!787 Intel: Support In Field Scan(IFS) Array BIST

Merge Pull Request from: @allen-shi 
 
Intel 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.

IFS Scan At Field(SAF) multi-blob images supported in [PR471](https://gitee.com/openeuler/kernel/pulls/471) and [PR580](https://gitee.com/openeuler/kernel/pulls/580)

IFS Array BIST performs tests on some portions of the core logic such as caches and register files. These are different portions of the silicon compared to the parts tested by the first test type i.e Scan at Field (SAF). Emerald Rapids (EMR) is the first CPU to support Array BIST.

This PR is to support In Field Scan(IFS) Array BIST and includes 9 commits totally.
It is upstreamed in v6.4-rc1.
https://lore.kernel.org/lkml/20230322003359.213046-1-jithu.joseph@intel.com/

 
 **Intel-Kernel Issue** 
[#I73EG8](https://gitee.com/openeuler/intel-kernel/issues/I73EG8)

 **Test** 
Built and run the kernel successfully on openEuler 22.03 LTS SP1.
Test is PASS on EMR platform.

 **Known Issue** 
N/A

 **Default config change** 
N/A 
 
Link:https://gitee.com/openeuler/kernel/pulls/787 

Reviewed-by: Jason Zeng <jason.zeng@intel.com> 
Reviewed-by: Jialin Zhang <zhangjialin11@huawei.com> 
Signed-off-by: Jialin Zhang <zhangjialin11@huawei.com> 

Documentation/ABI/testing/sysfs-platform-intel-ifs

+Device instance to test mapping
+intel_ifs_0  ->  Scan Test
+intel_ifs_1  ->  Array BIST test
+
 What:		/sys/devices/virtual/misc/intel_ifs_<N>/run_test
 Date:		Nov 16 2022
 KernelVersion:	6.2
@@ -8,6 +12,7 @@ Description:	Write <cpu#> to trigger IFS test for one online core.
 		completes the test for the core containing that thread.
 		Example: to test the core containing cpu5: echo 5 >
 		/sys/devices/virtual/misc/intel_ifs_<N>/run_test
+Devices:	all
 
 What:		/sys/devices/virtual/misc/intel_ifs_<N>/status
 Date:		Nov 16 2022
@@ -15,21 +20,25 @@ KernelVersion:	6.2
 Contact:	"Jithu Joseph" <jithu.joseph@intel.com>
 Description:	The status of the last test. It can be one of "pass", "fail"
 		or "untested".
+Devices:	all
 
 What:		/sys/devices/virtual/misc/intel_ifs_<N>/details
 Date:		Nov 16 2022
 KernelVersion:	6.2
 Contact:	"Jithu Joseph" <jithu.joseph@intel.com>
 Description:	Additional information regarding the last test. The details file reports
-		the hex value of the SCAN_STATUS MSR. Note that the error_code field
+		the hex value of the STATUS MSR for this test. Note that the error_code field
 		may contain driver defined software code not defined in the Intel SDM.
+Devices:	all
 
 What:		/sys/devices/virtual/misc/intel_ifs_<N>/image_version
 Date:		Nov 16 2022
 KernelVersion:	6.2
 Contact:	"Jithu Joseph" <jithu.joseph@intel.com>
-Description:	Version (hexadecimal) of loaded IFS binary image. If no scan image
-		is loaded reports "none".
+Description:	Version (hexadecimal) of loaded IFS test image. If no test image
+		is loaded reports "none". Only present for device instances where a test image
+		is applicable.
+Devices:	intel_ifs_0
 
 What:		/sys/devices/virtual/misc/intel_ifs_<N>/current_batch
 Date:		Nov 16 2022
@@ -39,3 +48,5 @@ Description:	Write a number less than or equal to 0xff to load an IFS test image
 		The number written treated as the 2 digit suffix in the following file name:
 		/lib/firmware/intel/ifs_<N>/ff-mm-ss-02x.scan
 		Reading the file will provide the suffix of the currently loaded IFS test image.
+		This file is present only for device instances where a test image is applicable.
+Devices:	intel_ifs_0

arch/x86/include/asm/msr-index.h

@@ -196,6 +196,8 @@
 
 /* Abbreviated from Intel SDM name IA32_INTEGRITY_CAPABILITIES */
 #define MSR_INTEGRITY_CAPS			0x000002d9
+#define MSR_INTEGRITY_CAPS_ARRAY_BIST_BIT      2
+#define MSR_INTEGRITY_CAPS_ARRAY_BIST          BIT(MSR_INTEGRITY_CAPS_ARRAY_BIST_BIT)
 #define MSR_INTEGRITY_CAPS_PERIODIC_BIST_BIT	4
 #define MSR_INTEGRITY_CAPS_PERIODIC_BIST	BIT(MSR_INTEGRITY_CAPS_PERIODIC_BIST_BIT)
 

drivers/platform/x86/intel/ifs/core.c

@@ -16,27 +16,63 @@
 
 static const struct x86_cpu_id ifs_cpu_ids[] __initconst = {
 	X86_MATCH(SAPPHIRERAPIDS_X),
+	X86_MATCH(EMERALDRAPIDS_X),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, ifs_cpu_ids);
 
-static struct ifs_device ifs_device = {
-	.data = {
-		.integrity_cap_bit = MSR_INTEGRITY_CAPS_PERIODIC_BIST_BIT,
-		.test_num = 0,
+ATTRIBUTE_GROUPS(plat_ifs);
+ATTRIBUTE_GROUPS(plat_ifs_array);
+
+bool *ifs_pkg_auth;
+
+static const struct ifs_test_caps scan_test = {
+	.integrity_cap_bit = MSR_INTEGRITY_CAPS_PERIODIC_BIST_BIT,
+	.test_num = IFS_TYPE_SAF,
+};
+
+static const struct ifs_test_caps array_test = {
+	.integrity_cap_bit = MSR_INTEGRITY_CAPS_ARRAY_BIST_BIT,
+	.test_num = IFS_TYPE_ARRAY_BIST,
+};
+
+static struct ifs_device ifs_devices[] = {
+	[IFS_TYPE_SAF] = {
+		.test_caps = &scan_test,
+		.misc = {
+			.name = "intel_ifs_0",
+			.minor = MISC_DYNAMIC_MINOR,
+			.groups = plat_ifs_groups,
+		},
 	},
-	.misc = {
-		.name = "intel_ifs_0",
-		.nodename = "intel_ifs/0",
-		.minor = MISC_DYNAMIC_MINOR,
+	[IFS_TYPE_ARRAY_BIST] = {
+		.test_caps = &array_test,
+		.misc = {
+			.name = "intel_ifs_1",
+			.minor = MISC_DYNAMIC_MINOR,
+			.groups = plat_ifs_array_groups,
+		},
 	},
 };
 
+#define IFS_NUMTESTS ARRAY_SIZE(ifs_devices)
+
+static void ifs_cleanup(void)
+{
+	int i;
+
+	for (i = 0; i < IFS_NUMTESTS; i++) {
+		if (ifs_devices[i].misc.this_device)
+			misc_deregister(&ifs_devices[i].misc);
+	}
+	kfree(ifs_pkg_auth);
+}
+
 static int __init ifs_init(void)
 {
 	const struct x86_cpu_id *m;
 	u64 msrval;
-	int ret;
+	int i, ret;
 
 	m = x86_match_cpu(ifs_cpu_ids);
 	if (!m)
@@ -51,28 +87,27 @@ static int __init ifs_init(void)
 	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)))
-		return -ENODEV;
-
-	ifs_device.data.pkg_auth = kmalloc_array(topology_max_packages(), sizeof(bool), GFP_KERNEL);
-	if (!ifs_device.data.pkg_auth)
+	ifs_pkg_auth = kmalloc_array(topology_max_packages(), sizeof(bool), GFP_KERNEL);
+	if (!ifs_pkg_auth)
 		return -ENOMEM;
 
-	ret = misc_register(&ifs_device.misc);
-	if (ret) {
-		kfree(ifs_device.data.pkg_auth);
-		return ret;
+	for (i = 0; i < IFS_NUMTESTS; i++) {
+		if (!(msrval & BIT(ifs_devices[i].test_caps->integrity_cap_bit)))
+			continue;
+		ret = misc_register(&ifs_devices[i].misc);
+		if (ret)
+			goto err_exit;
 	}
-
 	return 0;
+
+err_exit:
+	ifs_cleanup();
+	return ret;
 }
 
 static void __exit ifs_exit(void)
 {
-	misc_deregister(&ifs_device.misc);
-	kfree(ifs_device.data.pkg_auth);
+	ifs_cleanup();
 }
 
 module_init(ifs_init);

drivers/platform/x86/intel/ifs/ifs.h

@@ -17,7 +17,7 @@
  * 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.
+ * with a new platform-device instance-id.
  *
  *
  * IFS Image
@@ -25,7 +25,10 @@
  *
  * 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.
+ * family-model-stepping. IFS Images are not applicable for some test types.
+ * Wherever applicable the sysfs directory would provide a "current_batch" file
+ * (see below) for loading the image.
+ *
  *
  * IFS Image Loading
  * -----------------
@@ -35,7 +38,7 @@
  * SHA hashes for the test. Then the tests themselves. Status MSRs provide
  * feedback on the success/failure of these steps.
  *
- * The test files are kept in a fixed location: /lib/firmware/intel/ifs_0/
+ * The test files are kept in a fixed location: /lib/firmware/intel/ifs_<n>/
  * For e.g if there are 3 test files, they would be named in the following
  * fashion:
  * ff-mm-ss-01.scan
@@ -47,7 +50,7 @@
  * (e.g 1, 2 or 3 in the above scenario) into the curent_batch file.
  * To load ff-mm-ss-02.scan, the following command can be used::
  *
- *   # echo 2 > /sys/devices/virtual/misc/intel_ifs_0/current_batch
+ *   # echo 2 > /sys/devices/virtual/misc/intel_ifs_<n>/current_batch
  *
  * The above file can also be read to know the currently loaded image.
  *
@@ -69,16 +72,16 @@
  * 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
+ * In all cases reading the corresponding test's 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/
+ * The IFS driver provides sysfs interfaces via /sys/devices/virtual/misc/intel_ifs_<n>/
  * to control execution:
  *
  * Test a specific core::
  *
- *   # echo <cpu#> > /sys/devices/virtual/misc/intel_ifs_0/run_test
+ *   # echo <cpu#> > /sys/devices/virtual/misc/intel_ifs_<n>/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,
@@ -87,21 +90,21 @@
  *
  * For e.g. to test core corresponding to cpu5
  *
- *   # echo 5 > /sys/devices/virtual/misc/intel_ifs_0/run_test
+ *   # echo 5 > /sys/devices/virtual/misc/intel_ifs_<n>/run_test
  *
  * Results of the last test is provided in /sys::
  *
- *   $ cat /sys/devices/virtual/misc/intel_ifs_0/status
+ *   $ cat /sys/devices/virtual/misc/intel_ifs_<n>/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
+ *   $ cat /sys/devices/virtual/misc/intel_ifs_<n>/details
  *   0x8081
  *
- * The details file reports the hex value of the SCAN_STATUS MSR.
+ * The details file reports the hex value of the test specific 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:
@@ -127,6 +130,7 @@
 #include <linux/device.h>
 #include <linux/miscdevice.h>
 
+#define MSR_ARRAY_BIST				0x00000105
 #define MSR_COPY_SCAN_HASHES			0x000002c2
 #define MSR_SCAN_HASHES_STATUS			0x000002c3
 #define MSR_AUTHENTICATE_AND_COPY_CHUNK		0x000002c4
@@ -137,6 +141,9 @@
 #define SCAN_TEST_PASS				1
 #define SCAN_TEST_FAIL				2
 
+#define IFS_TYPE_SAF			0
+#define IFS_TYPE_ARRAY_BIST		1
+
 /* MSR_SCAN_HASHES_STATUS bit fields */
 union ifs_scan_hashes_status {
 	u64	data;
@@ -189,6 +196,17 @@ union ifs_status {
 	};
 };
 
+/* MSR_ARRAY_BIST bit fields */
+union ifs_array {
+	u64	data;
+	struct {
+		u32	array_bitmask;
+		u16	array_bank;
+		u16	rsvd			:15;
+		u16	ctrl_result		:1;
+	};
+};
+
 /*
  * Driver populated error-codes
  * 0xFD: Test timed out before completing all the chunks.
@@ -197,22 +215,22 @@ union ifs_status {
 #define IFS_SW_TIMEOUT				0xFD
 #define IFS_SW_PARTIAL_COMPLETION		0xFE
 
+struct ifs_test_caps {
+	int	integrity_cap_bit;
+	int	test_num;
+};
+
 /**
  * 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.
- * @pkg_auth: array of bool storing per package auth status
  * @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
  * @cur_batch: number indicating the currently loaded test file
- * @test_num: number indicating the test type
  */
 struct ifs_data {
-	int	integrity_cap_bit;
-	bool	*pkg_auth;
 	int	loaded_version;
 	bool	loaded;
 	bool	loading_error;
@@ -220,7 +238,6 @@ struct ifs_data {
 	int	status;
 	u64	scan_details;
 	u32	cur_batch;
-	int	test_num;
 };
 
 struct ifs_work {
@@ -229,7 +246,8 @@ struct ifs_work {
 };
 
 struct ifs_device {
-	struct ifs_data data;
+	const struct ifs_test_caps *test_caps;
+	struct ifs_data rw_data;
 	struct miscdevice misc;
 };
 
@@ -238,11 +256,21 @@ 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;
+	return &d->rw_data;
+}
+
+static inline const struct ifs_test_caps *ifs_get_test_caps(struct device *dev)
+{
+	struct miscdevice *m = dev_get_drvdata(dev);
+	struct ifs_device *d = container_of(m, struct ifs_device, misc);
+
+	return d->test_caps;
 }
 
+extern bool *ifs_pkg_auth;
 int 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 attribute *plat_ifs_attrs[];
+extern struct attribute *plat_ifs_array_attrs[];
 
 #endif

drivers/platform/x86/intel/ifs/load.c

@@ -192,7 +192,7 @@ static int scan_chunks_sanity_check(struct device *dev)
 	struct ifs_work local_work;
 	int curr_pkg, cpu, ret;
 
-	memset(ifsd->pkg_auth, 0, (topology_max_packages() * sizeof(bool)));
+	memset(ifs_pkg_auth, 0, (topology_max_packages() * sizeof(bool)));
 	ret = validate_ifs_metadata(dev);
 	if (ret)
 		return ret;
@@ -204,7 +204,7 @@ static int scan_chunks_sanity_check(struct device *dev)
 	cpus_read_lock();
 	for_each_online_cpu(cpu) {
 		curr_pkg = topology_physical_package_id(cpu);
-		if (ifsd->pkg_auth[curr_pkg])
+		if (ifs_pkg_auth[curr_pkg])
 			continue;
 		reinit_completion(&ifs_done);
 		local_work.dev = dev;
@@ -215,7 +215,7 @@ static int scan_chunks_sanity_check(struct device *dev)
 			ret = -EIO;
 			goto out;
 		}
-		ifsd->pkg_auth[curr_pkg] = 1;
+		ifs_pkg_auth[curr_pkg] = 1;
 	}
 	ret = 0;
 out:
@@ -257,13 +257,14 @@ static int image_sanity_check(struct device *dev, const struct microcode_header_
  */
 int ifs_load_firmware(struct device *dev)
 {
+	const struct ifs_test_caps *test = ifs_get_test_caps(dev);
 	struct ifs_data *ifsd = ifs_get_data(dev);
 	const struct firmware *fw;
 	char scan_path[64];
 	int ret = -EINVAL;
 
 	snprintf(scan_path, sizeof(scan_path), "intel/ifs_%d/%02x-%02x-%02x-%02x.scan",
-		 ifsd->test_num, boot_cpu_data.x86, boot_cpu_data.x86_model,
+		 test->test_num, boot_cpu_data.x86, boot_cpu_data.x86_model,
 		 boot_cpu_data.x86_stepping, ifsd->cur_batch);
 
 	ret = request_firmware_direct(&fw, scan_path, dev);

drivers/platform/x86/intel/ifs/runtest.c

@@ -229,6 +229,85 @@ static void ifs_test_core(int cpu, struct device *dev)
 	}
 }
 
+#define SPINUNIT 100 /* 100 nsec */
+static atomic_t array_cpus_out;
+
+/*
+ * Simplified cpu sibling rendezvous loop based on microcode loader __wait_for_cpus()
+ */
+static void wait_for_sibling_cpu(atomic_t *t, long long timeout)
+{
+	int cpu = smp_processor_id();
+	const struct cpumask *smt_mask = cpu_smt_mask(cpu);
+	int all_cpus = cpumask_weight(smt_mask);
+
+	atomic_inc(t);
+	while (atomic_read(t) < all_cpus) {
+		if (timeout < SPINUNIT)
+			return;
+		ndelay(SPINUNIT);
+		timeout -= SPINUNIT;
+		touch_nmi_watchdog();
+	}
+}
+
+static int do_array_test(void *data)
+{
+	union ifs_array *command = data;
+	int cpu = smp_processor_id();
+	int first;
+
+	/*
+	 * Only one logical CPU on a core needs to trigger the Array test via MSR write.
+	 */
+	first = cpumask_first(cpu_smt_mask(cpu));
+
+	if (cpu == first) {
+		wrmsrl(MSR_ARRAY_BIST, command->data);
+		/* Pass back the result of the test */
+		rdmsrl(MSR_ARRAY_BIST, command->data);
+	}
+
+	/* Tests complete faster if the sibling is spinning here */
+	wait_for_sibling_cpu(&array_cpus_out, NSEC_PER_SEC);
+
+	return 0;
+}
+
+static void ifs_array_test_core(int cpu, struct device *dev)
+{
+	union ifs_array command = {};
+	bool timed_out = false;
+	struct ifs_data *ifsd;
+	unsigned long timeout;
+
+	ifsd = ifs_get_data(dev);
+
+	command.array_bitmask = ~0U;
+	timeout = jiffies + HZ / 2;
+
+	do {
+		if (time_after(jiffies, timeout)) {
+			timed_out = true;
+			break;
+		}
+		atomic_set(&array_cpus_out, 0);
+		stop_core_cpuslocked(cpu, do_array_test, &command);
+
+		if (command.ctrl_result)
+			break;
+	} while (command.array_bitmask);
+
+	ifsd->scan_details = command.data;
+
+	if (command.ctrl_result)
+		ifsd->status = SCAN_TEST_FAIL;
+	else if (timed_out || command.array_bitmask)
+		ifsd->status = SCAN_NOT_TESTED;
+	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
@@ -236,6 +315,8 @@ static void ifs_test_core(int cpu, struct device *dev)
  */
 int do_core_test(int cpu, struct device *dev)
 {
+	const struct ifs_test_caps *test = ifs_get_test_caps(dev);
+	struct ifs_data *ifsd = ifs_get_data(dev);
 	int ret = 0;
 
 	/* Prevent CPUs from being taken offline during the scan test */
@@ -247,7 +328,18 @@ int do_core_test(int cpu, struct device *dev)
 		goto out;
 	}
 
-	ifs_test_core(cpu, dev);
+	switch (test->test_num) {
+	case IFS_TYPE_SAF:
+		if (!ifsd->loaded)
+			return -EPERM;
+		ifs_test_core(cpu, dev);
+		break;
+	case IFS_TYPE_ARRAY_BIST:
+		ifs_array_test_core(cpu, dev);
+		break;
+	default:
+		return -EINVAL;
+	}
 out:
 	cpus_read_unlock();
 	return ret;

drivers/platform/x86/intel/ifs/sysfs.c

@@ -64,7 +64,6 @@ 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;
 
@@ -75,10 +74,7 @@ static ssize_t run_test_store(struct device *dev,
 	if (down_interruptible(&ifs_sem))
 		return -EINTR;
 
-	if (!ifsd->loaded)
-		rc = -EPERM;
-	else
-		rc = do_core_test(cpu, dev);
+	rc = do_core_test(cpu, dev);
 
 	up(&ifs_sem);
 
@@ -141,7 +137,7 @@ static ssize_t image_version_show(struct device *dev,
 static DEVICE_ATTR_RO(image_version);
 
 /* global scan sysfs attributes */
-static struct attribute *plat_ifs_attrs[] = {
+struct attribute *plat_ifs_attrs[] = {
 	&dev_attr_details.attr,
 	&dev_attr_status.attr,
 	&dev_attr_run_test.attr,
@@ -150,9 +146,10 @@ static struct attribute *plat_ifs_attrs[] = {
 	NULL
 };
 
-ATTRIBUTE_GROUPS(plat_ifs);
-
-const struct attribute_group **ifs_get_groups(void)
-{
-	return plat_ifs_groups;
-}
+/* global array sysfs attributes */
+struct attribute *plat_ifs_array_attrs[] = {
+	&dev_attr_details.attr,
+	&dev_attr_status.attr,
+	&dev_attr_run_test.attr,
+	NULL
+};