOR_NONE); + _read_tf_level_info("tf_support", perf_level.sst_tf_support, 0, 0, + SST_TF_FEATURE_SUPPORTED_START, SST_TF_FEATURE_SUPPORTED_WIDTH, + SST_MUL_FACTOR_NONE); + + if (copy_to_user(argp, &perf_level, sizeof(perf_level))) + return -EFAULT; + + return 0; +} + +#define SST_PP_CONTROL_OFFSET 24 +#define SST_PP_LEVEL_CHANGE_TIME_MS 5 +#define SST_PP_LEVEL_CHANGE_RETRY_COUNT 3 + +static int isst_if_set_perf_level(void __user *argp) +{ + struct isst_perf_level_control perf_level; + struct tpmi_per_power_domain_info *power_domain_info; + int level, retry = 0; + + if (disable_dynamic_sst_features()) + return -EFAULT; + + if (copy_from_user(&perf_level, argp, sizeof(perf_level))) + return -EFAULT; + + power_domain_info = get_instance(perf_level.socket_id, perf_level.power_domain_id); + if (!power_domain_info) + return -EINVAL; + + if (!(power_domain_info->pp_header.allowed_level_mask & BIT(perf_level.level))) + return -EINVAL; + + _read_pp_info("current_level", level, SST_PP_STATUS_OFFSET, + SST_PP_LEVEL_START, SST_PP_LEVEL_WIDTH, SST_MUL_FACTOR_NONE) + + /* If the requested new level is same as the current level, reject */ + if (perf_level.level == level) + return -EINVAL; + + _write_pp_info("perf_level", perf_level.level, SST_PP_CONTROL_OFFSET, + SST_PP_LEVEL_START, SST_PP_LEVEL_WIDTH, SST_MUL_FACTOR_NONE) + + /* It is possible that firmware is busy (although unlikely), so retry */ + do { + /* Give time to FW to process */ + msleep(SST_PP_LEVEL_CHANGE_TIME_MS); + + _read_pp_info("current_level", level, SST_PP_STATUS_OFFSET, + SST_PP_LEVEL_START, SST_PP_LEVEL_WIDTH, SST_MUL_FACTOR_NONE) + + /* Check if the new level is active */ + if (perf_level.level == level) + break; + + } while (retry++ < SST_PP_LEVEL_CHANGE_RETRY_COUNT); + + /* If the level change didn't happen, return fault */ + if (perf_level.level != level) + return -EFAULT; + + /* Reset the feature state on level change */ + _write_pp_info("perf_feature", 0, SST_PP_CONTROL_OFFSET, + SST_PP_FEATURE_STATE_START, SST_PP_FEATURE_STATE_WIDTH, + SST_MUL_FACTOR_NONE) + + /* Give time to FW to process */ + msleep(SST_PP_LEVEL_CHANGE_TIME_MS); + + return 0; +} + +static int isst_if_set_perf_feature(void __user *argp) +{ + struct isst_perf_feature_control perf_feature; + struct tpmi_per_power_domain_info *power_domain_info; + + if (disable_dynamic_sst_features()) + return -EFAULT; + + if (copy_from_user(&perf_feature, argp, sizeof(perf_feature))) + return -EFAULT; + + power_domain_info = get_instance(perf_feature.socket_id, perf_feature.power_domain_id); + if (!power_domain_info) + return -EINVAL; + + _write_pp_info("perf_feature", perf_feature.feature, SST_PP_CONTROL_OFFSET, + SST_PP_FEATURE_STATE_START, SST_PP_FEATURE_STATE_WIDTH, + SST_MUL_FACTOR_NONE) + + return 0; +} + +#define _read_pp_level_info(name_str, name, level, offset, start, width, mult_factor)\ +{\ + u64 val, _mask;\ + \ + val = readq(power_domain_info->sst_base +\ + power_domain_info->perf_levels[level].mmio_offset +\ + (power_domain_info->feature_offsets.pp_offset * 8) + (offset));\ + _mask = GENMASK_ULL((start + width - 1), start);\ + val &= _mask; \ + val >>= start;\ + name = (val * mult_factor);\ +} + +#define SST_PP_INFO_0_OFFSET 0 +#define SST_PP_INFO_1_OFFSET 8 +#define SST_PP_INFO_2_OFFSET 16 +#define SST_PP_INFO_3_OFFSET 24 + +/* SST_PP_INFO_4_OFFSET to SST_PP_INFO_9_OFFSET are trl levels */ +#define SST_PP_INFO_4_OFFSET 32 + +#define SST_PP_INFO_10_OFFSET 80 +#define SST_PP_INFO_11_OFFSET 88 + +#define SST_PP_P1_SSE_START 0 +#define SST_PP_P1_SSE_WIDTH 8 + +#define SST_PP_P1_AVX2_START 8 +#define SST_PP_P1_AVX2_WIDTH 8 + +#define SST_PP_P1_AVX512_START 16 +#define SST_PP_P1_AVX512_WIDTH 8 + +#define SST_PP_P1_AMX_START 24 +#define SST_PP_P1_AMX_WIDTH 8 + +#define SST_PP_TDP_START 32 +#define SST_PP_TDP_WIDTH 15 + +#define SST_PP_T_PROCHOT_START 47 +#define SST_PP_T_PROCHOT_WIDTH 8 + +#define SST_PP_MAX_MEMORY_FREQ_START 55 +#define SST_PP_MAX_MEMORY_FREQ_WIDTH 7 + +#define SST_PP_COOLING_TYPE_START 62 +#define SST_PP_COOLING_TYPE_WIDTH 2 + +#define SST_PP_TRL_0_RATIO_0_START 0 +#define SST_PP_TRL_0_RATIO_0_WIDTH 8 + +#define SST_PP_TRL_CORES_BUCKET_0_START 0 +#define SST_PP_TRL_CORES_BUCKET_0_WIDTH 8 + +#define SST_PP_CORE_RATIO_P0_START 0 +#define SST_PP_CORE_RATIO_P0_WIDTH 8 + +#define SST_PP_CORE_RATIO_P1_START 8 +#define SST_PP_CORE_RATIO_P1_WIDTH 8 + +#define SST_PP_CORE_RATIO_PN_START 16 +#define SST_PP_CORE_RATIO_PN_WIDTH 8 + +#define SST_PP_CORE_RATIO_PM_START 24 +#define SST_PP_CORE_RATIO_PM_WIDTH 8 + +#define SST_PP_CORE_RATIO_P0_FABRIC_START 32 +#define SST_PP_CORE_RATIO_P0_FABRIC_WIDTH 8 + +#define SST_PP_CORE_RATIO_P1_FABRIC_START 40 +#define SST_PP_CORE_RATIO_P1_FABRIC_WIDTH 8 + +#define SST_PP_CORE_RATIO_PM_FABRIC_START 48 +#define SST_PP_CORE_RATIO_PM_FABRIC_WIDTH 8 + +static int isst_if_get_perf_level_info(void __user *argp) +{ + struct isst_perf_level_data_info perf_level; + struct tpmi_per_power_domain_info *power_domain_info; + int i, j; + + if (copy_from_user(&perf_level, argp, sizeof(perf_level))) + return -EFAULT; + + power_domain_info = get_instance(perf_level.socket_id, perf_level.power_domain_id); + if (!power_domain_info) + return -EINVAL; + + if (perf_level.level > power_domain_info->max_level) + return -EINVAL; + + if (!(power_domain_info->pp_header.level_en_mask & BIT(perf_level.level))) + return -EINVAL; + + _read_pp_level_info("tdp_ratio", perf_level.tdp_ratio, perf_level.level, + SST_PP_INFO_0_OFFSET, SST_PP_P1_SSE_START, SST_PP_P1_SSE_WIDTH, + SST_MUL_FACTOR_NONE) + _read_pp_level_info("base_freq_mhz", perf_level.base_freq_mhz, perf_level.level, + SST_PP_INFO_0_OFFSET, SST_PP_P1_SSE_START, SST_PP_P1_SSE_WIDTH, + SST_MUL_FACTOR_FREQ) + _read_pp_level_info("base_freq_avx2_mhz", perf_level.base_freq_avx2_mhz, perf_level.level, + SST_PP_INFO_0_OFFSET, SST_PP_P1_AVX2_START, SST_PP_P1_AVX2_WIDTH, + SST_MUL_FACTOR_FREQ) + _read_pp_level_info("base_freq_avx512_mhz", perf_level.base_freq_avx512_mhz, + perf_level.level, SST_PP_INFO_0_OFFSET, SST_PP_P1_AVX512_START, + SST_PP_P1_AVX512_WIDTH, SST_MUL_FACTOR_FREQ) + _read_pp_level_info("base_freq_amx_mhz", perf_level.base_freq_amx_mhz, perf_level.level, + SST_PP_INFO_0_OFFSET, SST_PP_P1_AMX_START, SST_PP_P1_AMX_WIDTH, + SST_MUL_FACTOR_FREQ) + + _read_pp_level_info("thermal_design_power_w", perf_level.thermal_design_power_w, + perf_level.level, SST_PP_INFO_1_OFFSET, SST_PP_TDP_START, + SST_PP_TDP_WIDTH, SST_MUL_FACTOR_NONE) + perf_level.thermal_design_power_w /= 8; /* units are in 1/8th watt */ + _read_pp_level_info("tjunction_max_c", perf_level.tjunction_max_c, perf_level.level, + SST_PP_INFO_1_OFFSET, SST_PP_T_PROCHOT_START, SST_PP_T_PROCHOT_WIDTH, + SST_MUL_FACTOR_NONE) + _read_pp_level_info("max_memory_freq_mhz", perf_level.max_memory_freq_mhz, + perf_level.level, SST_PP_INFO_1_OFFSET, SST_PP_MAX_MEMORY_FREQ_START, + SST_PP_MAX_MEMORY_FREQ_WIDTH, SST_MUL_FACTOR_FREQ) + _read_pp_level_info("cooling_type", perf_level.cooling_type, perf_level.level, + SST_PP_INFO_1_OFFSET, SST_PP_COOLING_TYPE_START, + SST_PP_COOLING_TYPE_WIDTH, SST_MUL_FACTOR_NONE) + + for (i = 0; i < TRL_MAX_LEVELS; ++i) { + for (j = 0; j < TRL_MAX_BUCKETS; ++j) + _read_pp_level_info("trl*_bucket*_freq_mhz", + perf_level.trl_freq_mhz[i][j], perf_level.level, + SST_PP_INFO_4_OFFSET + (i * SST_PP_TRL_0_RATIO_0_WIDTH), + j * SST_PP_TRL_0_RATIO_0_WIDTH, + SST_PP_TRL_0_RATIO_0_WIDTH, + SST_MUL_FACTOR_FREQ); + } + + for (i = 0; i < TRL_MAX_BUCKETS; ++i) + _read_pp_level_info("bucket*_core_count", perf_level.bucket_core_counts[i], + perf_level.level, SST_PP_INFO_10_OFFSET, + SST_PP_TRL_CORES_BUCKET_0_WIDTH * i, + SST_PP_TRL_CORES_BUCKET_0_WIDTH, SST_MUL_FACTOR_NONE) + + perf_level.max_buckets = TRL_MAX_BUCKETS; + perf_level.max_trl_levels = TRL_MAX_LEVELS; + + _read_pp_level_info("p0_freq_mhz", perf_level.p0_freq_mhz, perf_level.level, + SST_PP_INFO_11_OFFSET, SST_PP_CORE_RATIO_P0_START, + SST_PP_CORE_RATIO_P0_WIDTH, SST_MUL_FACTOR_FREQ) + _read_pp_level_info("p1_freq_mhz", perf_level.p1_freq_mhz, perf_level.level, + SST_PP_INFO_11_OFFSET, SST_PP_CORE_RATIO_P1_START, + SST_PP_CORE_RATIO_P1_WIDTH, SST_MUL_FACTOR_FREQ) + _read_pp_level_info("pn_freq_mhz", perf_level.pn_freq_mhz, perf_level.level, + SST_PP_INFO_11_OFFSET, SST_PP_CORE_RATIO_PN_START, + SST_PP_CORE_RATIO_PN_WIDTH, SST_MUL_FACTOR_FREQ) + _read_pp_level_info("pm_freq_mhz", perf_level.pm_freq_mhz, perf_level.level, + SST_PP_INFO_11_OFFSET, SST_PP_CORE_RATIO_PM_START, + SST_PP_CORE_RATIO_PM_WIDTH, SST_MUL_FACTOR_FREQ) + _read_pp_level_info("p0_fabric_freq_mhz", perf_level.p0_fabric_freq_mhz, + perf_level.level, SST_PP_INFO_11_OFFSET, + SST_PP_CORE_RATIO_P0_FABRIC_START, + SST_PP_CORE_RATIO_P0_FABRIC_WIDTH, SST_MUL_FACTOR_FREQ) + _read_pp_level_info("p1_fabric_freq_mhz", perf_level.p1_fabric_freq_mhz, + perf_level.level, SST_PP_INFO_11_OFFSET, + SST_PP_CORE_RATIO_P1_FABRIC_START, + SST_PP_CORE_RATIO_P1_FABRIC_WIDTH, SST_MUL_FACTOR_FREQ) + _read_pp_level_info("pm_fabric_freq_mhz", perf_level.pm_fabric_freq_mhz, + perf_level.level, SST_PP_INFO_11_OFFSET, + SST_PP_CORE_RATIO_PM_FABRIC_START, + SST_PP_CORE_RATIO_PM_FABRIC_WIDTH, SST_MUL_FACTOR_FREQ) + + if (copy_to_user(argp, &perf_level, sizeof(perf_level))) + return -EFAULT; + + return 0; +} + +#define SST_PP_FUSED_CORE_COUNT_START 0 +#define SST_PP_FUSED_CORE_COUNT_WIDTH 8 + +#define SST_PP_RSLVD_CORE_COUNT_START 8 +#define SST_PP_RSLVD_CORE_COUNT_WIDTH 8 + +#define SST_PP_RSLVD_CORE_MASK_START 0 +#define SST_PP_RSLVD_CORE_MASK_WIDTH 64 + +static int isst_if_get_perf_level_mask(void __user *argp) +{ + static struct isst_perf_level_cpu_mask cpumask; + struct tpmi_per_power_domain_info *power_domain_info; + u64 mask; + + if (copy_from_user(&cpumask, argp, sizeof(cpumask))) + return -EFAULT; + + power_domain_info = get_instance(cpumask.socket_id, cpumask.power_domain_id); + if (!power_domain_info) + return -EINVAL; + + _read_pp_level_info("mask", mask, cpumask.level, SST_PP_INFO_2_OFFSET, + SST_PP_RSLVD_CORE_MASK_START, SST_PP_RSLVD_CORE_MASK_WIDTH, + SST_MUL_FACTOR_NONE) + + cpumask.mask = mask; + + if (!cpumask.punit_cpu_map) + return -EOPNOTSUPP; + + if (copy_to_user(argp, &cpumask, sizeof(cpumask))) + return -EFAULT; + + return 0; +} + +#define SST_BF_INFO_0_OFFSET 0 +#define SST_BF_INFO_1_OFFSET 8 + +#define SST_BF_P1_HIGH_START 13 +#define SST_BF_P1_HIGH_WIDTH 8 + +#define SST_BF_P1_LOW_START 21 +#define SST_BF_P1_LOW_WIDTH 8 + +#define SST_BF_T_PROHOT_START 38 +#define SST_BF_T_PROHOT_WIDTH 8 + +#define SST_BF_TDP_START 46 +#define SST_BF_TDP_WIDTH 15 + +static int isst_if_get_base_freq_info(void __user *argp) +{ + static struct isst_base_freq_info base_freq; + struct tpmi_per_power_domain_info *power_domain_info; + + if (copy_from_user(&base_freq, argp, sizeof(base_freq))) + return -EFAULT; + + power_domain_info = get_instance(base_freq.socket_id, base_freq.power_domain_id); + if (!power_domain_info) + return -EINVAL; + + if (base_freq.level > power_domain_info->max_level) + return -EINVAL; + + _read_bf_level_info("p1_high", base_freq.high_base_freq_mhz, base_freq.level, + SST_BF_INFO_0_OFFSET, SST_BF_P1_HIGH_START, SST_BF_P1_HIGH_WIDTH, + SST_MUL_FACTOR_FREQ) + _read_bf_level_info("p1_low", base_freq.low_base_freq_mhz, base_freq.level, + SST_BF_INFO_0_OFFSET, SST_BF_P1_LOW_START, SST_BF_P1_LOW_WIDTH, + SST_MUL_FACTOR_FREQ) + _read_bf_level_info("BF-TJ", base_freq.tjunction_max_c, base_freq.level, + SST_BF_INFO_0_OFFSET, SST_BF_T_PROHOT_START, SST_BF_T_PROHOT_WIDTH, + SST_MUL_FACTOR_NONE) + _read_bf_level_info("BF-tdp", base_freq.thermal_design_power_w, base_freq.level, + SST_BF_INFO_0_OFFSET, SST_BF_TDP_START, SST_BF_TDP_WIDTH, + SST_MUL_FACTOR_NONE) + base_freq.thermal_design_power_w /= 8; /*unit = 1/8th watt*/ + + if (copy_to_user(argp, &base_freq, sizeof(base_freq))) + return -EFAULT; + + return 0; +} + +#define P1_HI_CORE_MASK_START 0 +#define P1_HI_CORE_MASK_WIDTH 64 + +static int isst_if_get_base_freq_mask(void __user *argp) +{ + static struct isst_perf_level_cpu_mask cpumask; + struct tpmi_per_power_domain_info *power_domain_info; + u64 mask; + + if (copy_from_user(&cpumask, argp, sizeof(cpumask))) + return -EFAULT; + + power_domain_info = get_instance(cpumask.socket_id, cpumask.power_domain_id); + if (!power_domain_info) + return -EINVAL; + + _read_bf_level_info("BF-cpumask", mask, cpumask.level, SST_BF_INFO_1_OFFSET, + P1_HI_CORE_MASK_START, P1_HI_CORE_MASK_WIDTH, + SST_MUL_FACTOR_NONE) + + cpumask.mask = mask; + + if (!cpumask.punit_cpu_map) + return -EOPNOTSUPP; + + if (copy_to_user(argp, &cpumask, sizeof(cpumask))) + return -EFAULT; + + return 0; +} + +static int isst_if_get_tpmi_instance_count(void __user *argp) +{ + struct isst_tpmi_instance_count tpmi_inst; + struct tpmi_sst_struct *sst_inst; + int i; + + if (copy_from_user(&tpmi_inst, argp, sizeof(tpmi_inst))) + return -EFAULT; + + if (tpmi_inst.socket_id >= topology_max_packages()) + return -EINVAL; + + tpmi_inst.count = isst_common.sst_inst[tpmi_inst.socket_id]->number_of_power_domains; + + sst_inst = isst_common.sst_inst[tpmi_inst.socket_id]; + tpmi_inst.valid_mask = 0; + for (i = 0; i < sst_inst->number_of_power_domains; ++i) { + struct tpmi_per_power_domain_info *pd_info; + + pd_info = &sst_inst->power_domain_info[i]; + if (pd_info->sst_base) + tpmi_inst.valid_mask |= BIT(i); + } + + if (copy_to_user(argp, &tpmi_inst, sizeof(tpmi_inst))) + return -EFAULT; + + return 0; +} + +#define SST_TF_INFO_0_OFFSET 0 +#define SST_TF_INFO_1_OFFSET 8 +#define SST_TF_INFO_2_OFFSET 16 + +#define SST_TF_MAX_LP_CLIP_RATIOS TRL_MAX_LEVELS + +#define SST_TF_LP_CLIP_RATIO_0_START 16 +#define SST_TF_LP_CLIP_RATIO_0_WIDTH 8 + +#define SST_TF_RATIO_0_START 0 +#define SST_TF_RATIO_0_WIDTH 8 + +#define SST_TF_NUM_CORE_0_START 0 +#define SST_TF_NUM_CORE_0_WIDTH 8 + +static int isst_if_get_turbo_freq_info(void __user *argp) +{ + static struct isst_turbo_freq_info turbo_freq; + struct tpmi_per_power_domain_info *power_domain_info; + int i, j; + + if (copy_from_user(&turbo_freq, argp, sizeof(turbo_freq))) + return -EFAULT; + + power_domain_info = get_instance(turbo_freq.socket_id, turbo_freq.power_domain_id); + if (!power_domain_info) + return -EINVAL; + + if (turbo_freq.level > power_domain_info->max_level) + return -EINVAL; + + turbo_freq.max_buckets = TRL_MAX_BUCKETS; + turbo_freq.max_trl_levels = TRL_MAX_LEVELS; + turbo_freq.max_clip_freqs = SST_TF_MAX_LP_CLIP_RATIOS; + + for (i = 0; i < turbo_freq.max_clip_freqs; ++i) + _read_tf_level_info("lp_clip*", turbo_freq.lp_clip_freq_mhz[i], + turbo_freq.level, SST_TF_INFO_0_OFFSET, + SST_TF_LP_CLIP_RATIO_0_START + + (i * SST_TF_LP_CLIP_RATIO_0_WIDTH), + SST_TF_LP_CLIP_RATIO_0_WIDTH, SST_MUL_FACTOR_FREQ) + + for (i = 0; i < TRL_MAX_LEVELS; ++i) { + for (j = 0; j < TRL_MAX_BUCKETS; ++j) + _read_tf_level_info("cydn*_bucket_*_trl", + turbo_freq.trl_freq_mhz[i][j], turbo_freq.level, + SST_TF_INFO_2_OFFSET + (i * SST_TF_RATIO_0_WIDTH), + j * SST_TF_RATIO_0_WIDTH, SST_TF_RATIO_0_WIDTH, + SST_MUL_FACTOR_FREQ) + } + + for (i = 0; i < TRL_MAX_BUCKETS; ++i) + _read_tf_level_info("bucket_*_core_count", turbo_freq.bucket_core_counts[i], + turbo_freq.level, SST_TF_INFO_1_OFFSET, + SST_TF_NUM_CORE_0_WIDTH * i, SST_TF_NUM_CORE_0_WIDTH, + SST_MUL_FACTOR_NONE) + + if (copy_to_user(argp, &turbo_freq, sizeof(turbo_freq))) + return -EFAULT; + + return 0; +} + +static long isst_if_def_ioctl(struct file *file, unsigned int cmd, + unsigned long arg) +{ + void __user *argp = (void __user *)arg; + long ret = -ENOTTY; + + mutex_lock(&isst_tpmi_dev_lock); + switch (cmd) { + case ISST_IF_COUNT_TPMI_INSTANCES: + ret = isst_if_get_tpmi_instance_count(argp); + break; + case ISST_IF_CORE_POWER_STATE: + ret = isst_if_core_power_state(argp); + break; + case ISST_IF_CLOS_PARAM: + ret = isst_if_clos_param(argp); + break; + case ISST_IF_CLOS_ASSOC: + ret = isst_if_clos_assoc(argp); + break; + case ISST_IF_PERF_LEVELS: + ret = isst_if_get_perf_level(argp); + break; + case ISST_IF_PERF_SET_LEVEL: + ret = isst_if_set_perf_level(argp); + break; + case ISST_IF_PERF_SET_FEATURE: + ret = isst_if_set_perf_feature(argp); + break; + case ISST_IF_GET_PERF_LEVEL_INFO: + ret = isst_if_get_perf_level_info(argp); + break; + case ISST_IF_GET_PERF_LEVEL_CPU_MASK: + ret = isst_if_get_perf_level_mask(argp); + break; + case ISST_IF_GET_BASE_FREQ_INFO: + ret = isst_if_get_base_freq_info(argp); + break; + case ISST_IF_GET_BASE_FREQ_CPU_MASK: + ret = isst_if_get_base_freq_mask(argp); + break; + case ISST_IF_GET_TURBO_FREQ_INFO: + ret = isst_if_get_turbo_freq_info(argp); + break; + default: + break; + } + mutex_unlock(&isst_tpmi_dev_lock); + + return ret; +} + +#define TPMI_SST_AUTO_SUSPEND_DELAY_MS 2000 + +int tpmi_sst_dev_add(struct auxiliary_device *auxdev) +{ + struct intel_tpmi_plat_info *plat_info; + struct tpmi_sst_struct *tpmi_sst; + int i, ret, pkg = 0, inst = 0; + int num_resources; + + plat_info = tpmi_get_platform_data(auxdev); + if (!plat_info) { + dev_err(&auxdev->dev, "No platform info\n"); + return -EINVAL; + } + + pkg = plat_info->package_id; + if (pkg >= topology_max_packages()) { + dev_err(&auxdev->dev, "Invalid package id :%x\n", pkg); + return -EINVAL; + } + + if (isst_common.sst_inst[pkg]) + return -EEXIST; + + num_resources = tpmi_get_resource_count(auxdev); + + if (!num_resources) + return -EINVAL; + + tpmi_sst = devm_kzalloc(&auxdev->dev, sizeof(*tpmi_sst), GFP_KERNEL); + if (!tpmi_sst) + return -ENOMEM; + + tpmi_sst->power_domain_info = devm_kcalloc(&auxdev->dev, num_resources, + sizeof(*tpmi_sst->power_domain_info), + GFP_KERNEL); + if (!tpmi_sst->power_domain_info) + return -ENOMEM; + + tpmi_sst->number_of_power_domains = num_resources; + + for (i = 0; i < num_resources; ++i) { + struct resource *res; + + res = tpmi_get_resource_at_index(auxdev, i); + if (!res) { + tpmi_sst->power_domain_info[i].sst_base = NULL; + continue; + } + + tpmi_sst->power_domain_info[i].package_id = pkg; + tpmi_sst->power_domain_info[i].power_domain_id = i; + tpmi_sst->power_domain_info[i].auxdev = auxdev; + tpmi_sst->power_domain_info[i].sst_base = devm_ioremap_resource(&auxdev->dev, res); + if (IS_ERR(tpmi_sst->power_domain_info[i].sst_base)) + return PTR_ERR(tpmi_sst->power_domain_info[i].sst_base); + + ret = sst_main(auxdev, &tpmi_sst->power_domain_info[i]); + if (ret) { + devm_iounmap(&auxdev->dev, tpmi_sst->power_domain_info[i].sst_base); + tpmi_sst->power_domain_info[i].sst_base = NULL; + continue; + } + + ++inst; + } + + if (!inst) + return -ENODEV; + + tpmi_sst->package_id = pkg; + auxiliary_set_drvdata(auxdev, tpmi_sst); + + mutex_lock(&isst_tpmi_dev_lock); + if (isst_common.max_index < pkg) + isst_common.max_index = pkg; + isst_common.sst_inst[pkg] = tpmi_sst; + mutex_unlock(&isst_tpmi_dev_lock); + + return 0; +} +EXPORT_SYMBOL_NS_GPL(tpmi_sst_dev_add, INTEL_TPMI_SST); + +void tpmi_sst_dev_remove(struct auxiliary_device *auxdev) +{ + struct tpmi_sst_struct *tpmi_sst = auxiliary_get_drvdata(auxdev); + + mutex_lock(&isst_tpmi_dev_lock); + isst_common.sst_inst[tpmi_sst->package_id] = NULL; + mutex_unlock(&isst_tpmi_dev_lock); +} +EXPORT_SYMBOL_NS_GPL(tpmi_sst_dev_remove, INTEL_TPMI_SST); + +void tpmi_sst_dev_suspend(struct auxiliary_device *auxdev) +{ + struct tpmi_sst_struct *tpmi_sst = auxiliary_get_drvdata(auxdev); + struct tpmi_per_power_domain_info *power_domain_info = tpmi_sst->power_domain_info; + void __iomem *cp_base; + + cp_base = power_domain_info->sst_base + power_domain_info->sst_header.cp_offset; + power_domain_info->saved_sst_cp_control = readq(cp_base + SST_CP_CONTROL_OFFSET); + + memcpy_fromio(power_domain_info->saved_clos_configs, cp_base + SST_CLOS_CONFIG_0_OFFSET, + sizeof(power_domain_info->saved_clos_configs)); + + memcpy_fromio(power_domain_info->saved_clos_assocs, cp_base + SST_CLOS_ASSOC_0_OFFSET, + sizeof(power_domain_info->saved_clos_assocs)); + + power_domain_info->saved_pp_control = readq(power_domain_info->sst_base + + power_domain_info->sst_header.pp_offset + + SST_PP_CONTROL_OFFSET); +} +EXPORT_SYMBOL_NS_GPL(tpmi_sst_dev_suspend, INTEL_TPMI_SST); + +void tpmi_sst_dev_resume(struct auxiliary_device *auxdev) +{ + struct tpmi_sst_struct *tpmi_sst = auxiliary_get_drvdata(auxdev); + struct tpmi_per_power_domain_info *power_domain_info = tpmi_sst->power_domain_info; + void __iomem *cp_base; + + cp_base = power_domain_info->sst_base + power_domain_info->sst_header.cp_offset; + writeq(power_domain_info->saved_sst_cp_control, cp_base + SST_CP_CONTROL_OFFSET); + + memcpy_toio(cp_base + SST_CLOS_CONFIG_0_OFFSET, power_domain_info->saved_clos_configs, + sizeof(power_domain_info->saved_clos_configs)); + + memcpy_toio(cp_base + SST_CLOS_ASSOC_0_OFFSET, power_domain_info->saved_clos_assocs, + sizeof(power_domain_info->saved_clos_assocs)); + + writeq(power_domain_info->saved_pp_control, power_domain_info->sst_base + + power_domain_info->sst_header.pp_offset + SST_PP_CONTROL_OFFSET); +} +EXPORT_SYMBOL_NS_GPL(tpmi_sst_dev_resume, INTEL_TPMI_SST); + +#define ISST_TPMI_API_VERSION 0x02 + +int tpmi_sst_init(void) +{ + struct isst_if_cmd_cb cb; + int ret = 0; + + mutex_lock(&isst_tpmi_dev_lock); + + if (isst_core_usage_count) { + ++isst_core_usage_count; + goto init_done; + } + + isst_common.sst_inst = kcalloc(topology_max_packages(), + sizeof(*isst_common.sst_inst), + GFP_KERNEL); + if (!isst_common.sst_inst) { + ret = -ENOMEM; + goto init_done; + } + + memset(&cb, 0, sizeof(cb)); + cb.cmd_size = sizeof(struct isst_if_io_reg); + cb.offset = offsetof(struct isst_if_io_regs, io_reg); + cb.cmd_callback = NULL; + cb.api_version = ISST_TPMI_API_VERSION; + cb.def_ioctl = isst_if_def_ioctl; + cb.owner = THIS_MODULE; + ret = isst_if_cdev_register(ISST_IF_DEV_TPMI, &cb); + if (ret) + kfree(isst_common.sst_inst); + else + ++isst_core_usage_count; +init_done: + mutex_unlock(&isst_tpmi_dev_lock); + return ret; +} +EXPORT_SYMBOL_NS_GPL(tpmi_sst_init, INTEL_TPMI_SST); + +void tpmi_sst_exit(void) +{ + mutex_lock(&isst_tpmi_dev_lock); + if (isst_core_usage_count) + --isst_core_usage_count; + + if (!isst_core_usage_count) { + isst_if_cdev_unregister(ISST_IF_DEV_TPMI); + kfree(isst_common.sst_inst); + } + mutex_unlock(&isst_tpmi_dev_lock); +} +EXPORT_SYMBOL_NS_GPL(tpmi_sst_exit, INTEL_TPMI_SST); + +MODULE_IMPORT_NS(INTEL_TPMI); +MODULE_IMPORT_NS(INTEL_TPMI_POWER_DOMAIN); + +MODULE_LICENSE("GPL"); diff --git a/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.h b/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.h new file mode 100644 index 0000000000..900b483703 --- /dev/null +++ b/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Intel Speed Select Interface: Drivers Internal defines + * Copyright (c) 2023, Intel Corporation. + * All rights reserved. + * + */ + +#ifndef _ISST_TPMI_CORE_H +#define _ISST_TPMI_CORE_H + +int tpmi_sst_init(void); +void tpmi_sst_exit(void); +int tpmi_sst_dev_add(struct auxiliary_device *auxdev); +void tpmi_sst_dev_remove(struct auxiliary_device *auxdev); +void tpmi_sst_dev_suspend(struct auxiliary_device *auxdev); +void tpmi_sst_dev_resume(struct auxiliary_device *auxdev); +#endif |