Merge tag 'amd-drm-next-6.5-2023-06-09' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.5-2023-06-02:

amdgpu:
- SR-IOV fixes
- Warning fixes
- Misc code cleanups and spelling fixes
- DCN 3.2 updates
- Improved DC FAMS support for better power management
- Improved DC SubVP support for better power management
- DCN 3.1.x fixes
- Max IB size query
- DC GPU reset fixes
- RAS updates
- DCN 3.0.x fixes
- S/G display fixes
- CP shadow buffer support
- Implement connector force callback
- Z8 power improvements
- PSP 13.0.10 vbflash support
- Mode2 reset fixes
- Store MQDs in VRAM to improve queue switch latency
- VCN 3.x fixes
- JPEG 3.x fixes
- Enable DC_FP on LoongArch
- GFXOFF fixes
- GC 9.4.3 partition support
- SDMA 4.4.2 partition support
- VCN/JPEG 4.0.3 partition support
- VCN 4.0.3 updates
- NBIO 7.9 updates
- GC 9.4.3 updates
- Take NUMA into account when allocating memory
- Handle NUMA for partitions
- SMU 13.0.6 updates
- GC 9.4.3 RAS updates
- Stop including unused swiotlb.h
- SMU 13.0.7 fixes
- Fix clock output ordering on some APUs
- Clean up DC FPGA code
- GFX9 preemption fixes
- Misc irq fixes
- S0ix fixes
- Add new DRM_AMDGPU_WERROR config parameter to help with CI
- PCIe fix for RDNA2
- kdoc fixes
- Documentation updates

amdkfd:
- Query TTM mem limit rather than hardcoding it
- GC 9.4.3 partition support
- Handle NUMA for partitions

radeon:
- Fix possible double free
- Stop including unused swiotlb.h
- Fix possible division by zero

ttm:
- Add query for TTM mem limit
- Add NUMA awareness to pools
- Export ttm_pool_fini()

UAPI:
- Add new ctx query flag to better handle GPU resets
  Mesa MR: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22290
- Add new interface to query and set shadow buffer for RDNA3
  Mesa MR: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21986
- Add new INFO query for max IB size
  Proposed userspace: https://gitlab.freedesktop.org/bnieuwenhuizen/mesa/-/commits/ib-rejection-v3

amd-drm-next-6.5-2023-06-09:

amdgpu:
- S0ix fixes
- Initial SMU13 Overdrive support
- kdoc fixes
- Misc clode cleanups
- Flexible array fixes
- Display OTG fixes
- SMU 13.0.6 updates
- Revert some broken clock counter updates
- Misc display fixes
- GFX9 preemption fixes
- Add support for newer EEPROM bad page table format
- Add missing radeon secondary id
- Add support for new colorspace KMS API
- CSA fix
- Stable pstate fixes for APUs
- make vbl interface admin only
- Handle PCI accelerator class

amdkfd:
- Add debugger support for gdb

radeon:
- Fix possible UAF

drm:
- Add Colorspace functionality

UAPI:
- Add debugger interface for enabling gdb
  Proposed userspace: https://github.com/ROCm-Developer-Tools/ROCdbgapi/tree/wip-dbgapi
- Add KMS colorspace API
  Discussion: https://lists.freedesktop.org/archives/dri-devel/2023-June/408128.html

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230609174817.7764-1-alexander.deucher@amd.com

3 files changed, 16 insertions, 6 deletions

diff --git a/drivers/gpu/drm/ttm/ttm_device.c b/drivers/gpu/drm/ttm/ttm_device.c
index df4cf5468e7f..7726a72befc5 100644
--- a/drivers/gpu/drm/ttm/ttm_device.c
+++ b/drivers/gpu/drm/ttm/ttm_device.c
@@ -213,7 +213,7 @@ int ttm_device_init(struct ttm_device *bdev, const struct ttm_device_funcs *func
 	bdev->funcs = funcs;
 
 	ttm_sys_man_init(bdev);
-	ttm_pool_init(&bdev->pool, dev, use_dma_alloc, use_dma32);
+	ttm_pool_init(&bdev->pool, dev, NUMA_NO_NODE, use_dma_alloc, use_dma32);
 
 	bdev->vma_manager = vma_manager;
 	spin_lock_init(&bdev->lru_lock);
diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c
index 4db3982057be..cddb9151d20f 100644
--- a/drivers/gpu/drm/ttm/ttm_pool.c
+++ b/drivers/gpu/drm/ttm/ttm_pool.c
@@ -93,7 +93,7 @@ static struct page *ttm_pool_alloc_page(struct ttm_pool *pool, gfp_t gfp_flags,
 			__GFP_KSWAPD_RECLAIM;
 
 	if (!pool->use_dma_alloc) {
-		p = alloc_pages(gfp_flags, order);
+		p = alloc_pages_node(pool->nid, gfp_flags, order);
 		if (p)
 			p->private = order;
 		return p;
@@ -287,7 +287,7 @@ static struct ttm_pool_type *ttm_pool_select_type(struct ttm_pool *pool,
 						  enum ttm_caching caching,
 						  unsigned int order)
 {
-	if (pool->use_dma_alloc)
+	if (pool->use_dma_alloc || pool->nid != NUMA_NO_NODE)
 		return &pool->caching[caching].orders[order];
 
 #ifdef CONFIG_X86
@@ -545,29 +545,32 @@ EXPORT_SYMBOL(ttm_pool_free);
  *
  * @pool: the pool to initialize
  * @dev: device for DMA allocations and mappings
+ * @nid: NUMA node to use for allocations
  * @use_dma_alloc: true if coherent DMA alloc should be used
  * @use_dma32: true if GFP_DMA32 should be used
  *
  * Initialize the pool and its pool types.
  */
 void ttm_pool_init(struct ttm_pool *pool, struct device *dev,
-		   bool use_dma_alloc, bool use_dma32)
+		   int nid, bool use_dma_alloc, bool use_dma32)
 {
 	unsigned int i, j;
 
 	WARN_ON(!dev && use_dma_alloc);
 
 	pool->dev = dev;
+	pool->nid = nid;
 	pool->use_dma_alloc = use_dma_alloc;
 	pool->use_dma32 = use_dma32;
 
-	if (use_dma_alloc) {
+	if (use_dma_alloc || nid != NUMA_NO_NODE) {
 		for (i = 0; i < TTM_NUM_CACHING_TYPES; ++i)
 			for (j = 0; j <= MAX_ORDER; ++j)
 				ttm_pool_type_init(&pool->caching[i].orders[j],
 						   pool, i, j);
 	}
 }
+EXPORT_SYMBOL(ttm_pool_init);
 
 /**
  * ttm_pool_fini - Cleanup a pool
@@ -581,7 +584,7 @@ void ttm_pool_fini(struct ttm_pool *pool)
 {
 	unsigned int i, j;
 
-	if (pool->use_dma_alloc) {
+	if (pool->use_dma_alloc || pool->nid != NUMA_NO_NODE) {
 		for (i = 0; i < TTM_NUM_CACHING_TYPES; ++i)
 			for (j = 0; j <= MAX_ORDER; ++j)
 				ttm_pool_type_fini(&pool->caching[i].orders[j]);
@@ -592,6 +595,7 @@ void ttm_pool_fini(struct ttm_pool *pool)
 	 */
 	synchronize_shrinkers();
 }
+EXPORT_SYMBOL(ttm_pool_fini);
 
 /* As long as pages are available make sure to release at least one */
 static unsigned long ttm_pool_shrinker_scan(struct shrinker *shrink,
diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c
index 1ce4b36ab33b..e0a77671edd6 100644
--- a/drivers/gpu/drm/ttm/ttm_tt.c
+++ b/drivers/gpu/drm/ttm/ttm_tt.c
@@ -449,3 +449,9 @@ ttm_kmap_iter_tt_init(struct ttm_kmap_iter_tt *iter_tt,
 	return &iter_tt->base;
 }
 EXPORT_SYMBOL(ttm_kmap_iter_tt_init);
+
+unsigned long ttm_tt_pages_limit(void)
+{
+	return ttm_pages_limit;
+}
+EXPORT_SYMBOL(ttm_tt_pages_limit);