1 files changed, 311 insertions, 52 deletions

diff --git a/drivers/platform/x86/intel/ifs/runtest.c b/drivers/platform/x86/intel/ifs/runtest.c
index 13ecd55c6668..f978dd05d4d8 100644
--- a/drivers/platform/x86/intel/ifs/runtest.c
+++ b/drivers/platform/x86/intel/ifs/runtest.c
@@ -23,6 +23,19 @@
 /* Max retries on the same chunk */
 #define MAX_IFS_RETRIES  5
 
+struct run_params {
+	struct ifs_data *ifsd;
+	union ifs_scan *activate;
+	union ifs_status status;
+};
+
+struct sbaf_run_params {
+	struct ifs_data *ifsd;
+	int *retry_cnt;
+	union ifs_sbaf *activate;
+	union ifs_sbaf_status status;
+};
+
 /*
  * Number of TSC cycles that a logical CPU will wait for the other
  * logical CPU on the core in the WRMSR(ACTIVATE_SCAN).
@@ -63,6 +76,19 @@ static const char * const scan_test_status[] = {
 
 static void message_not_tested(struct device *dev, int cpu, union ifs_status status)
 {
+	struct ifs_data *ifsd = ifs_get_data(dev);
+
+	/*
+	 * 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_warn(dev, "CPU(s) %*pbl: Scan controller error. Batch: %02x version: 0x%x\n",
+			 cpumask_pr_args(cpu_smt_mask(cpu)), ifsd->cur_batch, ifsd->loaded_version);
+		return;
+	}
+
 	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)),
@@ -85,16 +111,6 @@ static void message_fail(struct device *dev, int cpu, union ifs_status status)
 	struct ifs_data *ifsd = ifs_get_data(dev);
 
 	/*
-	 * 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. Batch: %02x version: 0x%x\n",
-			cpumask_pr_args(cpu_smt_mask(cpu)), ifsd->cur_batch, ifsd->loaded_version);
-	}
-
-	/*
 	 * 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
@@ -134,19 +150,57 @@ static bool can_restart(union ifs_status status)
 	return false;
 }
 
+#define SPINUNIT 100 /* 100 nsec */
+static atomic_t array_cpus_in;
+static atomic_t scan_cpus_in;
+static atomic_t sbaf_cpus_in;
+
+/*
+ * 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();
+	}
+}
+
 /*
  * 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 cpu = smp_processor_id(), start, stop;
+	struct run_params *params = data;
+	union ifs_status status;
+	struct ifs_data *ifsd;
 	int first;
 
+	ifsd = params->ifsd;
+
+	if (ifsd->generation) {
+		start = params->activate->gen2.start;
+		stop = params->activate->gen2.stop;
+	} else {
+		start = params->activate->gen0.start;
+		stop = params->activate->gen0.stop;
+	}
+
 	/* Only the first logical CPU on a core reports result */
 	first = cpumask_first(cpu_smt_mask(cpu));
 
+	wait_for_sibling_cpu(&scan_cpus_in, NSEC_PER_SEC);
+
 	/*
 	 * This WRMSR will wait for other HT threads to also write
 	 * to this MSR (at most for activate.delay cycles). Then it
@@ -155,12 +209,14 @@ static int doscan(void *data)
 	 * 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]);
+	wrmsrl(MSR_ACTIVATE_SCAN, params->activate->data);
+	rdmsrl(MSR_SCAN_STATUS, status.data);
 
-	if (cpu == first) {
-		/* Pass back the result of the scan */
-		rdmsrl(MSR_SCAN_STATUS, msrs[1]);
-	}
+	trace_ifs_status(ifsd->cur_batch, start, stop, status.data);
+
+	/* Pass back the result of the scan */
+	if (cpu == first)
+		params->status = status;
 
 	return 0;
 }
@@ -173,13 +229,13 @@ static int doscan(void *data)
  */
 static void ifs_test_core(int cpu, struct device *dev)
 {
+	union ifs_status status = {};
 	union ifs_scan activate;
-	union ifs_status status;
 	unsigned long timeout;
 	struct ifs_data *ifsd;
 	int to_start, to_stop;
 	int status_chunk;
-	u64 msrvals[2];
+	struct run_params params;
 	int retries;
 
 	ifsd = ifs_get_data(dev);
@@ -190,6 +246,8 @@ static void ifs_test_core(int cpu, struct device *dev)
 	to_start = 0;
 	to_stop = ifsd->valid_chunks - 1;
 
+	params.ifsd = ifs_get_data(dev);
+
 	if (ifsd->generation) {
 		activate.gen2.start = to_start;
 		activate.gen2.stop = to_stop;
@@ -207,12 +265,11 @@ static void ifs_test_core(int cpu, struct device *dev)
 			break;
 		}
 
-		msrvals[0] = activate.data;
-		stop_core_cpuslocked(cpu, doscan, msrvals);
-
-		status.data = msrvals[1];
+		params.activate = &activate;
+		atomic_set(&scan_cpus_in, 0);
+		stop_core_cpuslocked(cpu, doscan, &params);
 
-		trace_ifs_status(cpu, to_start, to_stop, status.data);
+		status = params.status;
 
 		/* Some cases can be retried, give up for others */
 		if (!can_restart(status))
@@ -239,10 +296,10 @@ static void ifs_test_core(int cpu, struct device *dev)
 	/* Update status for this core */
 	ifsd->scan_details = status.data;
 
-	if (status.control_error || status.signature_error) {
+	if (status.signature_error) {
 		ifsd->status = SCAN_TEST_FAIL;
 		message_fail(dev, cpu, status);
-	} else if (status.error_code) {
+	} else if (status.control_error || status.error_code) {
 		ifsd->status = SCAN_NOT_TESTED;
 		message_not_tested(dev, cpu, status);
 	} else {
@@ -250,34 +307,14 @@ 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;
 
+	wait_for_sibling_cpu(&array_cpus_in, NSEC_PER_SEC);
+
 	/*
 	 * Only one logical CPU on a core needs to trigger the Array test via MSR write.
 	 */
@@ -289,9 +326,6 @@ static int do_array_test(void *data)
 		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;
 }
 
@@ -312,7 +346,7 @@ static void ifs_array_test_core(int cpu, struct device *dev)
 			timed_out = true;
 			break;
 		}
-		atomic_set(&array_cpus_out, 0);
+		atomic_set(&array_cpus_in, 0);
 		stop_core_cpuslocked(cpu, do_array_test, &command);
 
 		if (command.ctrl_result)
@@ -361,6 +395,225 @@ static void ifs_array_test_gen1(int cpu, struct device *dev)
 		ifsd->status = SCAN_TEST_PASS;
 }
 
+#define SBAF_STATUS_PASS			0
+#define SBAF_STATUS_SIGN_FAIL			1
+#define SBAF_STATUS_INTR			2
+#define SBAF_STATUS_TEST_FAIL			3
+
+enum sbaf_status_err_code {
+	IFS_SBAF_NO_ERROR				= 0,
+	IFS_SBAF_OTHER_THREAD_COULD_NOT_JOIN		= 1,
+	IFS_SBAF_INTERRUPTED_BEFORE_RENDEZVOUS		= 2,
+	IFS_SBAF_UNASSIGNED_ERROR_CODE3			= 3,
+	IFS_SBAF_INVALID_BUNDLE_INDEX			= 4,
+	IFS_SBAF_MISMATCH_ARGS_BETWEEN_THREADS		= 5,
+	IFS_SBAF_CORE_NOT_CAPABLE_CURRENTLY		= 6,
+	IFS_SBAF_UNASSIGNED_ERROR_CODE7			= 7,
+	IFS_SBAF_EXCEED_NUMBER_OF_THREADS_CONCURRENT	= 8,
+	IFS_SBAF_INTERRUPTED_DURING_EXECUTION		= 9,
+	IFS_SBAF_INVALID_PROGRAM_INDEX			= 0xA,
+	IFS_SBAF_CORRUPTED_CHUNK			= 0xB,
+	IFS_SBAF_DID_NOT_START				= 0xC,
+};
+
+static const char * const sbaf_test_status[] = {
+	[IFS_SBAF_NO_ERROR] = "SBAF no error",
+	[IFS_SBAF_OTHER_THREAD_COULD_NOT_JOIN] = "Other thread could not join.",
+	[IFS_SBAF_INTERRUPTED_BEFORE_RENDEZVOUS] = "Interrupt occurred prior to SBAF coordination.",
+	[IFS_SBAF_UNASSIGNED_ERROR_CODE3] = "Unassigned error code 0x3",
+	[IFS_SBAF_INVALID_BUNDLE_INDEX] = "Non-valid sbaf bundles. Reload test image",
+	[IFS_SBAF_MISMATCH_ARGS_BETWEEN_THREADS] = "Mismatch in arguments between threads T0/T1.",
+	[IFS_SBAF_CORE_NOT_CAPABLE_CURRENTLY] = "Core not capable of performing SBAF currently",
+	[IFS_SBAF_UNASSIGNED_ERROR_CODE7] = "Unassigned error code 0x7",
+	[IFS_SBAF_EXCEED_NUMBER_OF_THREADS_CONCURRENT] = "Exceeded number of Logical Processors (LP) allowed to run Scan-At-Field concurrently",
+	[IFS_SBAF_INTERRUPTED_DURING_EXECUTION] = "Interrupt occurred prior to SBAF start",
+	[IFS_SBAF_INVALID_PROGRAM_INDEX] = "SBAF program index not valid",
+	[IFS_SBAF_CORRUPTED_CHUNK] = "SBAF operation aborted due to corrupted chunk",
+	[IFS_SBAF_DID_NOT_START] = "SBAF operation did not start",
+};
+
+static void sbaf_message_not_tested(struct device *dev, int cpu, u64 status_data)
+{
+	union ifs_sbaf_status status = (union ifs_sbaf_status)status_data;
+
+	if (status.error_code < ARRAY_SIZE(sbaf_test_status)) {
+		dev_info(dev, "CPU(s) %*pbl: SBAF operation did not start. %s\n",
+			 cpumask_pr_args(cpu_smt_mask(cpu)),
+			 sbaf_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 SBAF bundles executed. Maximum forward progress retries exceeded");
+	} else {
+		dev_info(dev, "CPU(s) %*pbl: SBAF unknown status %llx\n",
+			 cpumask_pr_args(cpu_smt_mask(cpu)), status.data);
+	}
+}
+
+static void sbaf_message_fail(struct device *dev, int cpu, union ifs_sbaf_status status)
+{
+	/* Failed signature check is set when SBAF signature did not match the expected value */
+	if (status.sbaf_status == SBAF_STATUS_SIGN_FAIL) {
+		dev_err(dev, "CPU(s) %*pbl: Failed signature check\n",
+			cpumask_pr_args(cpu_smt_mask(cpu)));
+	}
+
+	/* Failed to reach end of test */
+	if (status.sbaf_status == SBAF_STATUS_TEST_FAIL) {
+		dev_err(dev, "CPU(s) %*pbl: Failed to complete test\n",
+			cpumask_pr_args(cpu_smt_mask(cpu)));
+	}
+}
+
+static bool sbaf_bundle_completed(union ifs_sbaf_status status)
+{
+	return !(status.sbaf_status || status.error_code);
+}
+
+static bool sbaf_can_restart(union ifs_sbaf_status status)
+{
+	enum sbaf_status_err_code err_code = status.error_code;
+
+	/* Signature for chunk is bad, or scan test failed */
+	if (status.sbaf_status == SBAF_STATUS_SIGN_FAIL ||
+	    status.sbaf_status == SBAF_STATUS_TEST_FAIL)
+		return false;
+
+	switch (err_code) {
+	case IFS_SBAF_NO_ERROR:
+	case IFS_SBAF_OTHER_THREAD_COULD_NOT_JOIN:
+	case IFS_SBAF_INTERRUPTED_BEFORE_RENDEZVOUS:
+	case IFS_SBAF_EXCEED_NUMBER_OF_THREADS_CONCURRENT:
+	case IFS_SBAF_INTERRUPTED_DURING_EXECUTION:
+		return true;
+	case IFS_SBAF_UNASSIGNED_ERROR_CODE3:
+	case IFS_SBAF_INVALID_BUNDLE_INDEX:
+	case IFS_SBAF_MISMATCH_ARGS_BETWEEN_THREADS:
+	case IFS_SBAF_CORE_NOT_CAPABLE_CURRENTLY:
+	case IFS_SBAF_UNASSIGNED_ERROR_CODE7:
+	case IFS_SBAF_INVALID_PROGRAM_INDEX:
+	case IFS_SBAF_CORRUPTED_CHUNK:
+	case IFS_SBAF_DID_NOT_START:
+		break;
+	}
+	return false;
+}
+
+/*
+ * Execute the SBAF test. Called "simultaneously" on all threads of a core
+ * at high priority using the stop_cpus mechanism.
+ */
+static int dosbaf(void *data)
+{
+	struct sbaf_run_params *run_params = data;
+	int cpu = smp_processor_id();
+	union ifs_sbaf_status status;
+	struct ifs_data *ifsd;
+	int first;
+
+	ifsd = run_params->ifsd;
+
+	/* Only the first logical CPU on a core reports result */
+	first = cpumask_first(cpu_smt_mask(cpu));
+	wait_for_sibling_cpu(&sbaf_cpus_in, NSEC_PER_SEC);
+
+	/*
+	 * 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 bundle. The core test happens
+	 * during the "execution" of the WRMSR.
+	 */
+	wrmsrl(MSR_ACTIVATE_SBAF, run_params->activate->data);
+	rdmsrl(MSR_SBAF_STATUS, status.data);
+	trace_ifs_sbaf(ifsd->cur_batch, *run_params->activate, status);
+
+	/* Pass back the result of the test */
+	if (cpu == first)
+		run_params->status = status;
+
+	return 0;
+}
+
+static void ifs_sbaf_test_core(int cpu, struct device *dev)
+{
+	struct sbaf_run_params run_params;
+	union ifs_sbaf_status status = {};
+	union ifs_sbaf activate;
+	unsigned long timeout;
+	struct ifs_data *ifsd;
+	int stop_bundle;
+	int retries;
+
+	ifsd = ifs_get_data(dev);
+
+	activate.data = 0;
+	activate.delay = IFS_THREAD_WAIT;
+
+	timeout = jiffies + 2 * HZ;
+	retries = MAX_IFS_RETRIES;
+	activate.bundle_idx = 0;
+	stop_bundle = ifsd->max_bundle;
+
+	while (activate.bundle_idx <= stop_bundle) {
+		if (time_after(jiffies, timeout)) {
+			status.error_code = IFS_SW_TIMEOUT;
+			break;
+		}
+
+		atomic_set(&sbaf_cpus_in, 0);
+
+		run_params.ifsd = ifsd;
+		run_params.activate = &activate;
+		run_params.retry_cnt = &retries;
+		stop_core_cpuslocked(cpu, dosbaf, &run_params);
+
+		status = run_params.status;
+
+		if (sbaf_bundle_completed(status)) {
+			activate.bundle_idx = status.bundle_idx + 1;
+			activate.pgm_idx = 0;
+			retries = MAX_IFS_RETRIES;
+			continue;
+		}
+
+		/* Some cases can be retried, give up for others */
+		if (!sbaf_can_restart(status))
+			break;
+
+		if (status.pgm_idx == activate.pgm_idx) {
+			/* If no progress retry */
+			if (--retries == 0) {
+				if (status.error_code == IFS_NO_ERROR)
+					status.error_code = IFS_SW_PARTIAL_COMPLETION;
+				break;
+			}
+		} else {
+			/* if some progress, more pgms remaining in bundle, reset retries */
+			retries = MAX_IFS_RETRIES;
+			activate.bundle_idx = status.bundle_idx;
+			activate.pgm_idx = status.pgm_idx;
+		}
+	}
+
+	/* Update status for this core */
+	ifsd->scan_details = status.data;
+
+	if (status.sbaf_status == SBAF_STATUS_SIGN_FAIL ||
+	    status.sbaf_status == SBAF_STATUS_TEST_FAIL) {
+		ifsd->status = SCAN_TEST_FAIL;
+		sbaf_message_fail(dev, cpu, status);
+	} else if (status.error_code || status.sbaf_status == SBAF_STATUS_INTR ||
+		   (activate.bundle_idx < stop_bundle)) {
+		ifsd->status = SCAN_NOT_TESTED;
+		sbaf_message_not_tested(dev, cpu, status.data);
+	} 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
@@ -394,6 +647,12 @@ int do_core_test(int cpu, struct device *dev)
 		else
 			ifs_array_test_gen1(cpu, dev);
 		break;
+	case IFS_TYPE_SBAF:
+		if (!ifsd->loaded)
+			ret = -EPERM;
+		else
+			ifs_sbaf_test_core(cpu, dev);
+		break;
 	default:
 		ret = -EINVAL;
 	}