diff options
Diffstat (limited to 'drivers/platform/x86/intel/ifs')
| -rw-r--r-- | drivers/platform/x86/intel/ifs/Kconfig | 16 | ||||
| -rw-r--r-- | drivers/platform/x86/intel/ifs/Makefile | 3 | ||||
| -rw-r--r-- | drivers/platform/x86/intel/ifs/core.c | 73 | ||||
| -rw-r--r-- | drivers/platform/x86/intel/ifs/ifs.h | 234 | ||||
| -rw-r--r-- | drivers/platform/x86/intel/ifs/load.c | 266 | ||||
| -rw-r--r-- | drivers/platform/x86/intel/ifs/runtest.c | 252 | ||||
| -rw-r--r-- | drivers/platform/x86/intel/ifs/sysfs.c | 149 |
7 files changed, 993 insertions, 0 deletions
diff --git a/drivers/platform/x86/intel/ifs/Kconfig b/drivers/platform/x86/intel/ifs/Kconfig new file mode 100644 index 000000000..c341a27cc --- /dev/null +++ b/drivers/platform/x86/intel/ifs/Kconfig @@ -0,0 +1,16 @@ +config INTEL_IFS + tristate "Intel In Field Scan" + depends on X86 && CPU_SUP_INTEL && 64BIT && SMP + # Discussion on the list has shown that the sysfs API needs a bit + # more work, mark this as broken for now + depends on BROKEN + select INTEL_IFS_DEVICE + help + Enable support for the In Field Scan capability in select + CPUs. The capability allows for running low level tests via + a scan image distributed by Intel via Github to validate CPU + operation beyond baseline RAS capabilities. To compile this + support as a module, choose M here. The module will be called + intel_ifs. + + If unsure, say N. diff --git a/drivers/platform/x86/intel/ifs/Makefile b/drivers/platform/x86/intel/ifs/Makefile new file mode 100644 index 000000000..30f035ef5 --- /dev/null +++ b/drivers/platform/x86/intel/ifs/Makefile @@ -0,0 +1,3 @@ +obj-$(CONFIG_INTEL_IFS) += intel_ifs.o + +intel_ifs-objs := core.o load.o runtest.o sysfs.o diff --git a/drivers/platform/x86/intel/ifs/core.c b/drivers/platform/x86/intel/ifs/core.c new file mode 100644 index 000000000..27204e3d6 --- /dev/null +++ b/drivers/platform/x86/intel/ifs/core.c @@ -0,0 +1,73 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright(c) 2022 Intel Corporation. */ + +#include <linux/module.h> +#include <linux/kdev_t.h> +#include <linux/semaphore.h> + +#include <asm/cpu_device_id.h> + +#include "ifs.h" + +#define X86_MATCH(model) \ + X86_MATCH_VENDOR_FAM_MODEL_FEATURE(INTEL, 6, \ + INTEL_FAM6_##model, X86_FEATURE_CORE_CAPABILITIES, NULL) + +static const struct x86_cpu_id ifs_cpu_ids[] __initconst = { + X86_MATCH(SAPPHIRERAPIDS_X), + {} +}; +MODULE_DEVICE_TABLE(x86cpu, ifs_cpu_ids); + +static struct ifs_device ifs_device = { + .data = { + .integrity_cap_bit = MSR_INTEGRITY_CAPS_PERIODIC_BIST_BIT, + }, + .misc = { + .name = "intel_ifs_0", + .nodename = "intel_ifs/0", + .minor = MISC_DYNAMIC_MINOR, + }, +}; + +static int __init ifs_init(void) +{ + const struct x86_cpu_id *m; + u64 msrval; + + m = x86_match_cpu(ifs_cpu_ids); + if (!m) + return -ENODEV; + + if (rdmsrl_safe(MSR_IA32_CORE_CAPS, &msrval)) + return -ENODEV; + + if (!(msrval & MSR_IA32_CORE_CAPS_INTEGRITY_CAPS)) + return -ENODEV; + + if (rdmsrl_safe(MSR_INTEGRITY_CAPS, &msrval)) + return -ENODEV; + + ifs_device.misc.groups = ifs_get_groups(); + + if ((msrval & BIT(ifs_device.data.integrity_cap_bit)) && + !misc_register(&ifs_device.misc)) { + down(&ifs_sem); + ifs_load_firmware(ifs_device.misc.this_device); + up(&ifs_sem); + return 0; + } + + return -ENODEV; +} + +static void __exit ifs_exit(void) +{ + misc_deregister(&ifs_device.misc); +} + +module_init(ifs_init); +module_exit(ifs_exit); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Intel In Field Scan (IFS) device"); diff --git a/drivers/platform/x86/intel/ifs/ifs.h b/drivers/platform/x86/intel/ifs/ifs.h new file mode 100644 index 000000000..73c8e91cf --- /dev/null +++ b/drivers/platform/x86/intel/ifs/ifs.h @@ -0,0 +1,234 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright(c) 2022 Intel Corporation. */ + +#ifndef _IFS_H_ +#define _IFS_H_ + +/** + * DOC: In-Field Scan + * + * ============= + * In-Field Scan + * ============= + * + * Introduction + * ------------ + * + * In Field Scan (IFS) is a hardware feature to run circuit level tests on + * a CPU core to detect problems that are not caught by parity or ECC checks. + * Future CPUs will support more than one type of test which will show up + * with a new platform-device instance-id, for now only .0 is exposed. + * + * + * IFS Image + * --------- + * + * Intel provides a firmware file containing the scan tests via + * github [#f1]_. Similar to microcode there is a separate file for each + * family-model-stepping. + * + * IFS Image Loading + * ----------------- + * + * The driver loads the tests into memory reserved BIOS local to each CPU + * socket in a two step process using writes to MSRs to first load the + * SHA hashes for the test. Then the tests themselves. Status MSRs provide + * feedback on the success/failure of these steps. When a new test file + * is installed it can be loaded by writing to the driver reload file:: + * + * # echo 1 > /sys/devices/virtual/misc/intel_ifs_0/reload + * + * Similar to microcode, the current version of the scan tests is stored + * in a fixed location: /lib/firmware/intel/ifs.0/family-model-stepping.scan + * + * Running tests + * ------------- + * + * Tests are run by the driver synchronizing execution of all threads on a + * core and then writing to the ACTIVATE_SCAN MSR on all threads. Instruction + * execution continues when: + * + * 1) All tests have completed. + * 2) Execution was interrupted. + * 3) A test detected a problem. + * + * Note that ALL THREADS ON THE CORE ARE EFFECTIVELY OFFLINE FOR THE + * DURATION OF THE TEST. This can be up to 200 milliseconds. If the system + * is running latency sensitive applications that cannot tolerate an + * interruption of this magnitude, the system administrator must arrange + * to migrate those applications to other cores before running a core test. + * It may also be necessary to redirect interrupts to other CPUs. + * + * In all cases reading the SCAN_STATUS MSR provides details on what + * happened. The driver makes the value of this MSR visible to applications + * via the "details" file (see below). Interrupted tests may be restarted. + * + * The IFS driver provides sysfs interfaces via /sys/devices/virtual/misc/intel_ifs_0/ + * to control execution: + * + * Test a specific core:: + * + * # echo <cpu#> > /sys/devices/virtual/misc/intel_ifs_0/run_test + * + * when HT is enabled any of the sibling cpu# can be specified to test + * its corresponding physical core. Since the tests are per physical core, + * the result of testing any thread is same. All siblings must be online + * to run a core test. It is only necessary to test one thread. + * + * For e.g. to test core corresponding to cpu5 + * + * # echo 5 > /sys/devices/virtual/misc/intel_ifs_0/run_test + * + * Results of the last test is provided in /sys:: + * + * $ cat /sys/devices/virtual/misc/intel_ifs_0/status + * pass + * + * Status can be one of pass, fail, untested + * + * Additional details of the last test is provided by the details file:: + * + * $ cat /sys/devices/virtual/misc/intel_ifs_0/details + * 0x8081 + * + * The details file reports the hex value of the SCAN_STATUS MSR. + * Hardware defined error codes are documented in volume 4 of the Intel + * Software Developer's Manual but the error_code field may contain one of + * the following driver defined software codes: + * + * +------+--------------------+ + * | 0xFD | Software timeout | + * +------+--------------------+ + * | 0xFE | Partial completion | + * +------+--------------------+ + * + * Driver design choices + * --------------------- + * + * 1) The ACTIVATE_SCAN MSR allows for running any consecutive subrange of + * available tests. But the driver always tries to run all tests and only + * uses the subrange feature to restart an interrupted test. + * + * 2) Hardware allows for some number of cores to be tested in parallel. + * The driver does not make use of this, it only tests one core at a time. + * + * .. [#f1] https://github.com/intel/TBD + */ +#include <linux/device.h> +#include <linux/miscdevice.h> + +#define MSR_COPY_SCAN_HASHES 0x000002c2 +#define MSR_SCAN_HASHES_STATUS 0x000002c3 +#define MSR_AUTHENTICATE_AND_COPY_CHUNK 0x000002c4 +#define MSR_CHUNKS_AUTHENTICATION_STATUS 0x000002c5 +#define MSR_ACTIVATE_SCAN 0x000002c6 +#define MSR_SCAN_STATUS 0x000002c7 +#define SCAN_NOT_TESTED 0 +#define SCAN_TEST_PASS 1 +#define SCAN_TEST_FAIL 2 + +/* MSR_SCAN_HASHES_STATUS bit fields */ +union ifs_scan_hashes_status { + u64 data; + struct { + u32 chunk_size :16; + u32 num_chunks :8; + u32 rsvd1 :8; + u32 error_code :8; + u32 rsvd2 :11; + u32 max_core_limit :12; + u32 valid :1; + }; +}; + +/* MSR_CHUNKS_AUTH_STATUS bit fields */ +union ifs_chunks_auth_status { + u64 data; + struct { + u32 valid_chunks :8; + u32 total_chunks :8; + u32 rsvd1 :16; + u32 error_code :8; + u32 rsvd2 :24; + }; +}; + +/* MSR_ACTIVATE_SCAN bit fields */ +union ifs_scan { + u64 data; + struct { + u32 start :8; + u32 stop :8; + u32 rsvd :16; + u32 delay :31; + u32 sigmce :1; + }; +}; + +/* MSR_SCAN_STATUS bit fields */ +union ifs_status { + u64 data; + struct { + u32 chunk_num :8; + u32 chunk_stop_index :8; + u32 rsvd1 :16; + u32 error_code :8; + u32 rsvd2 :22; + u32 control_error :1; + u32 signature_error :1; + }; +}; + +/* + * Driver populated error-codes + * 0xFD: Test timed out before completing all the chunks. + * 0xFE: not all scan chunks were executed. Maximum forward progress retries exceeded. + */ +#define IFS_SW_TIMEOUT 0xFD +#define IFS_SW_PARTIAL_COMPLETION 0xFE + +/** + * struct ifs_data - attributes related to intel IFS driver + * @integrity_cap_bit: MSR_INTEGRITY_CAPS bit enumerating this test + * @loaded_version: stores the currently loaded ifs image version. + * @loaded: If a valid test binary has been loaded into the memory + * @loading_error: Error occurred on another CPU while loading image + * @valid_chunks: number of chunks which could be validated. + * @status: it holds simple status pass/fail/untested + * @scan_details: opaque scan status code from h/w + */ +struct ifs_data { + int integrity_cap_bit; + int loaded_version; + bool loaded; + bool loading_error; + int valid_chunks; + int status; + u64 scan_details; +}; + +struct ifs_work { + struct work_struct w; + struct device *dev; +}; + +struct ifs_device { + struct ifs_data data; + struct miscdevice misc; +}; + +static inline struct ifs_data *ifs_get_data(struct device *dev) +{ + struct miscdevice *m = dev_get_drvdata(dev); + struct ifs_device *d = container_of(m, struct ifs_device, misc); + + return &d->data; +} + +void ifs_load_firmware(struct device *dev); +int do_core_test(int cpu, struct device *dev); +const struct attribute_group **ifs_get_groups(void); + +extern struct semaphore ifs_sem; + +#endif diff --git a/drivers/platform/x86/intel/ifs/load.c b/drivers/platform/x86/intel/ifs/load.c new file mode 100644 index 000000000..3e52b4eb1 --- /dev/null +++ b/drivers/platform/x86/intel/ifs/load.c @@ -0,0 +1,266 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright(c) 2022 Intel Corporation. */ + +#include <linux/firmware.h> +#include <asm/cpu.h> +#include <linux/slab.h> +#include <asm/microcode_intel.h> + +#include "ifs.h" + +struct ifs_header { + u32 header_ver; + u32 blob_revision; + u32 date; + u32 processor_sig; + u32 check_sum; + u32 loader_rev; + u32 processor_flags; + u32 metadata_size; + u32 total_size; + u32 fusa_info; + u64 reserved; +}; + +#define IFS_HEADER_SIZE (sizeof(struct ifs_header)) +static struct ifs_header *ifs_header_ptr; /* pointer to the ifs image header */ +static u64 ifs_hash_ptr; /* Address of ifs metadata (hash) */ +static u64 ifs_test_image_ptr; /* 256B aligned address of test pattern */ +static DECLARE_COMPLETION(ifs_done); + +static const char * const scan_hash_status[] = { + [0] = "No error reported", + [1] = "Attempt to copy scan hashes when copy already in progress", + [2] = "Secure Memory not set up correctly", + [3] = "FuSaInfo.ProgramID does not match or ff-mm-ss does not match", + [4] = "Reserved", + [5] = "Integrity check failed", + [6] = "Scan reload or test is in progress" +}; + +static const char * const scan_authentication_status[] = { + [0] = "No error reported", + [1] = "Attempt to authenticate a chunk which is already marked as authentic", + [2] = "Chunk authentication error. The hash of chunk did not match expected value" +}; + +/* + * To copy scan hashes and authenticate test chunks, the initiating cpu must point + * to the EDX:EAX to the test image in linear address. + * Run wrmsr(MSR_COPY_SCAN_HASHES) for scan hash copy and run wrmsr(MSR_AUTHENTICATE_AND_COPY_CHUNK) + * for scan hash copy and test chunk authentication. + */ +static void copy_hashes_authenticate_chunks(struct work_struct *work) +{ + struct ifs_work *local_work = container_of(work, struct ifs_work, w); + union ifs_scan_hashes_status hashes_status; + union ifs_chunks_auth_status chunk_status; + struct device *dev = local_work->dev; + int i, num_chunks, chunk_size; + struct ifs_data *ifsd; + u64 linear_addr, base; + u32 err_code; + + ifsd = ifs_get_data(dev); + /* run scan hash copy */ + wrmsrl(MSR_COPY_SCAN_HASHES, ifs_hash_ptr); + rdmsrl(MSR_SCAN_HASHES_STATUS, hashes_status.data); + + /* enumerate the scan image information */ + num_chunks = hashes_status.num_chunks; + chunk_size = hashes_status.chunk_size * 1024; + err_code = hashes_status.error_code; + + if (!hashes_status.valid) { + ifsd->loading_error = true; + if (err_code >= ARRAY_SIZE(scan_hash_status)) { + dev_err(dev, "invalid error code 0x%x for hash copy\n", err_code); + goto done; + } + dev_err(dev, "Hash copy error : %s", scan_hash_status[err_code]); + goto done; + } + + /* base linear address to the scan data */ + base = ifs_test_image_ptr; + + /* scan data authentication and copy chunks to secured memory */ + for (i = 0; i < num_chunks; i++) { + linear_addr = base + i * chunk_size; + linear_addr |= i; + + wrmsrl(MSR_AUTHENTICATE_AND_COPY_CHUNK, linear_addr); + rdmsrl(MSR_CHUNKS_AUTHENTICATION_STATUS, chunk_status.data); + + ifsd->valid_chunks = chunk_status.valid_chunks; + err_code = chunk_status.error_code; + + if (err_code) { + ifsd->loading_error = true; + if (err_code >= ARRAY_SIZE(scan_authentication_status)) { + dev_err(dev, + "invalid error code 0x%x for authentication\n", err_code); + goto done; + } + dev_err(dev, "Chunk authentication error %s\n", + scan_authentication_status[err_code]); + goto done; + } + } +done: + complete(&ifs_done); +} + +/* + * IFS requires scan chunks authenticated per each socket in the platform. + * Once the test chunk is authenticated, it is automatically copied to secured memory + * and proceed the authentication for the next chunk. + */ +static int scan_chunks_sanity_check(struct device *dev) +{ + int metadata_size, curr_pkg, cpu, ret = -ENOMEM; + struct ifs_data *ifsd = ifs_get_data(dev); + bool *package_authenticated; + struct ifs_work local_work; + char *test_ptr; + + package_authenticated = kcalloc(topology_max_packages(), sizeof(bool), GFP_KERNEL); + if (!package_authenticated) + return ret; + + metadata_size = ifs_header_ptr->metadata_size; + + /* Spec says that if the Meta Data Size = 0 then it should be treated as 2000 */ + if (metadata_size == 0) + metadata_size = 2000; + + /* Scan chunk start must be 256 byte aligned */ + if ((metadata_size + IFS_HEADER_SIZE) % 256) { + dev_err(dev, "Scan pattern offset within the binary is not 256 byte aligned\n"); + return -EINVAL; + } + + test_ptr = (char *)ifs_header_ptr + IFS_HEADER_SIZE + metadata_size; + ifsd->loading_error = false; + + ifs_test_image_ptr = (u64)test_ptr; + ifsd->loaded_version = ifs_header_ptr->blob_revision; + + /* copy the scan hash and authenticate per package */ + cpus_read_lock(); + for_each_online_cpu(cpu) { + curr_pkg = topology_physical_package_id(cpu); + if (package_authenticated[curr_pkg]) + continue; + reinit_completion(&ifs_done); + local_work.dev = dev; + INIT_WORK_ONSTACK(&local_work.w, copy_hashes_authenticate_chunks); + schedule_work_on(cpu, &local_work.w); + wait_for_completion(&ifs_done); + if (ifsd->loading_error) + goto out; + package_authenticated[curr_pkg] = 1; + } + ret = 0; +out: + cpus_read_unlock(); + kfree(package_authenticated); + + return ret; +} + +static int ifs_sanity_check(struct device *dev, + const struct microcode_header_intel *mc_header) +{ + unsigned long total_size, data_size; + u32 sum, *mc; + + total_size = get_totalsize(mc_header); + data_size = get_datasize(mc_header); + + if ((data_size + MC_HEADER_SIZE > total_size) || (total_size % sizeof(u32))) { + dev_err(dev, "bad ifs data file size.\n"); + return -EINVAL; + } + + if (mc_header->ldrver != 1 || mc_header->hdrver != 1) { + dev_err(dev, "invalid/unknown ifs update format.\n"); + return -EINVAL; + } + + mc = (u32 *)mc_header; + sum = 0; + for (int i = 0; i < total_size / sizeof(u32); i++) + sum += mc[i]; + + if (sum) { + dev_err(dev, "bad ifs data checksum, aborting.\n"); + return -EINVAL; + } + + return 0; +} + +static bool find_ifs_matching_signature(struct device *dev, struct ucode_cpu_info *uci, + const struct microcode_header_intel *shdr) +{ + unsigned int mc_size; + + mc_size = get_totalsize(shdr); + + if (!mc_size || ifs_sanity_check(dev, shdr) < 0) { + dev_err(dev, "ifs sanity check failure\n"); + return false; + } + + if (!intel_cpu_signatures_match(uci->cpu_sig.sig, uci->cpu_sig.pf, shdr->sig, shdr->pf)) { + dev_err(dev, "ifs signature, pf not matching\n"); + return false; + } + + return true; +} + +static bool ifs_image_sanity_check(struct device *dev, const struct microcode_header_intel *data) +{ + struct ucode_cpu_info uci; + + intel_cpu_collect_info(&uci); + + return find_ifs_matching_signature(dev, &uci, data); +} + +/* + * Load ifs image. Before loading ifs module, the ifs image must be located + * in /lib/firmware/intel/ifs and named as {family/model/stepping}.{testname}. + */ +void ifs_load_firmware(struct device *dev) +{ + struct ifs_data *ifsd = ifs_get_data(dev); + const struct firmware *fw; + char scan_path[32]; + int ret; + + snprintf(scan_path, sizeof(scan_path), "intel/ifs/%02x-%02x-%02x.scan", + boot_cpu_data.x86, boot_cpu_data.x86_model, boot_cpu_data.x86_stepping); + + ret = request_firmware_direct(&fw, scan_path, dev); + if (ret) { + dev_err(dev, "ifs file %s load failed\n", scan_path); + goto done; + } + + if (!ifs_image_sanity_check(dev, (struct microcode_header_intel *)fw->data)) { + dev_err(dev, "ifs header sanity check failed\n"); + goto release; + } + + ifs_header_ptr = (struct ifs_header *)fw->data; + ifs_hash_ptr = (u64)(ifs_header_ptr + 1); + + ret = scan_chunks_sanity_check(dev); +release: + release_firmware(fw); +done: + ifsd->loaded = (ret == 0); +} diff --git a/drivers/platform/x86/intel/ifs/runtest.c b/drivers/platform/x86/intel/ifs/runtest.c new file mode 100644 index 000000000..b2ca2bb45 --- /dev/null +++ b/drivers/platform/x86/intel/ifs/runtest.c @@ -0,0 +1,252 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright(c) 2022 Intel Corporation. */ + +#include <linux/cpu.h> +#include <linux/delay.h> +#include <linux/fs.h> +#include <linux/nmi.h> +#include <linux/slab.h> +#include <linux/stop_machine.h> + +#include "ifs.h" + +/* + * Note all code and data in this file is protected by + * ifs_sem. On HT systems all threads on a core will + * execute together, but only the first thread on the + * core will update results of the test. + */ + +#define CREATE_TRACE_POINTS +#include <trace/events/intel_ifs.h> + +/* Max retries on the same chunk */ +#define MAX_IFS_RETRIES 5 + +/* + * Number of TSC cycles that a logical CPU will wait for the other + * logical CPU on the core in the WRMSR(ACTIVATE_SCAN). + */ +#define IFS_THREAD_WAIT 100000 + +enum ifs_status_err_code { + IFS_NO_ERROR = 0, + IFS_OTHER_THREAD_COULD_NOT_JOIN = 1, + IFS_INTERRUPTED_BEFORE_RENDEZVOUS = 2, + IFS_POWER_MGMT_INADEQUATE_FOR_SCAN = 3, + IFS_INVALID_CHUNK_RANGE = 4, + IFS_MISMATCH_ARGUMENTS_BETWEEN_THREADS = 5, + IFS_CORE_NOT_CAPABLE_CURRENTLY = 6, + IFS_UNASSIGNED_ERROR_CODE = 7, + IFS_EXCEED_NUMBER_OF_THREADS_CONCURRENT = 8, + IFS_INTERRUPTED_DURING_EXECUTION = 9, +}; + +static const char * const scan_test_status[] = { + [IFS_NO_ERROR] = "SCAN no error", + [IFS_OTHER_THREAD_COULD_NOT_JOIN] = "Other thread could not join.", + [IFS_INTERRUPTED_BEFORE_RENDEZVOUS] = "Interrupt occurred prior to SCAN coordination.", + [IFS_POWER_MGMT_INADEQUATE_FOR_SCAN] = + "Core Abort SCAN Response due to power management condition.", + [IFS_INVALID_CHUNK_RANGE] = "Non valid chunks in the range", + [IFS_MISMATCH_ARGUMENTS_BETWEEN_THREADS] = "Mismatch in arguments between threads T0/T1.", + [IFS_CORE_NOT_CAPABLE_CURRENTLY] = "Core not capable of performing SCAN currently", + [IFS_UNASSIGNED_ERROR_CODE] = "Unassigned error code 0x7", + [IFS_EXCEED_NUMBER_OF_THREADS_CONCURRENT] = + "Exceeded number of Logical Processors (LP) allowed to run Scan-At-Field concurrently", + [IFS_INTERRUPTED_DURING_EXECUTION] = "Interrupt occurred prior to SCAN start", +}; + +static void message_not_tested(struct device *dev, int cpu, union ifs_status status) +{ + if (status.error_code < ARRAY_SIZE(scan_test_status)) { + dev_info(dev, "CPU(s) %*pbl: SCAN operation did not start. %s\n", + cpumask_pr_args(cpu_smt_mask(cpu)), + scan_test_status[status.error_code]); + } else if (status.error_code == IFS_SW_TIMEOUT) { + dev_info(dev, "CPU(s) %*pbl: software timeout during scan\n", + cpumask_pr_args(cpu_smt_mask(cpu))); + } else if (status.error_code == IFS_SW_PARTIAL_COMPLETION) { + dev_info(dev, "CPU(s) %*pbl: %s\n", + cpumask_pr_args(cpu_smt_mask(cpu)), + "Not all scan chunks were executed. Maximum forward progress retries exceeded"); + } else { + dev_info(dev, "CPU(s) %*pbl: SCAN unknown status %llx\n", + cpumask_pr_args(cpu_smt_mask(cpu)), status.data); + } +} + +static void message_fail(struct device *dev, int cpu, union ifs_status status) +{ + /* + * control_error is set when the microcode runs into a problem + * loading the image from the reserved BIOS memory, or it has + * been corrupted. Reloading the image may fix this issue. + */ + if (status.control_error) { + dev_err(dev, "CPU(s) %*pbl: could not execute from loaded scan image\n", + cpumask_pr_args(cpu_smt_mask(cpu))); + } + + /* + * signature_error is set when the output from the scan chains does not + * match the expected signature. This might be a transient problem (e.g. + * due to a bit flip from an alpha particle or neutron). If the problem + * repeats on a subsequent test, then it indicates an actual problem in + * the core being tested. + */ + if (status.signature_error) { + dev_err(dev, "CPU(s) %*pbl: test signature incorrect.\n", + cpumask_pr_args(cpu_smt_mask(cpu))); + } +} + +static bool can_restart(union ifs_status status) +{ + enum ifs_status_err_code err_code = status.error_code; + + /* Signature for chunk is bad, or scan test failed */ + if (status.signature_error || status.control_error) + return false; + + switch (err_code) { + case IFS_NO_ERROR: + case IFS_OTHER_THREAD_COULD_NOT_JOIN: + case IFS_INTERRUPTED_BEFORE_RENDEZVOUS: + case IFS_POWER_MGMT_INADEQUATE_FOR_SCAN: + case IFS_EXCEED_NUMBER_OF_THREADS_CONCURRENT: + case IFS_INTERRUPTED_DURING_EXECUTION: + return true; + case IFS_INVALID_CHUNK_RANGE: + case IFS_MISMATCH_ARGUMENTS_BETWEEN_THREADS: + case IFS_CORE_NOT_CAPABLE_CURRENTLY: + case IFS_UNASSIGNED_ERROR_CODE: + break; + } + return false; +} + +/* + * Execute the scan. Called "simultaneously" on all threads of a core + * at high priority using the stop_cpus mechanism. + */ +static int doscan(void *data) +{ + int cpu = smp_processor_id(); + u64 *msrs = data; + int first; + + /* Only the first logical CPU on a core reports result */ + first = cpumask_first(cpu_smt_mask(cpu)); + + /* + * This WRMSR will wait for other HT threads to also write + * to this MSR (at most for activate.delay cycles). Then it + * starts scan of each requested chunk. The core scan happens + * during the "execution" of the WRMSR. This instruction can + * take up to 200 milliseconds (in the case where all chunks + * are processed in a single pass) before it retires. + */ + wrmsrl(MSR_ACTIVATE_SCAN, msrs[0]); + + if (cpu == first) { + /* Pass back the result of the scan */ + rdmsrl(MSR_SCAN_STATUS, msrs[1]); + } + + return 0; +} + +/* + * Use stop_core_cpuslocked() to synchronize writing to MSR_ACTIVATE_SCAN + * on all threads of the core to be tested. Loop if necessary to complete + * run of all chunks. Include some defensive tests to make sure forward + * progress is made, and that the whole test completes in a reasonable time. + */ +static void ifs_test_core(int cpu, struct device *dev) +{ + union ifs_scan activate; + union ifs_status status; + unsigned long timeout; + struct ifs_data *ifsd; + u64 msrvals[2]; + int retries; + + ifsd = ifs_get_data(dev); + + activate.rsvd = 0; + activate.delay = IFS_THREAD_WAIT; + activate.sigmce = 0; + activate.start = 0; + activate.stop = ifsd->valid_chunks - 1; + + timeout = jiffies + HZ / 2; + retries = MAX_IFS_RETRIES; + + while (activate.start <= activate.stop) { + if (time_after(jiffies, timeout)) { + status.error_code = IFS_SW_TIMEOUT; + break; + } + + msrvals[0] = activate.data; + stop_core_cpuslocked(cpu, doscan, msrvals); + + status.data = msrvals[1]; + + trace_ifs_status(cpu, activate, status); + + /* Some cases can be retried, give up for others */ + if (!can_restart(status)) + break; + + if (status.chunk_num == activate.start) { + /* Check for forward progress */ + if (--retries == 0) { + if (status.error_code == IFS_NO_ERROR) + status.error_code = IFS_SW_PARTIAL_COMPLETION; + break; + } + } else { + retries = MAX_IFS_RETRIES; + activate.start = status.chunk_num; + } + } + + /* Update status for this core */ + ifsd->scan_details = status.data; + + if (status.control_error || status.signature_error) { + ifsd->status = SCAN_TEST_FAIL; + message_fail(dev, cpu, status); + } else if (status.error_code) { + ifsd->status = SCAN_NOT_TESTED; + message_not_tested(dev, cpu, status); + } else { + ifsd->status = SCAN_TEST_PASS; + } +} + +/* + * Initiate per core test. It wakes up work queue threads on the target cpu and + * its sibling cpu. Once all sibling threads wake up, the scan test gets executed and + * wait for all sibling threads to finish the scan test. + */ +int do_core_test(int cpu, struct device *dev) +{ + int ret = 0; + + /* Prevent CPUs from being taken offline during the scan test */ + cpus_read_lock(); + + if (!cpu_online(cpu)) { + dev_info(dev, "cannot test on the offline cpu %d\n", cpu); + ret = -EINVAL; + goto out; + } + + ifs_test_core(cpu, dev); +out: + cpus_read_unlock(); + return ret; +} diff --git a/drivers/platform/x86/intel/ifs/sysfs.c b/drivers/platform/x86/intel/ifs/sysfs.c new file mode 100644 index 000000000..37d8380d6 --- /dev/null +++ b/drivers/platform/x86/intel/ifs/sysfs.c @@ -0,0 +1,149 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright(c) 2022 Intel Corporation. */ + +#include <linux/cpu.h> +#include <linux/delay.h> +#include <linux/fs.h> +#include <linux/semaphore.h> +#include <linux/slab.h> + +#include "ifs.h" + +/* + * Protects against simultaneous tests on multiple cores, or + * reloading can file while a test is in progress + */ +DEFINE_SEMAPHORE(ifs_sem); + +/* + * The sysfs interface to check additional details of last test + * cat /sys/devices/system/platform/ifs/details + */ +static ssize_t details_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct ifs_data *ifsd = ifs_get_data(dev); + + return sysfs_emit(buf, "%#llx\n", ifsd->scan_details); +} + +static DEVICE_ATTR_RO(details); + +static const char * const status_msg[] = { + [SCAN_NOT_TESTED] = "untested", + [SCAN_TEST_PASS] = "pass", + [SCAN_TEST_FAIL] = "fail" +}; + +/* + * The sysfs interface to check the test status: + * To check the status of last test + * cat /sys/devices/platform/ifs/status + */ +static ssize_t status_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct ifs_data *ifsd = ifs_get_data(dev); + + return sysfs_emit(buf, "%s\n", status_msg[ifsd->status]); +} + +static DEVICE_ATTR_RO(status); + +/* + * The sysfs interface for single core testing + * To start test, for example, cpu5 + * echo 5 > /sys/devices/platform/ifs/run_test + * To check the result: + * cat /sys/devices/platform/ifs/result + * The sibling core gets tested at the same time. + */ +static ssize_t run_test_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct ifs_data *ifsd = ifs_get_data(dev); + unsigned int cpu; + int rc; + + rc = kstrtouint(buf, 0, &cpu); + if (rc < 0 || cpu >= nr_cpu_ids) + return -EINVAL; + + if (down_interruptible(&ifs_sem)) + return -EINTR; + + if (!ifsd->loaded) + rc = -EPERM; + else + rc = do_core_test(cpu, dev); + + up(&ifs_sem); + + return rc ? rc : count; +} + +static DEVICE_ATTR_WO(run_test); + +/* + * Reload the IFS image. When user wants to install new IFS image + */ +static ssize_t reload_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct ifs_data *ifsd = ifs_get_data(dev); + bool res; + + + if (kstrtobool(buf, &res)) + return -EINVAL; + if (!res) + return count; + + if (down_interruptible(&ifs_sem)) + return -EINTR; + + ifs_load_firmware(dev); + + up(&ifs_sem); + + return ifsd->loaded ? count : -ENODEV; +} + +static DEVICE_ATTR_WO(reload); + +/* + * Display currently loaded IFS image version. + */ +static ssize_t image_version_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct ifs_data *ifsd = ifs_get_data(dev); + + if (!ifsd->loaded) + return sysfs_emit(buf, "%s\n", "none"); + else + return sysfs_emit(buf, "%#x\n", ifsd->loaded_version); +} + +static DEVICE_ATTR_RO(image_version); + +/* global scan sysfs attributes */ +static struct attribute *plat_ifs_attrs[] = { + &dev_attr_details.attr, + &dev_attr_status.attr, + &dev_attr_run_test.attr, + &dev_attr_reload.attr, + &dev_attr_image_version.attr, + NULL +}; + +ATTRIBUTE_GROUPS(plat_ifs); + +const struct attribute_group **ifs_get_groups(void) +{ + return plat_ifs_groups; +} |