Merge tag 'drm-next-2025-07-30' of https://gitlab.freedesktop.org/drm/kernel

Pull drm updates from Dave Airlie:
 "Highlights:

   - Intel xe enable Panthor Lake, started adding WildCat Lake

   - amdgpu has a bunch of reset improvments along with the usual IP
     updates

   - msm got VM_BIND support which is important for vulkan sparse memory

   - more drm_panic users

   - gpusvm common code to handle a bunch of core SVM work outside
     drivers.

  Detail summary:

  Changes outside drm subdirectory:
   - 'shrink_shmem_memory()' for better shmem/hibernate interaction
   - Rust support infrastructure:
      - make ETIMEDOUT available
      - add size constants up to SZ_2G
      - add DMA coherent allocation bindings
   - mtd driver for Intel GPU non-volatile storage
   - i2c designware quirk for Intel xe

  core:
   - atomic helpers: tune enable/disable sequences
   - add task info to wedge API
   - refactor EDID quirks
   - connector: move HDR sink to drm_display_info
   - fourcc: half-float and 32-bit float formats
   - mode_config: pass format info to simplify

  dma-buf:
   - heaps: Give CMA heap a stable name

  ci:
   - add device tree validation and kunit

  displayport:
   - change AUX DPCD access probe address
   - add quirk for DPCD probe
   - add panel replay definitions
   - backlight control helpers

  fbdev:
   - make CONFIG_FIRMWARE_EDID available on all arches

  fence:
   - fix UAF issues

  format-helper:
   - improve tests

  gpusvm:
   - introduce devmem only flag for allocation
   - add timeslicing support to GPU SVM

  ttm:
   - improve eviction

  sched:
   - tracing improvements
   - kunit improvements
   - memory leak fixes
   - reset handling improvements

  color mgmt:
   - add hardware gamma LUT handling helpers

  bridge:
   - add destroy hook
   - switch to reference counted drm_bridge allocations
   - tc358767: convert to devm_drm_bridge_alloc
   - improve CEC handling

  panel:
   - switch to reference counter drm_panel allocations
   - fwnode panel lookup
   - Huiling hl055fhv028c support
   - Raspberry Pi 7" 720x1280 support
   - edp: KDC KD116N3730A05, N160JCE-ELL CMN, N116BCJ-EAK
   - simple: AUO P238HAN01
   - st7701: Winstar wf40eswaa6mnn0
   - visionox: rm69299-shift
   - Renesas R61307, Renesas R69328 support
   - DJN HX83112B

  hdmi:
   - add CEC handling
   - YUV420 output support

  xe:
   - WildCat Lake support
   - Enable PanthorLake by default
   - mark BMG as SRIOV capable
   - update firmware recommendations
   - Expose media OA units
   - aux-bux support for non-volatile memory
   - MTD intel-dg driver for non-volatile memory
   - Expose fan control and voltage regulator in sysfs
   - restructure migration for multi-device
   - Restore GuC submit UAF fix
   - make GEM shrinker drm managed
   - SRIOV VF Post-migration recovery of GGTT nodes
   - W/A additions/reworks
   - Prefetch support for svm ranges
   - Don't allocate managed BO for each policy change
   - HWMON fixes for BMG
   - Create LRC BO without VM
   - PCI ID updates
   - make SLPC debugfs files optional
   - rework eviction rejection of bound external BOs
   - consolidate PAT programming logic for pre/post Xe2
   - init changes for flicker-free boot
   - Enable GuC Dynamic Inhibit Context switch

  i915:
   - drm_panic support for i915/xe
   - initial flip queue off by default for LNL/PNL
   - Wildcat Lake Display support
   - Support for DSC fractional link bpp
   - Support for simultaneous Panel Replay and Adaptive sync
   - Support for PTL+ double buffer LUT
   - initial PIPEDMC event handling
   - drm_panel_follower support
   - DPLL interface renames
   - allocate struct intel_display dynamically
   - flip queue preperation
   - abstract DRAM detection better
   - avoid GuC scheduling stalls
   - remove DG1 force probe requirement
   - fix MEI interrupt handler on RT kernels
   - use backlight control helpers for eDP
   - more shared display code refactoring

  amdgpu:
   - add userq slot to INFO ioctl
   - SR-IOV hibernation support
   - Suspend improvements
   - Backlight improvements
   - Use scaling for non-native eDP modes
   - cleaner shader updates for GC 9.x
   - Remove fence slab
   - SDMA fw checks for userq support
   - RAS updates
   - DMCUB updates
   - DP tunneling fixes
   - Display idle D3 support
   - Per queue reset improvements
   - initial smartmux support

  amdkfd:
   - enable KFD on loongarch
   - mtype fix for ext coherent system memory

  radeon:
   - CS validation additional GL extensions
   - drop console lock during suspend/resume
   - bump driver version

  msm:
   - VM BIND support
   - CI: infrastructure updates
   - UBWC single source of truth
   - decouple GPU and KMS support
   - DP: rework I/O accessors
   - DPU: SM8750 support
   - DSI: SM8750 support
   - GPU: X1-45 support and speedbin support for X1-85
   - MDSS: SM8750 support

  nova:
   - register! macro improvements
   - DMA object abstraction
   - VBIOS parser + fwsec lookup
   - sysmem flush page support
   - falcon: generic falcon boot code and HAL
   - FWSEC-FRTS: fb setup and load/execute

  ivpu:
   - Add Wildcat Lake support
   - Add turbo flag

  ast:
   - improve hardware generations implementation

  imx:
   - IMX8qxq Display Controller support

  lima:
   - Rockchip RK3528 GPU support

  nouveau:
   - fence handling cleanup

  panfrost:
   - MT8370 support
   - bo labeling
   - 64-bit register access

  qaic:
   - add RAS support

  rockchip:
   - convert inno_hdmi to a bridge

  rz-du:
   - add RZ/V2H(P) support
   - MIPI-DSI DCS support

  sitronix:
   - ST7567 support

  sun4i:
   - add H616 support

  tidss:
   - add TI AM62L support
   - AM65x OLDI bridge support

  bochs:
   - drm panic support

  vkms:
   - YUV and R* format support
   - use faux device

  vmwgfx:
   - fence improvements

  hyperv:
   - move out of simple
   - add drm_panic support"

* tag 'drm-next-2025-07-30' of https://gitlab.freedesktop.org/drm/kernel: (1479 commits)
  drm/tidss: oldi: convert to devm_drm_bridge_alloc() API
  drm/tidss: encoder: convert to devm_drm_bridge_alloc()
  drm/amdgpu: move reset support type checks into the caller
  drm/amdgpu/sdma7: re-emit unprocessed state on ring reset
  drm/amdgpu/sdma6: re-emit unprocessed state on ring reset
  drm/amdgpu/sdma5.2: re-emit unprocessed state on ring reset
  drm/amdgpu/sdma5: re-emit unprocessed state on ring reset
  drm/amdgpu/gfx12: re-emit unprocessed state on ring reset
  drm/amdgpu/gfx11: re-emit unprocessed state on ring reset
  drm/amdgpu/gfx10: re-emit unprocessed state on ring reset
  drm/amdgpu/gfx9.4.3: re-emit unprocessed state on kcq reset
  drm/amdgpu/gfx9: re-emit unprocessed state on kcq reset
  drm/amdgpu: Add WARN_ON to the resource clear function
  drm/amd/pm: Use cached metrics data on SMUv13.0.6
  drm/amd/pm: Use cached data for min/max clocks
  gpu: nova-core: fix bounds check in PmuLookupTableEntry::new
  drm/amdgpu: Replace HQD terminology with slots naming
  drm/amdgpu: Add user queue instance count in HW IP info
  drm/amd/amdgpu: Add helper functions for isp buffers
  drm/amd/amdgpu: Initialize swnode for ISP MFD device
  ...

15 files changed, 260 insertions, 191 deletions

diff --git a/drivers/gpu/drm/ttm/tests/ttm_bo_validate_test.c b/drivers/gpu/drm/ttm/tests/ttm_bo_validate_test.c
index 3148f5d3dbd6..1bcc67977f48 100644
--- a/drivers/gpu/drm/ttm/tests/ttm_bo_validate_test.c
+++ b/drivers/gpu/drm/ttm/tests/ttm_bo_validate_test.c
@@ -542,14 +542,15 @@ static void ttm_bo_validate_no_placement_signaled(struct kunit *test)
 		bo->ttm = old_tt;
 	}
 
-	err = ttm_resource_alloc(bo, place, &bo->resource, NULL);
-	KUNIT_EXPECT_EQ(test, err, 0);
-	KUNIT_ASSERT_EQ(test, man->usage, size);
-
 	placement = kunit_kzalloc(test, sizeof(*placement), GFP_KERNEL);
 	KUNIT_ASSERT_NOT_NULL(test, placement);
 
 	ttm_bo_reserve(bo, false, false, NULL);
+
+	err = ttm_resource_alloc(bo, place, &bo->resource, NULL);
+	KUNIT_EXPECT_EQ(test, err, 0);
+	KUNIT_ASSERT_EQ(test, man->usage, size);
+
 	err = ttm_bo_validate(bo, placement, &ctx);
 	ttm_bo_unreserve(bo);
 
@@ -757,56 +758,6 @@ static void ttm_bo_validate_move_fence_not_signaled(struct kunit *test)
 	ttm_mock_manager_fini(priv->ttm_dev, snd_mem);
 }
 
-static void ttm_bo_validate_swapout(struct kunit *test)
-{
-	unsigned long size_big, size = ALIGN(BO_SIZE, PAGE_SIZE);
-	enum ttm_bo_type bo_type = ttm_bo_type_device;
-	struct ttm_buffer_object *bo_small, *bo_big;
-	struct ttm_test_devices *priv = test->priv;
-	struct ttm_operation_ctx ctx = { };
-	struct ttm_placement *placement;
-	u32 mem_type = TTM_PL_TT;
-	struct ttm_place *place;
-	struct sysinfo si;
-	int err;
-
-	si_meminfo(&si);
-	size_big = ALIGN(((u64)si.totalram * si.mem_unit / 2), PAGE_SIZE);
-
-	ttm_mock_manager_init(priv->ttm_dev, mem_type, size_big + size);
-
-	place = ttm_place_kunit_init(test, mem_type, 0);
-	placement = ttm_placement_kunit_init(test, place, 1);
-
-	bo_small = kunit_kzalloc(test, sizeof(*bo_small), GFP_KERNEL);
-	KUNIT_ASSERT_NOT_NULL(test, bo_small);
-
-	drm_gem_private_object_init(priv->drm, &bo_small->base, size);
-
-	err = ttm_bo_init_reserved(priv->ttm_dev, bo_small, bo_type, placement,
-				   PAGE_SIZE, &ctx, NULL, NULL,
-				   &dummy_ttm_bo_destroy);
-	KUNIT_EXPECT_EQ(test, err, 0);
-	dma_resv_unlock(bo_small->base.resv);
-
-	bo_big = ttm_bo_kunit_init(test, priv, size_big, NULL);
-
-	dma_resv_lock(bo_big->base.resv, NULL);
-	err = ttm_bo_validate(bo_big, placement, &ctx);
-	dma_resv_unlock(bo_big->base.resv);
-
-	KUNIT_EXPECT_EQ(test, err, 0);
-	KUNIT_EXPECT_NOT_NULL(test, bo_big->resource);
-	KUNIT_EXPECT_EQ(test, bo_big->resource->mem_type, mem_type);
-	KUNIT_EXPECT_EQ(test, bo_small->resource->mem_type, TTM_PL_SYSTEM);
-	KUNIT_EXPECT_TRUE(test, bo_small->ttm->page_flags & TTM_TT_FLAG_SWAPPED);
-
-	ttm_bo_put(bo_big);
-	ttm_bo_put(bo_small);
-
-	ttm_mock_manager_fini(priv->ttm_dev, mem_type);
-}
-
 static void ttm_bo_validate_happy_evict(struct kunit *test)
 {
 	u32 mem_type = TTM_PL_VRAM, mem_multihop = TTM_PL_TT,
@@ -1201,7 +1152,6 @@ static struct kunit_case ttm_bo_validate_test_cases[] = {
 	KUNIT_CASE(ttm_bo_validate_move_fence_signaled),
 	KUNIT_CASE_PARAM(ttm_bo_validate_move_fence_not_signaled,
 			 ttm_bo_validate_wait_gen_params),
-	KUNIT_CASE(ttm_bo_validate_swapout),
 	KUNIT_CASE(ttm_bo_validate_happy_evict),
 	KUNIT_CASE(ttm_bo_validate_all_pinned_evict),
 	KUNIT_CASE(ttm_bo_validate_allowed_only_evict),
diff --git a/drivers/gpu/drm/ttm/tests/ttm_kunit_helpers.c b/drivers/gpu/drm/ttm/tests/ttm_kunit_helpers.c
index b91c13f46225..7aaf0d1395ff 100644
--- a/drivers/gpu/drm/ttm/tests/ttm_kunit_helpers.c
+++ b/drivers/gpu/drm/ttm/tests/ttm_kunit_helpers.c
@@ -2,6 +2,9 @@
 /*
  * Copyright © 2023 Intel Corporation
  */
+
+#include <linux/export.h>
+
 #include <drm/ttm/ttm_tt.h>
 
 #include "ttm_kunit_helpers.h"
diff --git a/drivers/gpu/drm/ttm/tests/ttm_mock_manager.c b/drivers/gpu/drm/ttm/tests/ttm_mock_manager.c
index f6d1c8a2845d..d7eb6471f2ed 100644
--- a/drivers/gpu/drm/ttm/tests/ttm_mock_manager.c
+++ b/drivers/gpu/drm/ttm/tests/ttm_mock_manager.c
@@ -2,6 +2,9 @@
 /*
  * Copyright © 2023 Intel Corporation
  */
+
+#include <linux/export.h>
+
 #include <drm/ttm/ttm_resource.h>
 #include <drm/ttm/ttm_device.h>
 #include <drm/ttm/ttm_placement.h>
diff --git a/drivers/gpu/drm/ttm/ttm_agp_backend.c b/drivers/gpu/drm/ttm/ttm_agp_backend.c
index d27691f2e451..fca0a1a3c6fd 100644
--- a/drivers/gpu/drm/ttm/ttm_agp_backend.c
+++ b/drivers/gpu/drm/ttm/ttm_agp_backend.c
@@ -36,6 +36,7 @@
 #include <drm/ttm/ttm_tt.h>
 #include <drm/ttm/ttm_resource.h>
 #include <linux/agp_backend.h>
+#include <linux/export.h>
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/io.h>
diff --git a/drivers/gpu/drm/ttm/ttm_backup.c b/drivers/gpu/drm/ttm/ttm_backup.c
index ffaab68bd5dd..cb1b8e5dadf5 100644
--- a/drivers/gpu/drm/ttm/ttm_backup.c
+++ b/drivers/gpu/drm/ttm/ttm_backup.c
@@ -4,6 +4,8 @@
  */
 
 #include <drm/ttm/ttm_backup.h>
+
+#include <linux/export.h>
 #include <linux/page-flags.h>
 #include <linux/swap.h>
 
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 08a23ab037cb..f4d9e68b21e7 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -35,6 +35,7 @@
 #include <drm/ttm/ttm_placement.h>
 #include <drm/ttm/ttm_tt.h>
 
+#include <linux/export.h>
 #include <linux/jiffies.h>
 #include <linux/slab.h>
 #include <linux/sched.h>
@@ -46,6 +47,7 @@
 #include <linux/dma-resv.h>
 
 #include "ttm_module.h"
+#include "ttm_bo_internal.h"
 
 static void ttm_bo_mem_space_debug(struct ttm_buffer_object *bo,
 					struct ttm_placement *placement)
@@ -524,11 +526,11 @@ static s64 ttm_bo_evict_cb(struct ttm_lru_walk *walk, struct ttm_buffer_object *
 		return 0;
 
 	if (bo->deleted) {
-		lret = ttm_bo_wait_ctx(bo, walk->ctx);
+		lret = ttm_bo_wait_ctx(bo, walk->arg.ctx);
 		if (!lret)
 			ttm_bo_cleanup_memtype_use(bo);
 	} else {
-		lret = ttm_bo_evict(bo, walk->ctx);
+		lret = ttm_bo_evict(bo, walk->arg.ctx);
 	}
 
 	if (lret)
@@ -564,8 +566,10 @@ static int ttm_bo_evict_alloc(struct ttm_device *bdev,
 	struct ttm_bo_evict_walk evict_walk = {
 		.walk = {
 			.ops = &ttm_evict_walk_ops,
-			.ctx = ctx,
-			.ticket = ticket,
+			.arg = {
+				.ctx = ctx,
+				.ticket = ticket,
+			}
 		},
 		.place = place,
 		.evictor = evictor,
@@ -574,7 +578,7 @@ static int ttm_bo_evict_alloc(struct ttm_device *bdev,
 	};
 	s64 lret;
 
-	evict_walk.walk.trylock_only = true;
+	evict_walk.walk.arg.trylock_only = true;
 	lret = ttm_lru_walk_for_evict(&evict_walk.walk, bdev, man, 1);
 
 	/* One more attempt if we hit low limit? */
@@ -588,12 +592,12 @@ static int ttm_bo_evict_alloc(struct ttm_device *bdev,
 	/* Reset low limit */
 	evict_walk.try_low = evict_walk.hit_low = false;
 	/* If ticket-locking, repeat while making progress. */
-	evict_walk.walk.trylock_only = false;
+	evict_walk.walk.arg.trylock_only = false;
 
 retry:
 	do {
 		/* The walk may clear the evict_walk.walk.ticket field */
-		evict_walk.walk.ticket = ticket;
+		evict_walk.walk.arg.ticket = ticket;
 		evict_walk.evicted = 0;
 		lret = ttm_lru_walk_for_evict(&evict_walk.walk, bdev, man, 1);
 	} while (!lret && evict_walk.evicted);
@@ -1104,7 +1108,7 @@ ttm_bo_swapout_cb(struct ttm_lru_walk *walk, struct ttm_buffer_object *bo)
 	struct ttm_place place = {.mem_type = bo->resource->mem_type};
 	struct ttm_bo_swapout_walk *swapout_walk =
 		container_of(walk, typeof(*swapout_walk), walk);
-	struct ttm_operation_ctx *ctx = walk->ctx;
+	struct ttm_operation_ctx *ctx = walk->arg.ctx;
 	s64 ret;
 
 	/*
@@ -1215,8 +1219,10 @@ s64 ttm_bo_swapout(struct ttm_device *bdev, struct ttm_operation_ctx *ctx,
 	struct ttm_bo_swapout_walk swapout_walk = {
 		.walk = {
 			.ops = &ttm_swap_ops,
-			.ctx = ctx,
-			.trylock_only = true,
+			.arg = {
+				.ctx = ctx,
+				.trylock_only = true,
+			},
 		},
 		.gfp_flags = gfp_flags,
 	};
diff --git a/drivers/gpu/drm/ttm/ttm_bo_internal.h b/drivers/gpu/drm/ttm/ttm_bo_internal.h
new file mode 100644
index 000000000000..9d8b747a34db
--- /dev/null
+++ b/drivers/gpu/drm/ttm/ttm_bo_internal.h
@@ -0,0 +1,58 @@
+/*
+ * Copyright 2018 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ *
+ */
+
+#ifndef _TTM_BO_INTERNAL_H_
+#define _TTM_BO_INTERNAL_H_
+
+#include <drm/ttm/ttm_bo.h>
+
+/**
+ * ttm_bo_get - reference a struct ttm_buffer_object
+ *
+ * @bo: The buffer object.
+ */
+static inline void ttm_bo_get(struct ttm_buffer_object *bo)
+{
+	kref_get(&bo->kref);
+}
+
+/**
+ * ttm_bo_get_unless_zero - reference a struct ttm_buffer_object unless
+ * its refcount has already reached zero.
+ * @bo: The buffer object.
+ *
+ * Used to reference a TTM buffer object in lookups where the object is removed
+ * from the lookup structure during the destructor and for RCU lookups.
+ *
+ * Returns: @bo if the referencing was successful, NULL otherwise.
+ */
+static inline __must_check struct ttm_buffer_object *
+ttm_bo_get_unless_zero(struct ttm_buffer_object *bo)
+{
+	if (!kref_get_unless_zero(&bo->kref))
+		return NULL;
+	return bo;
+}
+
+#endif
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index bd90404ea609..acbbca9d5c92 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -28,6 +28,8 @@
 /*
  * Authors: Thomas Hellstrom <thellstrom-at-vmware-dot-com>
  */
+
+#include <linux/export.h>
 #include <linux/swap.h>
 #include <linux/vmalloc.h>
 
@@ -37,6 +39,8 @@
 
 #include <drm/drm_cache.h>
 
+#include "ttm_bo_internal.h"
+
 struct ttm_transfer_obj {
 	struct ttm_buffer_object base;
 	struct ttm_buffer_object *bo;
@@ -379,6 +383,32 @@ static int ttm_bo_kmap_ttm(struct ttm_buffer_object *bo,
 }
 
 /**
+ * ttm_bo_kmap_try_from_panic
+ *
+ * @bo: The buffer object
+ * @page: The page to map
+ *
+ * Sets up a kernel virtual mapping using kmap_local_page_try_from_panic().
+ * This should only be called from the panic handler, if you make sure the bo
+ * is the one being displayed, so is properly allocated, and protected.
+ *
+ * Returns the vaddr, that you can use to write to the bo, and that you should
+ * pass to kunmap_local() when you're done with this page, or NULL if the bo
+ * is in iomem.
+ */
+void *ttm_bo_kmap_try_from_panic(struct ttm_buffer_object *bo, unsigned long page)
+{
+	if (page + 1 > PFN_UP(bo->resource->size))
+		return NULL;
+
+	if (!bo->resource->bus.is_iomem && bo->ttm->pages && bo->ttm->pages[page])
+		return kmap_local_page_try_from_panic(bo->ttm->pages[page]);
+
+	return NULL;
+}
+EXPORT_SYMBOL(ttm_bo_kmap_try_from_panic);
+
+/**
  * ttm_bo_kmap
  *
  * @bo: The buffer object.
@@ -770,14 +800,15 @@ error_destroy_tt:
 	return ret;
 }
 
-static bool ttm_lru_walk_trylock(struct ttm_operation_ctx *ctx,
-				 struct ttm_buffer_object *bo,
-				 bool *needs_unlock)
+static bool ttm_lru_walk_trylock(struct ttm_bo_lru_cursor *curs,
+				 struct ttm_buffer_object *bo)
 {
-	*needs_unlock = false;
+	struct ttm_operation_ctx *ctx = curs->arg->ctx;
+
+	curs->needs_unlock = false;
 
 	if (dma_resv_trylock(bo->base.resv)) {
-		*needs_unlock = true;
+		curs->needs_unlock = true;
 		return true;
 	}
 
@@ -789,27 +820,27 @@ static bool ttm_lru_walk_trylock(struct ttm_operation_ctx *ctx,
 	return false;
 }
 
-static int ttm_lru_walk_ticketlock(struct ttm_lru_walk *walk,
-				   struct ttm_buffer_object *bo,
-				   bool *needs_unlock)
+static int ttm_lru_walk_ticketlock(struct ttm_bo_lru_cursor *curs,
+				   struct ttm_buffer_object *bo)
 {
+	struct ttm_lru_walk_arg *arg = curs->arg;
 	struct dma_resv *resv = bo->base.resv;
 	int ret;
 
-	if (walk->ctx->interruptible)
-		ret = dma_resv_lock_interruptible(resv, walk->ticket);
+	if (arg->ctx->interruptible)
+		ret = dma_resv_lock_interruptible(resv, arg->ticket);
 	else
-		ret = dma_resv_lock(resv, walk->ticket);
+		ret = dma_resv_lock(resv, arg->ticket);
 
 	if (!ret) {
-		*needs_unlock = true;
+		curs->needs_unlock = true;
 		/*
 		 * Only a single ticketlock per loop. Ticketlocks are prone
 		 * to return -EDEADLK causing the eviction to fail, so
 		 * after waiting for the ticketlock, revert back to
 		 * trylocking for this walk.
 		 */
-		walk->ticket = NULL;
+		arg->ticket = NULL;
 	} else if (ret == -EDEADLK) {
 		/* Caller needs to exit the ww transaction. */
 		ret = -ENOSPC;
@@ -818,12 +849,6 @@ static int ttm_lru_walk_ticketlock(struct ttm_lru_walk *walk,
 	return ret;
 }
 
-static void ttm_lru_walk_unlock(struct ttm_buffer_object *bo, bool locked)
-{
-	if (locked)
-		dma_resv_unlock(bo->base.resv);
-}
-
 /**
  * ttm_lru_walk_for_evict() - Perform a LRU list walk, with actions taken on
  * valid items.
@@ -858,64 +883,21 @@ static void ttm_lru_walk_unlock(struct ttm_buffer_object *bo, bool locked)
 s64 ttm_lru_walk_for_evict(struct ttm_lru_walk *walk, struct ttm_device *bdev,
 			   struct ttm_resource_manager *man, s64 target)
 {
-	struct ttm_resource_cursor cursor;
-	struct ttm_resource *res;
+	struct ttm_bo_lru_cursor cursor;
+	struct ttm_buffer_object *bo;
 	s64 progress = 0;
 	s64 lret;
 
-	spin_lock(&bdev->lru_lock);
-	ttm_resource_cursor_init(&cursor, man);
-	ttm_resource_manager_for_each_res(&cursor, res) {
-		struct ttm_buffer_object *bo = res->bo;
-		bool bo_needs_unlock = false;
-		bool bo_locked = false;
-		int mem_type;
-
-		/*
-		 * Attempt a trylock before taking a reference on the bo,
-		 * since if we do it the other way around, and the trylock fails,
-		 * we need to drop the lru lock to put the bo.
-		 */
-		if (ttm_lru_walk_trylock(walk->ctx, bo, &bo_needs_unlock))
-			bo_locked = true;
-		else if (!walk->ticket || walk->ctx->no_wait_gpu ||
-			 walk->trylock_only)
-			continue;
-
-		if (!ttm_bo_get_unless_zero(bo)) {
-			ttm_lru_walk_unlock(bo, bo_needs_unlock);
-			continue;
-		}
-
-		mem_type = res->mem_type;
-		spin_unlock(&bdev->lru_lock);
-
-		lret = 0;
-		if (!bo_locked)
-			lret = ttm_lru_walk_ticketlock(walk, bo, &bo_needs_unlock);
-
-		/*
-		 * Note that in between the release of the lru lock and the
-		 * ticketlock, the bo may have switched resource,
-		 * and also memory type, since the resource may have been
-		 * freed and allocated again with a different memory type.
-		 * In that case, just skip it.
-		 */
-		if (!lret && bo->resource && bo->resource->mem_type == mem_type)
-			lret = walk->ops->process_bo(walk, bo);
-
-		ttm_lru_walk_unlock(bo, bo_needs_unlock);
-		ttm_bo_put(bo);
+	ttm_bo_lru_for_each_reserved_guarded(&cursor, man, &walk->arg, bo) {
+		lret = walk->ops->process_bo(walk, bo);
 		if (lret == -EBUSY || lret == -EALREADY)
 			lret = 0;
 		progress = (lret < 0) ? lret : progress + lret;
-
-		spin_lock(&bdev->lru_lock);
 		if (progress < 0 || progress >= target)
 			break;
 	}
-	ttm_resource_cursor_fini(&cursor);
-	spin_unlock(&bdev->lru_lock);
+	if (IS_ERR(bo))
+		return PTR_ERR(bo);
 
 	return progress;
 }
@@ -953,44 +935,87 @@ EXPORT_SYMBOL(ttm_bo_lru_cursor_fini);
  * ttm_bo_lru_cursor_init() - Initialize a struct ttm_bo_lru_cursor
  * @curs: The ttm_bo_lru_cursor to initialize.
  * @man: The ttm resource_manager whose LRU lists to iterate over.
- * @ctx: The ttm_operation_ctx to govern the locking.
+ * @arg: The ttm_lru_walk_arg to govern the walk.
  *
- * Initialize a struct ttm_bo_lru_cursor. Currently only trylocking
- * or prelocked buffer objects are available as detailed by
- * @ctx::resv and @ctx::allow_res_evict. Ticketlocking is not
- * supported.
+ * Initialize a struct ttm_bo_lru_cursor.
  *
  * Return: Pointer to @curs. The function does not fail.
  */
 struct ttm_bo_lru_cursor *
 ttm_bo_lru_cursor_init(struct ttm_bo_lru_cursor *curs,
 		       struct ttm_resource_manager *man,
-		       struct ttm_operation_ctx *ctx)
+		       struct ttm_lru_walk_arg *arg)
 {
 	memset(curs, 0, sizeof(*curs));
 	ttm_resource_cursor_init(&curs->res_curs, man);
-	curs->ctx = ctx;
+	curs->arg = arg;
 
 	return curs;
 }
 EXPORT_SYMBOL(ttm_bo_lru_cursor_init);
 
 static struct ttm_buffer_object *
-ttm_bo_from_res_reserved(struct ttm_resource *res, struct ttm_bo_lru_cursor *curs)
+__ttm_bo_lru_cursor_next(struct ttm_bo_lru_cursor *curs)
 {
-	struct ttm_buffer_object *bo = res->bo;
+	spinlock_t *lru_lock = &curs->res_curs.man->bdev->lru_lock;
+	struct ttm_resource *res = NULL;
+	struct ttm_buffer_object *bo;
+	struct ttm_lru_walk_arg *arg = curs->arg;
+	bool first = !curs->bo;
 
-	if (!ttm_lru_walk_trylock(curs->ctx, bo, &curs->needs_unlock))
-		return NULL;
+	ttm_bo_lru_cursor_cleanup_bo(curs);
 
-	if (!ttm_bo_get_unless_zero(bo)) {
-		if (curs->needs_unlock)
-			dma_resv_unlock(bo->base.resv);
-		return NULL;
+	spin_lock(lru_lock);
+	for (;;) {
+		int mem_type, ret = 0;
+		bool bo_locked = false;
+
+		if (first) {
+			res = ttm_resource_manager_first(&curs->res_curs);
+			first = false;
+		} else {
+			res = ttm_resource_manager_next(&curs->res_curs);
+		}
+		if (!res)
+			break;
+
+		bo = res->bo;
+		if (ttm_lru_walk_trylock(curs, bo))
+			bo_locked = true;
+		else if (!arg->ticket || arg->ctx->no_wait_gpu || arg->trylock_only)
+			continue;
+
+		if (!ttm_bo_get_unless_zero(bo)) {
+			if (curs->needs_unlock)
+				dma_resv_unlock(bo->base.resv);
+			continue;
+		}
+
+		mem_type = res->mem_type;
+		spin_unlock(lru_lock);
+		if (!bo_locked)
+			ret = ttm_lru_walk_ticketlock(curs, bo);
+
+		/*
+		 * Note that in between the release of the lru lock and the
+		 * ticketlock, the bo may have switched resource,
+		 * and also memory type, since the resource may have been
+		 * freed and allocated again with a different memory type.
+		 * In that case, just skip it.
+		 */
+		curs->bo = bo;
+		if (!ret && bo->resource && bo->resource->mem_type == mem_type)
+			return bo;
+
+		ttm_bo_lru_cursor_cleanup_bo(curs);
+		if (ret && ret != -EALREADY)
+			return ERR_PTR(ret);
+
+		spin_lock(lru_lock);
 	}
 
-	curs->bo = bo;
-	return bo;
+	spin_unlock(lru_lock);
+	return res ? bo : NULL;
 }
 
 /**
@@ -1004,25 +1029,7 @@ ttm_bo_from_res_reserved(struct ttm_resource *res, struct ttm_bo_lru_cursor *cur
  */
 struct ttm_buffer_object *ttm_bo_lru_cursor_next(struct ttm_bo_lru_cursor *curs)
 {
-	spinlock_t *lru_lock = &curs->res_curs.man->bdev->lru_lock;
-	struct ttm_resource *res = NULL;
-	struct ttm_buffer_object *bo;
-
-	ttm_bo_lru_cursor_cleanup_bo(curs);
-
-	spin_lock(lru_lock);
-	for (;;) {
-		res = ttm_resource_manager_next(&curs->res_curs);
-		if (!res)
-			break;
-
-		bo = ttm_bo_from_res_reserved(res, curs);
-		if (bo)
-			break;
-	}
-
-	spin_unlock(lru_lock);
-	return res ? bo : NULL;
+	return __ttm_bo_lru_cursor_next(curs);
 }
 EXPORT_SYMBOL(ttm_bo_lru_cursor_next);
 
@@ -1036,21 +1043,8 @@ EXPORT_SYMBOL(ttm_bo_lru_cursor_next);
  */
 struct ttm_buffer_object *ttm_bo_lru_cursor_first(struct ttm_bo_lru_cursor *curs)
 {
-	spinlock_t *lru_lock = &curs->res_curs.man->bdev->lru_lock;
-	struct ttm_buffer_object *bo;
-	struct ttm_resource *res;
-
-	spin_lock(lru_lock);
-	res = ttm_resource_manager_first(&curs->res_curs);
-	if (!res) {
-		spin_unlock(lru_lock);
-		return NULL;
-	}
-
-	bo = ttm_bo_from_res_reserved(res, curs);
-	spin_unlock(lru_lock);
-
-	return bo ? bo : ttm_bo_lru_cursor_next(curs);
+	ttm_bo_lru_cursor_cleanup_bo(curs);
+	return __ttm_bo_lru_cursor_next(curs);
 }
 EXPORT_SYMBOL(ttm_bo_lru_cursor_first);
 
diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
index bdfa6ecfef05..b47020fca199 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
@@ -31,6 +31,8 @@
 
 #define pr_fmt(fmt) "[TTM] " fmt
 
+#include <linux/export.h>
+
 #include <drm/ttm/ttm_bo.h>
 #include <drm/ttm/ttm_placement.h>
 #include <drm/ttm/ttm_tt.h>
diff --git a/drivers/gpu/drm/ttm/ttm_device.c b/drivers/gpu/drm/ttm/ttm_device.c
index 02e797fd1891..c3e2fcbdd2cc 100644
--- a/drivers/gpu/drm/ttm/ttm_device.c
+++ b/drivers/gpu/drm/ttm/ttm_device.c
@@ -28,6 +28,7 @@
 #define pr_fmt(fmt) "[TTM DEVICE] " fmt
 
 #include <linux/debugfs.h>
+#include <linux/export.h>
 #include <linux/mm.h>
 
 #include <drm/ttm/ttm_bo.h>
@@ -36,6 +37,7 @@
 #include <drm/ttm/ttm_placement.h>
 
 #include "ttm_module.h"
+#include "ttm_bo_internal.h"
 
 /*
  * ttm_global_mutex - protecting the global state
@@ -123,6 +125,28 @@ out:
 	return ret;
 }
 
+/**
+ * ttm_device_prepare_hibernation - move GTT BOs to shmem for hibernation.
+ *
+ * @bdev: A pointer to a struct ttm_device to prepare hibernation for.
+ *
+ * Return: 0 on success, negative number on failure.
+ */
+int ttm_device_prepare_hibernation(struct ttm_device *bdev)
+{
+	struct ttm_operation_ctx ctx = {
+		.interruptible = false,
+		.no_wait_gpu = false,
+	};
+	int ret;
+
+	do {
+		ret = ttm_device_swapout(bdev, &ctx, GFP_KERNEL);
+	} while (ret > 0);
+	return ret;
+}
+EXPORT_SYMBOL(ttm_device_prepare_hibernation);
+
 /*
  * A buffer object shrink method that tries to swap out the first
  * buffer object on the global::swap_lru list.
diff --git a/drivers/gpu/drm/ttm/ttm_execbuf_util.c b/drivers/gpu/drm/ttm/ttm_execbuf_util.c
index f1c60fa80c2d..bc7a83a9fe44 100644
--- a/drivers/gpu/drm/ttm/ttm_execbuf_util.c
+++ b/drivers/gpu/drm/ttm/ttm_execbuf_util.c
@@ -26,6 +26,8 @@
  *
  **************************************************************************/
 
+#include <linux/export.h>
+
 #include <drm/ttm/ttm_execbuf_util.h>
 #include <drm/ttm/ttm_bo.h>
 
diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c
index c2ea865be657..baf27c70a419 100644
--- a/drivers/gpu/drm/ttm/ttm_pool.c
+++ b/drivers/gpu/drm/ttm/ttm_pool.c
@@ -31,6 +31,7 @@
  * cause they are rather slow compared to alloc_pages+map.
  */
 
+#include <linux/export.h>
 #include <linux/module.h>
 #include <linux/dma-mapping.h>
 #include <linux/debugfs.h>
@@ -1132,7 +1133,9 @@ void ttm_pool_fini(struct ttm_pool *pool)
 }
 EXPORT_SYMBOL(ttm_pool_fini);
 
-/* As long as pages are available make sure to release at least one */
+/* Free average pool number of pages.  */
+#define TTM_SHRINKER_BATCH ((1 << (MAX_PAGE_ORDER / 2)) * NR_PAGE_ORDERS)
+
 static unsigned long ttm_pool_shrinker_scan(struct shrinker *shrink,
 					    struct shrink_control *sc)
 {
@@ -1140,9 +1143,12 @@ static unsigned long ttm_pool_shrinker_scan(struct shrinker *shrink,
 
 	do
 		num_freed += ttm_pool_shrink();
-	while (!num_freed && atomic_long_read(&allocated_pages));
+	while (num_freed < sc->nr_to_scan &&
+	       atomic_long_read(&allocated_pages));
+
+	sc->nr_scanned = num_freed;
 
-	return num_freed;
+	return num_freed ?: SHRINK_STOP;
 }
 
 /* Return the number of pages available or SHRINK_EMPTY if we have none */
@@ -1233,7 +1239,7 @@ int ttm_pool_debugfs(struct ttm_pool *pool, struct seq_file *m)
 {
 	unsigned int i;
 
-	if (!pool->use_dma_alloc) {
+	if (!pool->use_dma_alloc && pool->nid == NUMA_NO_NODE) {
 		seq_puts(m, "unused\n");
 		return 0;
 	}
@@ -1242,7 +1248,12 @@ int ttm_pool_debugfs(struct ttm_pool *pool, struct seq_file *m)
 
 	spin_lock(&shrinker_lock);
 	for (i = 0; i < TTM_NUM_CACHING_TYPES; ++i) {
-		seq_puts(m, "DMA ");
+		if (!ttm_pool_select_type(pool, i, 0))
+			continue;
+		if (pool->use_dma_alloc)
+			seq_puts(m, "DMA ");
+		else
+			seq_printf(m, "N%d ", pool->nid);
 		switch (i) {
 		case ttm_cached:
 			seq_puts(m, "\t:");
@@ -1266,10 +1277,15 @@ EXPORT_SYMBOL(ttm_pool_debugfs);
 /* Test the shrinker functions and dump the result */
 static int ttm_pool_debugfs_shrink_show(struct seq_file *m, void *data)
 {
-	struct shrink_control sc = { .gfp_mask = GFP_NOFS };
+	struct shrink_control sc = {
+		.gfp_mask = GFP_NOFS,
+		.nr_to_scan = TTM_SHRINKER_BATCH,
+	};
+	unsigned long count;
 
 	fs_reclaim_acquire(GFP_KERNEL);
-	seq_printf(m, "%lu/%lu\n", ttm_pool_shrinker_count(mm_shrinker, &sc),
+	count = ttm_pool_shrinker_count(mm_shrinker, &sc);
+	seq_printf(m, "%lu/%lu\n", count,
 		   ttm_pool_shrinker_scan(mm_shrinker, &sc));
 	fs_reclaim_release(GFP_KERNEL);
 
@@ -1324,6 +1340,7 @@ int ttm_pool_mgr_init(unsigned long num_pages)
 
 	mm_shrinker->count_objects = ttm_pool_shrinker_count;
 	mm_shrinker->scan_objects = ttm_pool_shrinker_scan;
+	mm_shrinker->batch = TTM_SHRINKER_BATCH;
 	mm_shrinker->seeks = 1;
 
 	shrinker_register(mm_shrinker);
diff --git a/drivers/gpu/drm/ttm/ttm_range_manager.c b/drivers/gpu/drm/ttm/ttm_range_manager.c
index ae11d07eb63a..db854b581d83 100644
--- a/drivers/gpu/drm/ttm/ttm_range_manager.c
+++ b/drivers/gpu/drm/ttm/ttm_range_manager.c
@@ -34,6 +34,8 @@
 #include <drm/ttm/ttm_range_manager.h>
 #include <drm/ttm/ttm_bo.h>
 #include <drm/drm_mm.h>
+
+#include <linux/export.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 
diff --git a/drivers/gpu/drm/ttm/ttm_resource.c b/drivers/gpu/drm/ttm/ttm_resource.c
index 769b0ca9be47..e2c82ad07eb4 100644
--- a/drivers/gpu/drm/ttm/ttm_resource.c
+++ b/drivers/gpu/drm/ttm/ttm_resource.c
@@ -23,6 +23,7 @@
  */
 
 #include <linux/debugfs.h>
+#include <linux/export.h>
 #include <linux/io-mapping.h>
 #include <linux/iosys-map.h>
 #include <linux/scatterlist.h>
@@ -557,6 +558,9 @@ int ttm_resource_manager_evict_all(struct ttm_device *bdev,
 		cond_resched();
 	} while (!ret);
 
+	if (ret && ret != -ENOENT)
+		return ret;
+
 	spin_lock(&man->move_lock);
 	fence = dma_fence_get(man->move);
 	spin_unlock(&man->move_lock);
diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c
index 698cd4bf5e46..506e257dfba8 100644
--- a/drivers/gpu/drm/ttm/ttm_tt.c
+++ b/drivers/gpu/drm/ttm/ttm_tt.c
@@ -33,6 +33,7 @@
 
 #include <linux/cc_platform.h>
 #include <linux/debugfs.h>
+#include <linux/export.h>
 #include <linux/file.h>
 #include <linux/module.h>
 #include <linux/sched.h>