summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/xe/xe_bo.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2024-07-18 09:34:02 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2024-07-18 09:34:02 -0700
commitb3ce7a30847a54a7f96a35e609303d8afecd460b (patch)
tree81fb53546e55b9c670da4476b4b0b27e57abb25d /drivers/gpu/drm/xe/xe_bo.c
parentb1bc554e009e3aeed7e4cfd2e717c7a34a98c683 (diff)
parent478a52707b0abe98aac7f8c53ccddb759be66b06 (diff)
downloadlwn-b3ce7a30847a54a7f96a35e609303d8afecd460b.tar.gz
lwn-b3ce7a30847a54a7f96a35e609303d8afecd460b.zip
Merge tag 'drm-next-2024-07-18' of https://gitlab.freedesktop.org/drm/kernel
Pull drm updates from Dave Airlie: "There's a lot of stuff in here, amd, i915 and xe have new platform work, lots of core rework around EDID handling, some new COMPILE_TEST options, maintainer changes and a lots of other stuff. Summary: core: - deprecate DRM data and return 0 date - connector: Create a set of helpers to help with HDMI support - Remove driver owner assignments - Allow more drivers to compile with COMPILE_TEST - Conversions to drm_edid - Sprinkle MODULE_DESCRIPTIONS everywhere they are missing - Remove drm_mm_replace_node - print: Add a drm prefix to warn level messages too, remove ___drm_dbg, consolidate prefix handling - New monochrome TV mode variant ttm: - improve number of page faults on some platforms - fix test builds under PREEMPT_RT - more test coverage ci: - Require a more recent version of mesa - improve farm setup and test generation dma-buf: - warn if reserving 0 fence slots - internal API heap enhancements fbdev: - Create memory manager optimized fbdev emulation panic: - Allow to select fonts - improve drm_fb_dma_get_scanout_buffer - Allow to dump kmsg to the screen bridge: - Remove redundant checks on bridge->encoder - Remove drm_bridge_chain_mode_fixup - bridge-connector: Plumb in the new HDMI helper - analogix_dp: Various improvements, handle AUX transfers timeout - samsung-dsim: Fix timings calculation - tc358767: Plenty of small fixes, fix no connector attach, fix clocks - sii902x: state validation improvements panels: - Switch panels from register table initialization to proper code - Now that the panel code tracks the panel state, remove every ad-hoc implementation in the panel drivers - More cleanup of prepare / enable state tracking in drivers - edp: Drop legacy panel compatibles - simple-bridge: Switch to devm_drm_bridge_add - New panels: Lincoln Tech Sol LCD185-101CT, Microtips Technology 13-101HIEBCAF0-C, Microtips Technology MF-103HIEB0GA0, BOE nv110wum-l60, IVO t109nw41, WL-355608-A8, PrimeView PM070WL4, Lincoln Technologies LCD197, Ortustech COM35H3P70ULC, AUO G104STN01, K&d kd101ne3-40ti amdgpu: - DCN 4.0.x support - GC 12.0 support - GMC 12.0 support - SDMA 7.0 support - MES12 support - MMHUB 4.1 support - GFX12 modifier and DCC support - lots of IP fixes/updates amdkfd: - Contiguous VRAM allocations - GC 12.0 support - SDMA 7.0 support - SR-IOV fixes - KFD GFX ALU exceptions i915: - Battlemage Xe2 HPD display enablement - Panel Replay enabling - DP AUX-less ALPM/LOBF - Enable link training failure fallback for DP MST links - CMRR (Content Match Refresh Rate) enabling - Increase ADL-S/ADL-P/DG2+ max TMDS bitrate to 6 Gbps - Enable eDP AUX based HDR backlight - Support replaying GPU hangs with captured context image - Automate CCS Mode setting during engine resets - lots of refactoring - Support replaying GPU hangs with captured context image - Increase FLR timeout from 3s to 9s - Enable w/a 16021333562 for DG2, MTL and ARL [guc] xe: - update MAINATINERS - New uapi adding OA functionality to Xe - expose l3 bank mask - fix display detect on ADL-N - runtime PM Fixes - Fix silent backmerge issues - More prep for SR-IOV - HWmon additions - per client usage info - Rework GPU page fault handling - Drop EXEC_QUEUE_FLAG_BANNED - Add BMG PCI IDs - Scheduler fixes and improvements - Rename xe_exec_queue::compute to xe_exec_queue::lr - Use ttm_uncached for BO with NEEDS_UC flag - Rename xe perf layer as xe observation layer - lots of refactoring radeon: - Backlight workaround for iMac - Silence UBSAN flex array warnings msm: - Validate registers XML description against schema in CI - core/dpu: SM7150 support - mdp5: Add support for MSM8937 - gpu: Add param for userspace to know if raytracing is supported - gpu: X185 support (aka gpu in X1 laptop chips) - gpu: a505 support ivpu: - hardware scheduler support - profiling support - improvements to the platform support layer - firmware handling improvements - clocks/power mgmt improvements - scheduler/logging improvements habanalabs: - Gradual sleep in polling memory macro - Reduce Gaudi2 MSI-X interrupt count to 128 - Add Gaudi2-D revision support - Add timestamp to CPLD info - Gaudi2: Assume hard-reset by firmware upon MC SEI severe error - Align Gaudi2 interrupt names - Check for errors after preboot is ready - Change habanalabs maintainer and git repo path mgag200: - refactoring and improvements - Add BMC output - enable polling nouveau: - add registry command line v3d: - perf counters improvements zynqmp: - irq and debugfs improvements atmel-hlcdc: - Support XLCDC in sam9x7 mipi-dbi: - Remove mipi_dbi_machine_little_endian - make SPI bits per word configurable - support RGB888 - allow pixel formats to be specified in the DT sun4i: - Rework the blender setup for DE2 panfrost: - Enable MT8188 support vc4: - Monochrome TV support exynos: - fix fallback mode regression - fix memory leak - Use drm_edid_duplicate() instead of kmemdup() etnaviv: - fix i.MX8MP NPU clock gating - workaround FE register cdc issues on some cores - fix DMA sync handling for cached buffers - fix job timeout handling - keep TS enabled on MMUv2 cores for improved performance mediatek: - Convert to platform remove callback returning void- - Drop chain_mode_fixup call in mode_valid() - Fixes the errors of MediaTek display driver found by IGT - Add display support for the MT8365-EVK board - Fix bit depth overwritten for mtk_ovl_set bit_depth() - Fix possible_crtcs calculation - Fix spurious kfree() ast: - refactor mode setting code stm: - Add LVDS support - DSI PHY updates" * tag 'drm-next-2024-07-18' of https://gitlab.freedesktop.org/drm/kernel: (2501 commits) drm/amdgpu/mes12: add missing opcode string drm/amdgpu/mes11: update opcode strings Revert "drm/amd/display: Reset freesync config before update new state" drm/omap: Restrict compile testing to PAGE_SIZE less than 64KB drm/xe: Drop trace_xe_hw_fence_free drm/xe/uapi: Rename xe perf layer as xe observation layer drm/amdgpu: remove exp hw support check for gfx12 drm/amdgpu: timely save bad pages to eeprom after gpu ras reset is completed drm/amdgpu: flush all cached ras bad pages to eeprom drm/amdgpu: select compute ME engines dynamically drm/amd/display: Allow display DCC for DCN401 drm/amdgpu: select compute ME engines dynamically drm/amdgpu/job: Replace DRM_INFO/ERROR logging drm/amdgpu: select compute ME engines dynamically drm/amd/pm: Ignore initial value in smu response register drm/amdgpu: Initialize VF partition mode drm/amd/amdgpu: fix SDMA IRQ client ID <-> req mapping MAINTAINERS: fix Xinhui's name MAINTAINERS: update powerplay and swsmu drm/qxl: Pin buffer objects for internal mappings ...
Diffstat (limited to 'drivers/gpu/drm/xe/xe_bo.c')
-rw-r--r--drivers/gpu/drm/xe/xe_bo.c82
1 files changed, 58 insertions, 24 deletions
diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
index b6f3a43d637f..31192d983d9e 100644
--- a/drivers/gpu/drm/xe/xe_bo.c
+++ b/drivers/gpu/drm/xe/xe_bo.c
@@ -25,7 +25,7 @@
#include "xe_pm.h"
#include "xe_preempt_fence.h"
#include "xe_res_cursor.h"
-#include "xe_trace.h"
+#include "xe_trace_bo.h"
#include "xe_ttm_stolen_mgr.h"
#include "xe_vm.h"
@@ -96,6 +96,20 @@ bool xe_bo_is_stolen(struct xe_bo *bo)
}
/**
+ * xe_bo_has_single_placement - check if BO is placed only in one memory location
+ * @bo: The BO
+ *
+ * This function checks whether a given BO is placed in only one memory location.
+ *
+ * Returns: true if the BO is placed in a single memory location, false otherwise.
+ *
+ */
+bool xe_bo_has_single_placement(struct xe_bo *bo)
+{
+ return bo->placement.num_placement == 1;
+}
+
+/**
* xe_bo_is_stolen_devmem - check if BO is of stolen type accessed via PCI BAR
* @bo: The BO
*
@@ -302,6 +316,18 @@ static int xe_tt_map_sg(struct ttm_tt *tt)
return 0;
}
+static void xe_tt_unmap_sg(struct ttm_tt *tt)
+{
+ struct xe_ttm_tt *xe_tt = container_of(tt, struct xe_ttm_tt, ttm);
+
+ if (xe_tt->sg) {
+ dma_unmap_sgtable(xe_tt->dev, xe_tt->sg,
+ DMA_BIDIRECTIONAL, 0);
+ sg_free_table(xe_tt->sg);
+ xe_tt->sg = NULL;
+ }
+}
+
struct sg_table *xe_bo_sg(struct xe_bo *bo)
{
struct ttm_tt *tt = bo->ttm.ttm;
@@ -361,6 +387,15 @@ static struct ttm_tt *xe_ttm_tt_create(struct ttm_buffer_object *ttm_bo,
caching = ttm_write_combined;
}
+ if (bo->flags & XE_BO_FLAG_NEEDS_UC) {
+ /*
+ * Valid only for internally-created buffers only, for
+ * which cpu_caching is never initialized.
+ */
+ xe_assert(xe, bo->cpu_caching == 0);
+ caching = ttm_uncached;
+ }
+
err = ttm_tt_init(&tt->ttm, &bo->ttm, page_flags, caching, extra_pages);
if (err) {
kfree(tt);
@@ -386,27 +421,15 @@ static int xe_ttm_tt_populate(struct ttm_device *ttm_dev, struct ttm_tt *tt,
if (err)
return err;
- /* A follow up may move this xe_bo_move when BO is moved to XE_PL_TT */
- err = xe_tt_map_sg(tt);
- if (err)
- ttm_pool_free(&ttm_dev->pool, tt);
-
return err;
}
static void xe_ttm_tt_unpopulate(struct ttm_device *ttm_dev, struct ttm_tt *tt)
{
- struct xe_ttm_tt *xe_tt = container_of(tt, struct xe_ttm_tt, ttm);
-
if (tt->page_flags & TTM_TT_FLAG_EXTERNAL)
return;
- if (xe_tt->sg) {
- dma_unmap_sgtable(xe_tt->dev, xe_tt->sg,
- DMA_BIDIRECTIONAL, 0);
- sg_free_table(xe_tt->sg);
- xe_tt->sg = NULL;
- }
+ xe_tt_unmap_sg(tt);
return ttm_pool_free(&ttm_dev->pool, tt);
}
@@ -637,17 +660,21 @@ static int xe_bo_move(struct ttm_buffer_object *ttm_bo, bool evict,
bool handle_system_ccs = (!IS_DGFX(xe) && xe_bo_needs_ccs_pages(bo) &&
ttm && ttm_tt_is_populated(ttm)) ? true : false;
int ret = 0;
+
/* Bo creation path, moving to system or TT. */
if ((!old_mem && ttm) && !handle_system_ccs) {
- ttm_bo_move_null(ttm_bo, new_mem);
- return 0;
+ if (new_mem->mem_type == XE_PL_TT)
+ ret = xe_tt_map_sg(ttm);
+ if (!ret)
+ ttm_bo_move_null(ttm_bo, new_mem);
+ goto out;
}
if (ttm_bo->type == ttm_bo_type_sg) {
ret = xe_bo_move_notify(bo, ctx);
if (!ret)
ret = xe_bo_move_dmabuf(ttm_bo, new_mem);
- goto out;
+ return ret;
}
tt_has_data = ttm && (ttm_tt_is_populated(ttm) ||
@@ -659,6 +686,12 @@ static int xe_bo_move(struct ttm_buffer_object *ttm_bo, bool evict,
needs_clear = (ttm && ttm->page_flags & TTM_TT_FLAG_ZERO_ALLOC) ||
(!ttm && ttm_bo->type == ttm_bo_type_device);
+ if (new_mem->mem_type == XE_PL_TT) {
+ ret = xe_tt_map_sg(ttm);
+ if (ret)
+ goto out;
+ }
+
if ((move_lacks_source && !needs_clear)) {
ttm_bo_move_null(ttm_bo, new_mem);
goto out;
@@ -795,8 +828,11 @@ static int xe_bo_move(struct ttm_buffer_object *ttm_bo, bool evict,
xe_pm_runtime_put(xe);
out:
- return ret;
+ if ((!ttm_bo->resource || ttm_bo->resource->mem_type == XE_PL_SYSTEM) &&
+ ttm_bo->ttm)
+ xe_tt_unmap_sg(ttm_bo->ttm);
+ return ret;
}
/**
@@ -1740,11 +1776,10 @@ void xe_bo_unpin_external(struct xe_bo *bo)
xe_assert(xe, xe_bo_is_pinned(bo));
xe_assert(xe, xe_bo_is_user(bo));
- if (bo->ttm.pin_count == 1 && !list_empty(&bo->pinned_link)) {
- spin_lock(&xe->pinned.lock);
+ spin_lock(&xe->pinned.lock);
+ if (bo->ttm.pin_count == 1 && !list_empty(&bo->pinned_link))
list_del_init(&bo->pinned_link);
- spin_unlock(&xe->pinned.lock);
- }
+ spin_unlock(&xe->pinned.lock);
ttm_bo_unpin(&bo->ttm);
@@ -1767,9 +1802,8 @@ void xe_bo_unpin(struct xe_bo *bo)
struct ttm_place *place = &(bo->placements[0]);
if (mem_type_is_vram(place->mem_type)) {
- xe_assert(xe, !list_empty(&bo->pinned_link));
-
spin_lock(&xe->pinned.lock);
+ xe_assert(xe, !list_empty(&bo->pinned_link));
list_del_init(&bo->pinned_link);
spin_unlock(&xe->pinned.lock);
}