Merge tag 'drm-xe-next-2024-10-10' of https://gitlab.freedesktop.org/drm/xe/kernel into drm-next

Cross-subsystem Changes:
- Add drm_line_printer (Michal)

Driver Changes:
- Fix an UAF (Matt Auld)
- Sanity check compression and coherency mode (Matt Auld)
- Some PIC-ID work (Jani)
- Use IS_ENABLED() instead of defined() on config options.
- gt powergating work (Riana)
- Suppress missing out ter rpm protection warning (Rodrigo)
- Fix a vm leak  (Dafna)
- Clean up and update 'has_flat_ccs' handling (Lucas)
- Fix arg to pci_iomap (Lucas)
- Mark reserved engines in shapshot (Lucas)
- Don't keep stale pointer (Michal)
- Fix build warning with CONFIG_PM=n (Arnd)
- Add a xe_bo subtest for shrinking / swapping (Thomas)
- Add a warkaround (Tejas)
- Some display PM work (Maarten)
- Enable Xe2 + PES disaggregation (Ashutosh)
- Large xe_mmio rework / cleanup (Matt Roper)
- A couple of fixes / cleanups in the xe client code (Matt Auld)
- Fix page-fault handling on closed VMs  (Matt Brost)
- Fix overflow in OA batch buffer (José)
- Style fixes (Lucas, Jiapeng, Nitin)
- Fixes and new development around SRIOV (Michal)
- Use devm_add_action_or_reset() in gt code (He)
- Fix CCS offset calculation (Matt Auld)
- Remove i915_drv.h include (Rodrigo)
- Restore PCI state on resume (Rodrigo)
- Fix DSB buffer coherency / Revert DSB disabling (Maarten / Animesh)
- Convert USM lock to rwsem (Matt Brost)
- Defer gt-mmio intialization (Matt Roper)
- meemirq changes (Ilia)
- Move some PVC related code out of xe-for-CI and to the driver (Rodrigo / Jani)
- Use a helper for ASID->VM lookup (Matt Brost)
- Add new PCI id for ARL (Dnyaneshwar)
- Use Xe2_LPM steering tables for Xe2_HPM (Gustavo)
- Performance tuning work for media GT and L3 cache flushing (Gustavo)
- Clean up VM- and exec queue file lock usage (Matt Brost)
- GuC locking fix (Matt Auld)
- Fix UAF around queue destruction (Matt Auld)
- Move IRQ-related registers to dedicated header (Matt Roper)
- Resume TDR after GT reset (Matt Brost)
- Move xa_alloc to prevent UAF (Matt Auld)
- Fix OA stream close (José)
- Remove unused i915_gpu_error.h (Jani)
- Prevent null pointer access in xe_migrate_copy (Zhanjun)
- Fix memory leak when aborting binds (Matt Brost)
- Prevent UAF in send_recv() (Matt Auld)
- Fix xa_store() error checking (Matt Auld)
- drop irq disabling around xa_erase in guc code (Matt Auld)
- Use fault injection infrastructure to find issues as probe time (Francois)
- Fix a workaround implementation. (Vinay)
- Mark wedged_mode debugfs writable (Matt Roper)
- Fix for prviewous memirq work (Michal)
- More SRIOV work (Michal)
- Devcoredump work (John)
- GuC logging + devcoredump support (John)
- Don't report L3 bank availability on PTL (Shekhar)
- Replicate Xe2 PAT settings on Xe2 (Matt Roper)
- Define Xe3 feature flags (Haridhar)
- Reuse Xe2 MOCS table on on PTL (Haridhar)
- Add PTL platform definition (Haridhar)
- Add MCR steering for Xe3 (Matt)
- More work around GuC capture for devcoredump (Zhanjun)
- Improve cache flushing behaviour on bmg (Matt Auld)
- Fix shrinker test compiler warnings on 32-bit (Thomas)
- Initial set of workarounds for Xe3 (Gustavo)
- Extend workaround for xe2lpg (Aradhya)
- Fix unbalanced rpm put x 2 (Matt Auld)

Signed-off-by: Dave Airlie <[email protected]>

# -----BEGIN PGP SIGNATURE-----
#
# iHUEABYKAB0WIQRskUM7w1oG5rx2IZO4FpNVCsYGvwUCZwekBwAKCRC4FpNVCsYG
# v32oAQDnIKVwjZecI1V3oUsy2ZE3TKWx8HH4FweT6S5L6tqZwQD/b0vkeA3UaojO
# 5FIkPEqyHFbrj+Sw7bLonLb3LHv4WAE=
# =FtY6
# -----END PGP SIGNATURE-----
# gpg: Signature made Thu 10 Oct 2024 19:53:11 AEST
# gpg:                using EDDSA key 6C91433BC35A06E6BC762193B81693550AC606BF
# gpg: Can't check signature: No public key

# Conflicts:
#	drivers/gpu/drm/xe/xe_gt_mcr.c
#	drivers/gpu/drm/xe/xe_tuning.c
From: Thomas Hellstrom <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/Zwekwrak12c5SSgo@fedora

Author: airlied

drivers/gpu/drm/drm_print.c

@@ -235,6 +235,20 @@ void __drm_printfn_err(struct drm_printer *p, struct va_format *vaf)
 }
 EXPORT_SYMBOL(__drm_printfn_err);
 
+void __drm_printfn_line(struct drm_printer *p, struct va_format *vaf)
+{
+	unsigned int counter = ++p->line.counter;
+	const char *prefix = p->prefix ?: "";
+	const char *pad = p->prefix ? " " : "";
+
+	if (p->line.series)
+		drm_printf(p->arg, "%s%s%u.%u: %pV",
+			   prefix, pad, p->line.series, counter, vaf);
+	else
+		drm_printf(p->arg, "%s%s%u: %pV", prefix, pad, counter, vaf);
+}
+EXPORT_SYMBOL(__drm_printfn_line);
+
 /**
  * drm_puts - print a const string to a &drm_printer stream
  * @p: the &drm printer

drivers/gpu/drm/i915/display/intel_dsb.c

@@ -706,10 +706,6 @@ struct intel_dsb *intel_dsb_prepare(struct intel_atomic_state *state,
 	if (!i915->display.params.enable_dsb)
 		return NULL;
 
-	/* TODO: DSB is broken in Xe KMD, so disabling it until fixed */
-	if (!IS_ENABLED(I915))
-		return NULL;
-
 	dsb = kzalloc(sizeof(*dsb), GFP_KERNEL);
 	if (!dsb)
 		goto out;

drivers/gpu/drm/xe/Kconfig.debug

@@ -40,9 +40,21 @@ config DRM_XE_DEBUG_VM
 
 	  If in doubt, say "N".
 
+config DRM_XE_DEBUG_MEMIRQ
+	bool "Enable extra memirq debugging"
+	default n
+	help
+	  Choose this option to enable additional debugging info for
+	  memory based interrupts.
+
+	  Recommended for driver developers only.
+
+	  If in doubt, say "N".
+
 config DRM_XE_DEBUG_SRIOV
 	bool "Enable extra SR-IOV debugging"
 	default n
+	select DRM_XE_DEBUG_MEMIRQ
 	help
 	  Enable extra SR-IOV debugging info.
 

drivers/gpu/drm/xe/Makefile

@@ -56,6 +56,7 @@ xe-y += xe_bb.o \
 	xe_gt_topology.o \
 	xe_guc.o \
 	xe_guc_ads.o \
+	xe_guc_capture.o \
 	xe_guc_ct.o \
 	xe_guc_db_mgr.o \
 	xe_guc_hwconfig.o \
@@ -129,6 +130,7 @@ xe-$(CONFIG_PCI_IOV) += \
 	xe_gt_sriov_pf.o \
 	xe_gt_sriov_pf_config.o \
 	xe_gt_sriov_pf_control.o \
+	xe_gt_sriov_pf_migration.o \
 	xe_gt_sriov_pf_monitor.o \
 	xe_gt_sriov_pf_policy.o \
 	xe_gt_sriov_pf_service.o \

drivers/gpu/drm/xe/abi/guc_actions_abi.h

@@ -176,6 +176,14 @@ enum xe_guc_sleep_state_status {
 #define GUC_LOG_CONTROL_VERBOSITY_MASK	(0xF << GUC_LOG_CONTROL_VERBOSITY_SHIFT)
 #define GUC_LOG_CONTROL_DEFAULT_LOGGING	(1 << 8)
 
+enum xe_guc_state_capture_event_status {
+	XE_GUC_STATE_CAPTURE_EVENT_STATUS_SUCCESS = 0x0,
+	XE_GUC_STATE_CAPTURE_EVENT_STATUS_NOSPACE = 0x1,
+};
+
+#define XE_GUC_STATE_CAPTURE_EVENT_STATUS_MASK      0x000000FF
+#define XE_GUC_ACTION_STATE_CAPTURE_NOTIFICATION_DATA_LEN 1
+
 #define XE_GUC_TLB_INVAL_TYPE_SHIFT 0
 #define XE_GUC_TLB_INVAL_MODE_SHIFT 8
 /* Flush PPC or SMRO caches along with TLB invalidation request */

drivers/gpu/drm/xe/abi/guc_actions_sriov_abi.h

@@ -557,4 +557,65 @@
 #define VF2GUC_QUERY_SINGLE_KLV_RESPONSE_MSG_2_VALUE64	GUC_HXG_REQUEST_MSG_n_DATAn
 #define VF2GUC_QUERY_SINGLE_KLV_RESPONSE_MSG_3_VALUE96	GUC_HXG_REQUEST_MSG_n_DATAn
 
+/**
+ * DOC: PF2GUC_SAVE_RESTORE_VF
+ *
+ * This message is used by the PF to migrate VF info state maintained by the GuC.
+ *
+ * This message must be sent as `CTB HXG Message`_.
+ *
+ * Available since GuC version 70.25.0
+ *
+ *  +---+-------+--------------------------------------------------------------+
+ *  |   | Bits  | Description                                                  |
+ *  +===+=======+==============================================================+
+ *  | 0 |    31 | ORIGIN = GUC_HXG_ORIGIN_HOST_                                |
+ *  |   +-------+--------------------------------------------------------------+
+ *  |   | 30:28 | TYPE = GUC_HXG_TYPE_REQUEST_                                 |
+ *  |   +-------+--------------------------------------------------------------+
+ *  |   | 27:16 | DATA0 = **OPCODE** - operation to take:                      |
+ *  |   |       |                                                              |
+ *  |   |       |   - _`GUC_PF_OPCODE_VF_SAVE` = 0                             |
+ *  |   |       |   - _`GUC_PF_OPCODE_VF_RESTORE` = 1                          |
+ *  |   +-------+--------------------------------------------------------------+
+ *  |   |  15:0 | ACTION = _`GUC_ACTION_PF2GUC_SAVE_RESTORE_VF` = 0x550B       |
+ *  +---+-------+--------------------------------------------------------------+
+ *  | 1 |  31:0 | **VFID** - VF identifier                                     |
+ *  +---+-------+--------------------------------------------------------------+
+ *  | 2 |  31:0 | **ADDR_LO** - lower 32-bits of GGTT offset to the buffer     |
+ *  |   |       | where the VF info will be save to or restored from.          |
+ *  +---+-------+--------------------------------------------------------------+
+ *  | 3 |  31:0 | **ADDR_HI** - upper 32-bits of GGTT offset to the buffer     |
+ *  |   |       | where the VF info will be save to or restored from.          |
+ *  +---+-------+--------------------------------------------------------------+
+ *  | 4 |  27:0 | **SIZE** - size of the buffer (in dwords)                    |
+ *  |   +-------+--------------------------------------------------------------+
+ *  |   | 31:28 | MBZ                                                          |
+ *  +---+-------+--------------------------------------------------------------+
+ *
+ *  +---+-------+--------------------------------------------------------------+
+ *  |   | Bits  | Description                                                  |
+ *  +===+=======+==============================================================+
+ *  | 0 |    31 | ORIGIN = GUC_HXG_ORIGIN_GUC_                                 |
+ *  |   +-------+--------------------------------------------------------------+
+ *  |   | 30:28 | TYPE = GUC_HXG_TYPE_RESPONSE_SUCCESS_                        |
+ *  |   +-------+--------------------------------------------------------------+
+ *  |   |  27:0 | DATA0 = **USED** - size of used buffer space (in dwords)     |
+ *  +---+-------+--------------------------------------------------------------+
+ */
+#define GUC_ACTION_PF2GUC_SAVE_RESTORE_VF		0x550Bu
+
+#define PF2GUC_SAVE_RESTORE_VF_REQUEST_MSG_LEN		(GUC_HXG_EVENT_MSG_MIN_LEN + 4u)
+#define PF2GUC_SAVE_RESTORE_VF_REQUEST_MSG_0_OPCODE	GUC_HXG_EVENT_MSG_0_DATA0
+#define   GUC_PF_OPCODE_VF_SAVE				0u
+#define   GUC_PF_OPCODE_VF_RESTORE			1u
+#define PF2GUC_SAVE_RESTORE_VF_REQUEST_MSG_1_VFID	GUC_HXG_EVENT_MSG_n_DATAn
+#define PF2GUC_SAVE_RESTORE_VF_REQUEST_MSG_2_ADDR_LO	GUC_HXG_EVENT_MSG_n_DATAn
+#define PF2GUC_SAVE_RESTORE_VF_REQUEST_MSG_3_ADDR_HI	GUC_HXG_EVENT_MSG_n_DATAn
+#define PF2GUC_SAVE_RESTORE_VF_REQUEST_MSG_4_SIZE	(0xfffffffu << 0)
+#define PF2GUC_SAVE_RESTORE_VF_REQUEST_MSG_4_MBZ	(0xfu << 28)
+
+#define PF2GUC_SAVE_RESTORE_VF_RESPONSE_MSG_LEN		GUC_HXG_RESPONSE_MSG_MIN_LEN
+#define PF2GUC_SAVE_RESTORE_VF_RESPONSE_MSG_0_USED	GUC_HXG_RESPONSE_MSG_0_DATA0
+
 #endif

drivers/gpu/drm/xe/abi/guc_capture_abi.h

@@ -0,0 +1,186 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2024 Intel Corporation
+ */
+
+#ifndef _ABI_GUC_CAPTURE_ABI_H
+#define _ABI_GUC_CAPTURE_ABI_H
+
+#include <linux/types.h>
+
+/* Capture List Index */
+enum guc_capture_list_index_type {
+	GUC_CAPTURE_LIST_INDEX_PF = 0,
+	GUC_CAPTURE_LIST_INDEX_VF = 1,
+};
+
+#define GUC_CAPTURE_LIST_INDEX_MAX	(GUC_CAPTURE_LIST_INDEX_VF + 1)
+
+/* Register-types of GuC capture register lists */
+enum guc_state_capture_type {
+	GUC_STATE_CAPTURE_TYPE_GLOBAL = 0,
+	GUC_STATE_CAPTURE_TYPE_ENGINE_CLASS,
+	GUC_STATE_CAPTURE_TYPE_ENGINE_INSTANCE
+};
+
+#define GUC_STATE_CAPTURE_TYPE_MAX	(GUC_STATE_CAPTURE_TYPE_ENGINE_INSTANCE + 1)
+
+/* Class indecies for capture_class and capture_instance arrays */
+enum guc_capture_list_class_type {
+	GUC_CAPTURE_LIST_CLASS_RENDER_COMPUTE = 0,
+	GUC_CAPTURE_LIST_CLASS_VIDEO = 1,
+	GUC_CAPTURE_LIST_CLASS_VIDEOENHANCE = 2,
+	GUC_CAPTURE_LIST_CLASS_BLITTER = 3,
+	GUC_CAPTURE_LIST_CLASS_GSC_OTHER = 4,
+};
+
+#define GUC_CAPTURE_LIST_CLASS_MAX	(GUC_CAPTURE_LIST_CLASS_GSC_OTHER + 1)
+
+/**
+ * struct guc_mmio_reg - GuC MMIO reg state struct
+ *
+ * GuC MMIO reg state struct
+ */
+struct guc_mmio_reg {
+	/** @offset: MMIO Offset - filled in by Host */
+	u32 offset;
+	/** @value: MMIO Value - Used by Firmware to store value */
+	u32 value;
+	/** @flags: Flags for accessing the MMIO */
+	u32 flags;
+	/** @mask: Value of a mask to apply if mask with value is set */
+	u32 mask;
+#define GUC_REGSET_MASKED		BIT(0)
+#define GUC_REGSET_STEERING_NEEDED	BIT(1)
+#define GUC_REGSET_MASKED_WITH_VALUE	BIT(2)
+#define GUC_REGSET_RESTORE_ONLY		BIT(3)
+#define GUC_REGSET_STEERING_GROUP       GENMASK(16, 12)
+#define GUC_REGSET_STEERING_INSTANCE    GENMASK(23, 20)
+} __packed;
+
+/**
+ * struct guc_mmio_reg_set - GuC register sets
+ *
+ * GuC register sets
+ */
+struct guc_mmio_reg_set {
+	/** @address: register address */
+	u32 address;
+	/** @count: register count */
+	u16 count;
+	/** @reserved: reserved */
+	u16 reserved;
+} __packed;
+
+/**
+ * struct guc_debug_capture_list_header - Debug capture list header.
+ *
+ * Debug capture list header.
+ */
+struct guc_debug_capture_list_header {
+	/** @info: contains number of MMIO descriptors in the capture list. */
+	u32 info;
+#define GUC_CAPTURELISTHDR_NUMDESCR GENMASK(15, 0)
+} __packed;
+
+/**
+ * struct guc_debug_capture_list - Debug capture list
+ *
+ * As part of ADS registration, these header structures (followed by
+ * an array of 'struct guc_mmio_reg' entries) are used to register with
+ * GuC microkernel the list of registers we want it to dump out prior
+ * to a engine reset.
+ */
+struct guc_debug_capture_list {
+	/** @header: Debug capture list header. */
+	struct guc_debug_capture_list_header header;
+	/** @regs: MMIO descriptors in the capture list. */
+	struct guc_mmio_reg regs[];
+} __packed;
+
+/**
+ * struct guc_state_capture_header_t - State capture header.
+ *
+ * Prior to resetting engines that have hung or faulted, GuC microkernel
+ * reports the engine error-state (register values that was read) by
+ * logging them into the shared GuC log buffer using these hierarchy
+ * of structures.
+ */
+struct guc_state_capture_header_t {
+	/**
+	 * @owner: VFID
+	 * BR[ 7: 0] MBZ when SRIOV is disabled. When SRIOV is enabled
+	 * VFID is an integer in range [0, 63] where 0 means the state capture
+	 * is corresponding to the PF and an integer N in range [1, 63] means
+	 * the state capture is for VF N.
+	 */
+	u32 owner;
+#define GUC_STATE_CAPTURE_HEADER_VFID GENMASK(7, 0)
+	/** @info: Engine class/instance and capture type info */
+	u32 info;
+#define GUC_STATE_CAPTURE_HEADER_CAPTURE_TYPE GENMASK(3, 0) /* see guc_state_capture_type */
+#define GUC_STATE_CAPTURE_HEADER_ENGINE_CLASS GENMASK(7, 4) /* see guc_capture_list_class_type */
+#define GUC_STATE_CAPTURE_HEADER_ENGINE_INSTANCE GENMASK(11, 8)
+	/**
+	 * @lrca: logical ring context address.
+	 * if type-instance, LRCA (address) that hung, else set to ~0
+	 */
+	u32 lrca;
+	/**
+	 * @guc_id: context_index.
+	 * if type-instance, context index of hung context, else set to ~0
+	 */
+	u32 guc_id;
+	/** @num_mmio_entries: Number of captured MMIO entries. */
+	u32 num_mmio_entries;
+#define GUC_STATE_CAPTURE_HEADER_NUM_MMIO_ENTRIES GENMASK(9, 0)
+} __packed;
+
+/**
+ * struct guc_state_capture_t - State capture.
+ *
+ * State capture
+ */
+struct guc_state_capture_t {
+	/** @header: State capture header. */
+	struct guc_state_capture_header_t header;
+	/** @mmio_entries: Array of captured guc_mmio_reg entries. */
+	struct guc_mmio_reg mmio_entries[];
+} __packed;
+
+/* State Capture Group Type */
+enum guc_state_capture_group_type {
+	GUC_STATE_CAPTURE_GROUP_TYPE_FULL = 0,
+	GUC_STATE_CAPTURE_GROUP_TYPE_PARTIAL
+};
+
+#define GUC_STATE_CAPTURE_GROUP_TYPE_MAX (GUC_STATE_CAPTURE_GROUP_TYPE_PARTIAL + 1)
+
+/**
+ * struct guc_state_capture_group_header_t - State capture group header
+ *
+ * State capture group header.
+ */
+struct guc_state_capture_group_header_t {
+	/** @owner: VFID */
+	u32 owner;
+#define GUC_STATE_CAPTURE_GROUP_HEADER_VFID GENMASK(7, 0)
+	/** @info: Engine class/instance and capture type info */
+	u32 info;
+#define GUC_STATE_CAPTURE_GROUP_HEADER_NUM_CAPTURES GENMASK(7, 0)
+#define GUC_STATE_CAPTURE_GROUP_HEADER_CAPTURE_GROUP_TYPE GENMASK(15, 8)
+} __packed;
+
+/**
+ * struct guc_state_capture_group_t - State capture group.
+ *
+ * this is the top level structure where an error-capture dump starts
+ */
+struct guc_state_capture_group_t {
+	/** @grp_header: State capture group header. */
+	struct guc_state_capture_group_header_t grp_header;
+	/** @capture_entries: Array of state captures */
+	struct guc_state_capture_t capture_entries[];
+} __packed;
+
+#endif

drivers/gpu/drm/xe/abi/guc_communication_ctb_abi.h

@@ -52,6 +52,7 @@ struct guc_ct_buffer_desc {
 #define GUC_CTB_STATUS_OVERFLOW				(1 << 0)
 #define GUC_CTB_STATUS_UNDERFLOW			(1 << 1)
 #define GUC_CTB_STATUS_MISMATCH				(1 << 2)
+#define GUC_CTB_STATUS_DISABLED				(1 << 3)
 	u32 reserved[13];
 } __packed;
 static_assert(sizeof(struct guc_ct_buffer_desc) == 64);