Merge tag 'drm-intel-gt-next-2023-04-06' of git://anongit.freedesktop.org/drm/drm-intel into drm-next

UAPI Changes:

- (Build-time only, should not have any impact)
  drm/i915/uapi: Replace fake flex-array with flexible-array member

  "Zero-length arrays as fake flexible arrays are deprecated and we are
  moving towards adopting C99 flexible-array members instead."

  This is on core kernel request moving towards GCC 13.

Driver Changes:

- Fix context runtime accounting on sysfs fdinfo for heavy workloads (Tvrtko)
- Add support for OA media units on MTL (Umesh)
- Add new workarounds for Meteorlake (Daniele, Radhakrishna, Haridhar)
- Fix sysfs to read actual frequency for MTL and Gen6 and earlier
  (Ashutosh)
- Synchronize i915/BIOS on C6 enabling on MTL (Vinay)
- Fix DMAR error noise due to GPU error capture (Andrej)
- Fix forcewake during BAR resize on discrete (Andrzej)
- Flush lmem contents after construction on discrete (Chris)
- Fix GuC loading timeout on systems where IFWI programs low boot
  frequency (John)
- Fix race condition UAF in i915_perf_add_config_ioctl (Min)

- Sanitycheck MMIO access early in driver load and during forcewake
  (Matt)
- Wakeref fixes for GuC RC error scenario and active VM tracking (Chris)
- Cancel HuC delayed load timer on reset (Daniele)
- Limit double GT reset to pre-MTL (Daniele)
- Use i915 instead of dev_priv insied the file_priv structure (Andi)
- Improve GuC load error reporting (John)
- Simplify VCS/BSD engine selection logic (Tvrtko)
- Perform uc late init after probe error injection (Andrzej)
- Fix format for perf_limit_reasons in debugfs (Vinay)
- Create per-gt debugfs files (Andi)

- Documentation and kerneldoc fixes (Nirmoy, Lee)
- Selftest improvements (Fei, Jonathan)

Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
From: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/ZC6APj/feB+jBf2d@jlahtine-mobl.ger.corp.intel.com

10 files changed, 161 insertions, 32 deletions

diff --git a/drivers/gpu/drm/i915/gt/uc/abi/guc_errors_abi.h b/drivers/gpu/drm/i915/gt/uc/abi/guc_errors_abi.h
index 8085fb181274..bcb1129b3610 100644
--- a/drivers/gpu/drm/i915/gt/uc/abi/guc_errors_abi.h
+++ b/drivers/gpu/drm/i915/gt/uc/abi/guc_errors_abi.h
@@ -21,6 +21,9 @@ enum intel_guc_load_status {
 	INTEL_GUC_LOAD_STATUS_ERROR_DEVID_BUILD_MISMATCH       = 0x02,
 	INTEL_GUC_LOAD_STATUS_GUC_PREPROD_BUILD_MISMATCH       = 0x03,
 	INTEL_GUC_LOAD_STATUS_ERROR_DEVID_INVALID_GUCTYPE      = 0x04,
+	INTEL_GUC_LOAD_STATUS_HWCONFIG_START                   = 0x05,
+	INTEL_GUC_LOAD_STATUS_HWCONFIG_DONE                    = 0x06,
+	INTEL_GUC_LOAD_STATUS_HWCONFIG_ERROR                   = 0x07,
 	INTEL_GUC_LOAD_STATUS_GDT_DONE                         = 0x10,
 	INTEL_GUC_LOAD_STATUS_IDT_DONE                         = 0x20,
 	INTEL_GUC_LOAD_STATUS_LAPIC_DONE                       = 0x30,
@@ -38,4 +41,18 @@ enum intel_guc_load_status {
 	INTEL_GUC_LOAD_STATUS_READY                            = 0xF0,
 };
 
+enum intel_bootrom_load_status {
+	INTEL_BOOTROM_STATUS_NO_KEY_FOUND                 = 0x13,
+	INTEL_BOOTROM_STATUS_AES_PROD_KEY_FOUND           = 0x1A,
+	INTEL_BOOTROM_STATUS_RSA_FAILED                   = 0x50,
+	INTEL_BOOTROM_STATUS_PAVPC_FAILED                 = 0x73,
+	INTEL_BOOTROM_STATUS_WOPCM_FAILED                 = 0x74,
+	INTEL_BOOTROM_STATUS_LOADLOC_FAILED               = 0x75,
+	INTEL_BOOTROM_STATUS_JUMP_PASSED                  = 0x76,
+	INTEL_BOOTROM_STATUS_JUMP_FAILED                  = 0x77,
+	INTEL_BOOTROM_STATUS_RC6CTXCONFIG_FAILED          = 0x79,
+	INTEL_BOOTROM_STATUS_MPUMAP_INCORRECT             = 0x7A,
+	INTEL_BOOTROM_STATUS_EXCEPTION                    = 0x7E,
+};
+
 #endif /* _ABI_GUC_ERRORS_ABI_H */
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_gsc_fw.h b/drivers/gpu/drm/i915/gt/uc/intel_gsc_fw.h
index 4b5dbb44afb4..f4c1106bb2a9 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_gsc_fw.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_gsc_fw.h
@@ -9,7 +9,9 @@
 #include <linux/types.h>
 
 struct intel_gsc_uc;
+struct intel_uncore;
 
 int intel_gsc_uc_fw_upload(struct intel_gsc_uc *gsc);
 bool intel_gsc_uc_fw_init_done(struct intel_gsc_uc *gsc);
+
 #endif
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
index bb4dfe707a7d..e46aac1a41e6 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
@@ -42,6 +42,8 @@ struct intel_guc {
 	/** @capture: the error-state-capture module's data and objects */
 	struct intel_guc_state_capture *capture;
 
+	struct dentry *dbgfs_node;
+
 	/** @sched_engine: Global engine used to submit requests to GuC */
 	struct i915_sched_engine *sched_engine;
 	/**
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c
index 69133420c78b..6fda3aec5c66 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c
@@ -12,6 +12,7 @@
 #include "gt/intel_gt.h"
 #include "gt/intel_gt_mcr.h"
 #include "gt/intel_gt_regs.h"
+#include "gt/intel_rps.h"
 #include "intel_guc_fw.h"
 #include "intel_guc_print.h"
 #include "i915_drv.h"
@@ -88,31 +89,80 @@ static int guc_xfer_rsa(struct intel_uc_fw *guc_fw,
 /*
  * Read the GuC status register (GUC_STATUS) and store it in the
  * specified location; then return a boolean indicating whether
- * the value matches either of two values representing completion
- * of the GuC boot process.
+ * the value matches either completion or a known failure code.
  *
  * This is used for polling the GuC status in a wait_for()
  * loop below.
  */
-static inline bool guc_ready(struct intel_uncore *uncore, u32 *status)
+static inline bool guc_load_done(struct intel_uncore *uncore, u32 *status, bool *success)
 {
 	u32 val = intel_uncore_read(uncore, GUC_STATUS);
 	u32 uk_val = REG_FIELD_GET(GS_UKERNEL_MASK, val);
+	u32 br_val = REG_FIELD_GET(GS_BOOTROM_MASK, val);
 
 	*status = val;
-	return uk_val == INTEL_GUC_LOAD_STATUS_READY;
+	switch (uk_val) {
+	case INTEL_GUC_LOAD_STATUS_READY:
+		*success = true;
+		return true;
+
+	case INTEL_GUC_LOAD_STATUS_ERROR_DEVID_BUILD_MISMATCH:
+	case INTEL_GUC_LOAD_STATUS_GUC_PREPROD_BUILD_MISMATCH:
+	case INTEL_GUC_LOAD_STATUS_ERROR_DEVID_INVALID_GUCTYPE:
+	case INTEL_GUC_LOAD_STATUS_HWCONFIG_ERROR:
+	case INTEL_GUC_LOAD_STATUS_DPC_ERROR:
+	case INTEL_GUC_LOAD_STATUS_EXCEPTION:
+	case INTEL_GUC_LOAD_STATUS_INIT_DATA_INVALID:
+	case INTEL_GUC_LOAD_STATUS_MPU_DATA_INVALID:
+	case INTEL_GUC_LOAD_STATUS_INIT_MMIO_SAVE_RESTORE_INVALID:
+		*success = false;
+		return true;
+	}
+
+	switch (br_val) {
+	case INTEL_BOOTROM_STATUS_NO_KEY_FOUND:
+	case INTEL_BOOTROM_STATUS_RSA_FAILED:
+	case INTEL_BOOTROM_STATUS_PAVPC_FAILED:
+	case INTEL_BOOTROM_STATUS_WOPCM_FAILED:
+	case INTEL_BOOTROM_STATUS_LOADLOC_FAILED:
+	case INTEL_BOOTROM_STATUS_JUMP_FAILED:
+	case INTEL_BOOTROM_STATUS_RC6CTXCONFIG_FAILED:
+	case INTEL_BOOTROM_STATUS_MPUMAP_INCORRECT:
+	case INTEL_BOOTROM_STATUS_EXCEPTION:
+		*success = false;
+		return true;
+	}
+
+	return false;
 }
 
+/*
+ * Use a longer timeout for debug builds so that problems can be detected
+ * and analysed. But a shorter timeout for releases so that user's don't
+ * wait forever to find out there is a problem. Note that the only reason
+ * an end user should hit the timeout is in case of extreme thermal throttling.
+ * And a system that is that hot during boot is probably dead anyway!
+ */
+#if defined(CONFIG_DRM_I915_DEBUG_GEM)
+#define GUC_LOAD_RETRY_LIMIT	20
+#else
+#define GUC_LOAD_RETRY_LIMIT	3
+#endif
+
 static int guc_wait_ucode(struct intel_guc *guc)
 {
 	struct intel_gt *gt = guc_to_gt(guc);
 	struct intel_uncore *uncore = gt->uncore;
+	ktime_t before, after, delta;
+	bool success;
 	u32 status;
-	int ret;
+	int ret, count;
+	u64 delta_ms;
+	u32 before_freq;
 
 	/*
 	 * Wait for the GuC to start up.
-	 * NB: Docs recommend not using the interrupt for completion.
+	 *
 	 * Measurements indicate this should take no more than 20ms
 	 * (assuming the GT clock is at maximum frequency). So, a
 	 * timeout here indicates that the GuC has failed and is unusable.
@@ -126,29 +176,80 @@ static int guc_wait_ucode(struct intel_guc *guc)
 	 * issues to be resolved. In the meantime bump the timeout to
 	 * 200ms. Even at slowest clock, this should be sufficient. And
 	 * in the working case, a larger timeout makes no difference.
+	 *
+	 * IFWI updates have also been seen to cause sporadic failures due to
+	 * the requested frequency not being granted and thus the firmware
+	 * load is attempted at minimum frequency. That can lead to load times
+	 * in the seconds range. However, there is a limit on how long an
+	 * individual wait_for() can wait. So wrap it in a loop.
 	 */
-	ret = wait_for(guc_ready(uncore, &status), 200);
-	if (ret) {
-		guc_info(guc, "load failed: status = 0x%08X\n", status);
-		guc_info(guc, "load failed: status: Reset = %d, "
-			"BootROM = 0x%02X, UKernel = 0x%02X, "
-			"MIA = 0x%02X, Auth = 0x%02X\n",
-			REG_FIELD_GET(GS_MIA_IN_RESET, status),
-			REG_FIELD_GET(GS_BOOTROM_MASK, status),
-			REG_FIELD_GET(GS_UKERNEL_MASK, status),
-			REG_FIELD_GET(GS_MIA_MASK, status),
-			REG_FIELD_GET(GS_AUTH_STATUS_MASK, status));
-
-		if ((status & GS_BOOTROM_MASK) == GS_BOOTROM_RSA_FAILED) {
+	before_freq = intel_rps_read_actual_frequency(&uncore->gt->rps);
+	before = ktime_get();
+	for (count = 0; count < GUC_LOAD_RETRY_LIMIT; count++) {
+		ret = wait_for(guc_load_done(uncore, &status, &success), 1000);
+		if (!ret || !success)
+			break;
+
+		guc_dbg(guc, "load still in progress, count = %d, freq = %dMHz\n",
+			count, intel_rps_read_actual_frequency(&uncore->gt->rps));
+	}
+	after = ktime_get();
+	delta = ktime_sub(after, before);
+	delta_ms = ktime_to_ms(delta);
+	if (ret || !success) {
+		u32 ukernel = REG_FIELD_GET(GS_UKERNEL_MASK, status);
+		u32 bootrom = REG_FIELD_GET(GS_BOOTROM_MASK, status);
+
+		guc_info(guc, "load failed: status = 0x%08X, time = %lldms, freq = %dMHz, ret = %d\n",
+			 status, delta_ms, intel_rps_read_actual_frequency(&uncore->gt->rps), ret);
+		guc_info(guc, "load failed: status: Reset = %d, BootROM = 0x%02X, UKernel = 0x%02X, MIA = 0x%02X, Auth = 0x%02X\n",
+			 REG_FIELD_GET(GS_MIA_IN_RESET, status),
+			 bootrom, ukernel,
+			 REG_FIELD_GET(GS_MIA_MASK, status),
+			 REG_FIELD_GET(GS_AUTH_STATUS_MASK, status));
+
+		switch (bootrom) {
+		case INTEL_BOOTROM_STATUS_NO_KEY_FOUND:
+			guc_info(guc, "invalid key requested, header = 0x%08X\n",
+				 intel_uncore_read(uncore, GUC_HEADER_INFO));
+			ret = -ENOEXEC;
+			break;
+
+		case INTEL_BOOTROM_STATUS_RSA_FAILED:
 			guc_info(guc, "firmware signature verification failed\n");
 			ret = -ENOEXEC;
+			break;
 		}
 
-		if (REG_FIELD_GET(GS_UKERNEL_MASK, status) == INTEL_GUC_LOAD_STATUS_EXCEPTION) {
+		switch (ukernel) {
+		case INTEL_GUC_LOAD_STATUS_EXCEPTION:
 			guc_info(guc, "firmware exception. EIP: %#x\n",
 				 intel_uncore_read(uncore, SOFT_SCRATCH(13)));
 			ret = -ENXIO;
+			break;
+
+		case INTEL_GUC_LOAD_STATUS_INIT_MMIO_SAVE_RESTORE_INVALID:
+			guc_info(guc, "illegal register in save/restore workaround list\n");
+			ret = -EPERM;
+			break;
+
+		case INTEL_GUC_LOAD_STATUS_HWCONFIG_START:
+			guc_info(guc, "still extracting hwconfig table.\n");
+			ret = -ETIMEDOUT;
+			break;
 		}
+
+		/* Uncommon/unexpected error, see earlier status code print for details */
+		if (ret == 0)
+			ret = -ENXIO;
+	} else if (delta_ms > 200) {
+		guc_warn(guc, "excessive init time: %lldms! [freq = %dMHz, before = %dMHz, status = 0x%08X, count = %d, ret = %d]\n",
+			 delta_ms, intel_rps_read_actual_frequency(&uncore->gt->rps),
+			 before_freq, status, count, ret);
+	} else {
+		guc_dbg(guc, "init took %lldms, freq = %dMHz, before = %dMHz, status = 0x%08X, count = %d, ret = %d\n",
+			delta_ms, intel_rps_read_actual_frequency(&uncore->gt->rps),
+			before_freq, status, count, ret);
 	}
 
 	return ret;
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_hwconfig.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_hwconfig.c
index 4781fccc2687..852bea0208ce 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_hwconfig.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_hwconfig.c
@@ -102,7 +102,7 @@ static bool has_table(struct drm_i915_private *i915)
 	return false;
 }
 
-/**
+/*
  * intel_guc_hwconfig_init - Initialize the HWConfig
  *
  * Retrieve the HWConfig table from the GuC and save it locally.
@@ -136,7 +136,7 @@ static int guc_hwconfig_init(struct intel_gt *gt)
 	return 0;
 }
 
-/**
+/*
  * intel_gt_init_hwconfig - Initialize the HWConfig if available
  *
  * Retrieve the HWConfig table if available on the current platform.
@@ -149,7 +149,7 @@ int intel_gt_init_hwconfig(struct intel_gt *gt)
 	return guc_hwconfig_init(gt);
 }
 
-/**
+/*
  * intel_gt_fini_hwconfig - Finalize the HWConfig
  *
  * Free up the memory allocation holding the table.
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c
index 195db8c9d420..55bc8b55fbc0 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c
@@ -542,8 +542,11 @@ static int guc_log_relay_create(struct intel_guc_log *log)
 	 */
 	n_subbufs = 8;
 
+	if (!guc->dbgfs_node)
+		return -ENOENT;
+
 	guc_log_relay_chan = relay_open("guc_log",
-					i915->drm.primary->debugfs_root,
+					guc->dbgfs_node,
 					subbuf_size, n_subbufs,
 					&relay_callbacks, i915);
 	if (!guc_log_relay_chan) {
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_reg.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_reg.h
index 9915de32e894..3fd798837502 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_reg.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_reg.h
@@ -18,8 +18,6 @@
 #define   GS_MIA_IN_RESET		  (0x01 << GS_RESET_SHIFT)
 #define   GS_BOOTROM_SHIFT		1
 #define   GS_BOOTROM_MASK		  (0x7F << GS_BOOTROM_SHIFT)
-#define   GS_BOOTROM_RSA_FAILED		  (0x50 << GS_BOOTROM_SHIFT)
-#define   GS_BOOTROM_JUMP_PASSED	  (0x76 << GS_BOOTROM_SHIFT)
 #define   GS_UKERNEL_SHIFT		8
 #define   GS_UKERNEL_MASK		  (0xFF << GS_UKERNEL_SHIFT)
 #define   GS_MIA_SHIFT			16
@@ -32,6 +30,8 @@
 #define   GS_AUTH_STATUS_BAD		  (0x01 << GS_AUTH_STATUS_SHIFT)
 #define   GS_AUTH_STATUS_GOOD		  (0x02 << GS_AUTH_STATUS_SHIFT)
 
+#define GUC_HEADER_INFO			_MMIO(0xc014)
+
 #define SOFT_SCRATCH(n)			_MMIO(0xc180 + (n) * 4)
 #define SOFT_SCRATCH_COUNT		16
 
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc.c b/drivers/gpu/drm/i915/gt/uc/intel_huc.c
index 72884e21470b..aefdaa62da99 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_huc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_huc.c
@@ -241,6 +241,13 @@ static void delayed_huc_load_fini(struct intel_huc *huc)
 	i915_sw_fence_fini(&huc->delayed_load.fence);
 }
 
+int intel_huc_sanitize(struct intel_huc *huc)
+{
+	delayed_huc_load_complete(huc);
+	intel_uc_fw_sanitize(&huc->fw);
+	return 0;
+}
+
 static bool vcs_supported(struct intel_gt *gt)
 {
 	intel_engine_mask_t mask = gt->info.engine_mask;
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc.h b/drivers/gpu/drm/i915/gt/uc/intel_huc.h
index 52db03620c60..db555b3c1f56 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_huc.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_huc.h
@@ -41,6 +41,7 @@ struct intel_huc {
 	} delayed_load;
 };
 
+int intel_huc_sanitize(struct intel_huc *huc);
 void intel_huc_init_early(struct intel_huc *huc);
 int intel_huc_init(struct intel_huc *huc);
 void intel_huc_fini(struct intel_huc *huc);
@@ -54,12 +55,6 @@ bool intel_huc_is_authenticated(struct intel_huc *huc);
 void intel_huc_register_gsc_notifier(struct intel_huc *huc, struct bus_type *bus);
 void intel_huc_unregister_gsc_notifier(struct intel_huc *huc, struct bus_type *bus);
 
-static inline int intel_huc_sanitize(struct intel_huc *huc)
-{
-	intel_uc_fw_sanitize(&huc->fw);
-	return 0;
-}
-
 static inline bool intel_huc_is_supported(struct intel_huc *huc)
 {
 	return intel_uc_fw_is_supported(&huc->fw);
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_debugfs.c b/drivers/gpu/drm/i915/gt/uc/intel_uc_debugfs.c
index 284d6fbc2d08..2f93cc4e408a 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc_debugfs.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_debugfs.c
@@ -54,6 +54,8 @@ void intel_uc_debugfs_register(struct intel_uc *uc, struct dentry *gt_root)
 	if (IS_ERR(root))
 		return;
 
+	uc->guc.dbgfs_node = root;
+
 	intel_gt_debugfs_register_files(root, files, ARRAY_SIZE(files), uc);
 
 	intel_guc_debugfs_register(&uc->guc, root);