Merge tag 'drm-next-2024-05-15' of https://gitlab.freedesktop.org/drm/kernel

Pull drm updates from Dave Airlie:
 "This is the main pull request for the drm subsystems for 6.10.

  In drivers the main thing is a new driver for ARM Mali firmware based
  GPUs, otherwise there are a lot of changes to amdgpu/xe/i915/msm and
  scattered changes to everything else.

  In the core a bunch of headers and Kconfig was refactored, along with
  the addition of a new panic handler which is meant to provide a user
  friendly message when a panic happens and graphical display is
  enabled.

  New drivers:
   - panthor: ARM Mali/Immortalis CSF-based GPU driver

  Core:
   - add a CONFIG_DRM_WERROR option
   - make more headers self-contained
   - grab resv lock in pin/unpin
   - fix vmap resv locking
   - EDID/eDP panel matching
   - Kconfig cleanups
   - DT sound bindings
   - Add SIZE_HINTS property for cursor planes
   - Add struct drm_edid_product_id and helpers.
   - Use drm device based logging in more drm functions.
   - drop seq_file.h from a bunch of places
   - use drm_edid driver conversions

  dp:
   - DP Tunnel documentation
   - MST read sideband cap
   - Adaptive sync SDP prep work

  ttm:
   - improve placement for TTM BOs in idle/busy handling

  panic:
   - Fixes for drm-panic, and option to test it.
   - Add drm panic to simpledrm, mgag200, imx, ast

  bridge:
   - improve init ordering
   - adv7511: allow GPIO pin sharing
   - tc358775: add tc358675 support

  panel:
   - AUO B120XAN01.0
   - Samsung s6e3fa7
   - BOE NT116WHM-N44
   - CMN N116BCA-EA1,
   - CrystalClear CMT430B19N00
   - Startek KD050HDFIA020-C020A
   - powertip PH128800T006-ZHC01
   - Innolux G121X1-L03
   - LG sw43408
   - Khadas TS050 V2
   - EDO RM69380 OLED
   - CSOT MNB601LS1-1

  amdgpu:
   - HDCP/ODM/RAS fixes
   - Devcoredump improvements
   - Expose VCN activity via sysfs
   - SMY 13.0.x updates
   - Enable fast updates on DCN 3.1.4
   - Add dclk and vclk reporting on additional devices
   - Add ACA RAS infrastructure
   - Implement TLB flush fence
   - EEPROM handling fixes
   - SMUIO 14.0.2 support
   - SMU 14.0.1 Updates
   - SMU 14.0.2 support
   - Sync page table freeing with TLB flushes
   - DML2 refactor
   - DC debug improvements
   - DCN 3.5.x Updates
   - GPU reset fixes
   - HDP fix for second GFX pipe on GC 10.x
   - Enable secondary GFX pipe on GC 10.3
   - Refactor and clean up BACO/BOCO/BAMACO handling
   - Remove invalid TTM resource start check
   - UAF fix in VA IOCTL
   - GPUVM page fault redirection to secondary IH rings for IH 6.x
   - Initial support for mapping kernel queues via MES
   - Fix VRAM memory accounting

  amdkfd:
   - MQD handling cleanup
   - Preemption handling fixes for XCDs
   - TLB flush fix for GC 9.4.2
   - Properly clean up workqueue during module unload
   - Fix memory leak process create failure
   - Range check CP bad op exception targets to avoid reporting invalid exceptions to userspace
   - Fix eviction fence handling
   - Fix leak in GPU memory allocation failure case
   - DMABuf import handling fix
   - Enable SQ watchpoint for gfx10

  i915:
   - Adding new DG2 PCI ID
   - add context hints for GT frequency
   - enable only one CCS for compute workloads
   - new workarounds
   - Fix UAF on destroy against retire race and remove two earlier partial fixes
   - Limit the reserved VM space to only the platforms that need it
   - Fix gt reset with GuC submission is disable
   - Add and use gt_to_guc() wrapper

  i915/xe display:
   - Lunar Lake display enabling, including cdclk and other refactors
   - BIOS/VBT/opregion related refactor
   - Digital port related refactor/clean-up
   - Fix 2s boot time regression on DP panel replay init
   - Remove duplication on audio enable/disable on SDVO and g4x+ DP
   - Disable AuxCCS framebuffers if built for Xe
   - Make crtc disable more atomic
   - Increase DP idle pattern wait timeout to 2ms
   - Start using container_of_const() for some extra const safety
   - Fix Jasper Lake boot freeze
   - Enable MST mode for 128b/132b single-stream sideband
   - Enable Adaptive Sync SDP Support for DP
   - Fix MTL supported DP rates - removal of UHBR13.5
   - PLL refactoring
   - Limit eDP MSO pipe only for display version 20
   - More display refactor towards independence from i915 dev_priv
   - Convert i915/xe fbdev to DRM client
   - More initial work to make display code more independent from i915

  xe:
   - improved error capture
   - clean up some uAPI leftovers
   - devcoredump update
   - Add BMG mocs table
   - Handle GSCCS ER interrupt
   - Implement xe2- and GuC workarounds
   - struct xe_device cleanup
   - Hwmon updates
   - Add LRC parsing for more GPU instruction
   - Increase VM_BIND number of per-ioctl Ops
   - drm/xe: Add XE_BO_GGTT_INVALIDATE flag
   - Initial development for SR-IOV support
   - Add new PCI IDs to DG2 platform
   - Move userptr over to start using hmm_range_fault

  msm:
   - Switched to generating register header files during build process
     instead of shipping pre-generated headers
   - Merged DPU and MDP4 format databases.
   - DP:
     - Stop using compat string to distinguish DP and eDP cases
     - Added support for X Elite platform (X1E80100)
     - Reworked DP aux/audio support
     - Added SM6350 DP to the bindings
   - GPU:
     - a7xx perfcntr reg fixes
     - MAINTAINERS updates
     - a750 devcoredump support

  radeon:
   - Silence UBSAN warnings related to flexible arrays

  nouveau:
   - move some uAPI objects to uapi headers

  omapdrm:
   - console fix

  ast:
   - add i2c polling

  qaic:
   - add debugfs entries

  exynos:
   - fix platform_driver .owner
   - drop cleanup code

  mediatek:
   - Use devm_platform_get_and_ioremap_resource() in mtk_hdmi_ddc_probe()
   - Add GAMMA 12-bit LUT support for MT8188
   - Rename mtk_drm_* to mtk_*
   - Drop driver owner initialization
   - Correct calculation formula of PHY Timing"

* tag 'drm-next-2024-05-15' of https://gitlab.freedesktop.org/drm/kernel: (1477 commits)
  drm/xe/ads: Use flexible-array
  drm/xe: Use ordered WQ for G2H handler
  drm/msm/gen_header: allow skipping the validation
  drm/msm/a6xx: Cleanup indexed regs const'ness
  drm/msm: Add devcoredump support for a750
  drm/msm: Adjust a7xx GBIF debugbus dumping
  drm/msm: Update a6xx registers XML
  drm/msm: Fix imported a750 snapshot header for upstream
  drm/msm: Import a750 snapshot registers from kgsl
  MAINTAINERS: Add Konrad Dybcio as a reviewer for the Adreno driver
  MAINTAINERS: Add a separate entry for Qualcomm Adreno GPU drivers
  drm/msm/a6xx: Avoid a nullptr dereference when speedbin setting fails
  drm/msm/adreno: fix CP cycles stat retrieval on a7xx
  drm/msm/a7xx: allow writing to CP_BV counter selection registers
  drm: zynqmp_dpsub: Always register bridge
  Revert "drm/bridge: ti-sn65dsi83: Fix enable error path"
  drm/fb_dma: Add checks in drm_fb_dma_get_scanout_buffer()
  drm/fbdev-generic: Do not set physical framebuffer address
  drm/panthor: Fix the FW reset logic
  drm/panthor: Make sure we handle 'unknown group state' case properly
  ...

1 files changed, 77 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
index e0f8ce9d8440..c8980d5f6540 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
@@ -26,6 +26,9 @@
 
 #include <linux/debugfs.h>
 #include <linux/list.h>
+#include <linux/kfifo.h>
+#include <linux/radix-tree.h>
+#include <linux/siphash.h>
 #include "ta_ras_if.h"
 #include "amdgpu_ras_eeprom.h"
 #include "amdgpu_smuio.h"
@@ -64,6 +67,14 @@ struct amdgpu_iv_entry;
 /* The high three bits indicates socketid */
 #define AMDGPU_RAS_GET_FEATURES(val)  ((val) & ~AMDGPU_RAS_FEATURES_SOCKETID_MASK)
 
+#define RAS_EVENT_LOG(_adev, _id, _fmt, ...)				\
+do {									\
+	if (amdgpu_ras_event_id_is_valid((_adev), (_id)))			\
+	    dev_info((_adev)->dev, "{%llu}" _fmt, (_id), ##__VA_ARGS__);	\
+	else								\
+	    dev_info((_adev)->dev, _fmt, ##__VA_ARGS__);			\
+} while (0)
+
 enum amdgpu_ras_block {
 	AMDGPU_RAS_BLOCK__UMC = 0,
 	AMDGPU_RAS_BLOCK__SDMA,
@@ -419,6 +430,52 @@ struct umc_ecc_info {
 	int record_ce_addr_supported;
 };
 
+enum ras_event_type {
+	RAS_EVENT_TYPE_INVALID = -1,
+	RAS_EVENT_TYPE_ISR = 0,
+	RAS_EVENT_TYPE_COUNT,
+};
+
+struct ras_event_manager {
+	atomic64_t seqnos[RAS_EVENT_TYPE_COUNT];
+};
+
+struct ras_query_context {
+	enum ras_event_type type;
+	u64 event_id;
+};
+
+typedef int (*pasid_notify)(struct amdgpu_device *adev,
+		uint16_t pasid, void *data);
+
+struct ras_poison_msg {
+	enum amdgpu_ras_block block;
+	uint16_t pasid;
+	uint32_t reset;
+	pasid_notify pasid_fn;
+	void *data;
+};
+
+struct ras_err_pages {
+	uint32_t count;
+	uint64_t *pfn;
+};
+
+struct ras_ecc_err {
+	u64 hash_index;
+	uint64_t status;
+	uint64_t ipid;
+	uint64_t addr;
+	struct ras_err_pages err_pages;
+};
+
+struct ras_ecc_log_info {
+	struct mutex lock;
+	siphash_key_t ecc_key;
+	struct radix_tree_root de_page_tree;
+	bool	de_updated;
+};
+
 struct amdgpu_ras {
 	/* ras infrastructure */
 	/* for ras itself. */
@@ -477,8 +534,18 @@ struct amdgpu_ras {
 	wait_queue_head_t page_retirement_wq;
 	struct mutex page_retirement_lock;
 	atomic_t page_retirement_req_cnt;
+	struct mutex page_rsv_lock;
+	DECLARE_KFIFO(poison_fifo, struct ras_poison_msg, 128);
+	struct ras_ecc_log_info  umc_ecc_log;
+	struct delayed_work page_retirement_dwork;
+
 	/* Fatal error detected flag */
 	atomic_t fed;
+
+	/* RAS event manager */
+	struct ras_event_manager __event_mgr;
+	struct ras_event_manager *event_mgr;
+
 };
 
 struct ras_fs_data {
@@ -512,6 +579,7 @@ struct ras_err_data {
 	unsigned long de_count;
 	unsigned long err_addr_cnt;
 	struct eeprom_table_record *err_addr;
+	unsigned long err_addr_len;
 	u32 err_list_count;
 	struct list_head err_node_list;
 };
@@ -879,4 +947,13 @@ void amdgpu_ras_del_mca_err_addr(struct ras_err_info *err_info,
 void amdgpu_ras_set_fed(struct amdgpu_device *adev, bool status);
 bool amdgpu_ras_get_fed_status(struct amdgpu_device *adev);
 
+bool amdgpu_ras_event_id_is_valid(struct amdgpu_device *adev, u64 id);
+u64 amdgpu_ras_acquire_event_id(struct amdgpu_device *adev, enum ras_event_type type);
+
+int amdgpu_ras_reserve_page(struct amdgpu_device *adev, uint64_t pfn);
+
+int amdgpu_ras_put_poison_req(struct amdgpu_device *adev,
+		enum amdgpu_ras_block block, uint16_t pasid,
+		pasid_notify pasid_fn, void *data, uint32_t reset);
+
 #endif