summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/xe/xe_vm.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2024-03-14 04:34:05 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2024-03-14 04:34:05 +0300
commit480e035fc4c714fb5536e64ab9db04fedc89e910 (patch)
tree01341ee43abe7ecb8efb4e7bbbb1c3b3b50f7ec8 /drivers/gpu/drm/xe/xe_vm.c
parente5e038b7ae9da96b93974bf072ca1876899a01a3 (diff)
parent119b225f01e4d3ce974cd3b4d982c76a380c796d (diff)
downloadlinux-480e035fc4c714fb5536e64ab9db04fedc89e910.tar.xz
Merge tag 'drm-next-2024-03-13' of https://gitlab.freedesktop.org/drm/kernel
Pull drm updates from Dave Airlie: "Highlights are usual, more AMD IP blocks for future hw, i915/xe changes, Displayport tunnelling support for i915, msm YUV over DP changes, new tests for ttm, but its mostly a lot of stuff all over the place from lots of people. core: - EDID cleanups - scheduler error handling fixes - managed: add drmm_release_action() with tests - add ratelimited drm debug print - DPCD PSR early transport macro - DP tunneling and bandwidth allocation helpers - remove built-in edids - dp: Avoid AUX transfers on powered-down displays - dp: Add VSC SDP helpers cross drivers: - use new drm print helpers - switch to ->read_edid callback - gem: add stats for shared buffers plus updates to amdgpu, i915, xe syncobj: - fixes to waiting and sleeping ttm: - add tests - fix errno codes - simply busy-placement handling - fix page decryption media: - tc358743: fix v4l device registration video: - move all kernel parameters for video behind CONFIG_VIDEO sound: - remove <drm/drm_edid.h> include from header ci: - add tests for msm - fix apq8016 runner efifb: - use copy of global screen_info state vesafb: - use copy of global screen_info state simplefb: - fix logging bridge: - ite-6505: fix DP link-training bug - samsung-dsim: fix error checking in probe - samsung-dsim: add bsh-smm-s2/pro boards - tc358767: fix regmap usage - imx: add i.MX8MP HDMI PVI plus DT bindings - imx: add i.MX8MP HDMI TX plus DT bindings - sii902x: fix probing and unregistration - tc358767: limit pixel PLL input range - switch to new drm_bridge_read_edid() interface panel: - ltk050h3146w: error-handling fixes - panel-edp: support delay between power-on and enable; use put_sync in unprepare; support Mediatek MT8173 Chromebooks, BOE NV116WHM-N49 V8.0, BOE NV122WUM-N41, CSO MNC207QS1-1 plus DT bindings - panel-lvds: support EDT ETML0700Z9NDHA plus DT bindings - panel-novatek: FRIDA FRD400B25025-A-CTK plus DT bindings - add BOE TH101MB31IG002-28A plus DT bindings - add EDT ETML1010G3DRA plus DT bindings - add Novatek NT36672E LCD DSI plus DT bindings - nt36523: support 120Hz timings, fix includes - simple: fix display timings on RK32FN48H - visionox-vtdr6130: fix initialization - add Powkiddy RGB10MAX3 plus DT bindings - st7703: support panel rotation plus DT bindings - add Himax HX83112A plus DT bindings - ltk500hd1829: add support for ltk101b4029w and admatec 9904370 - simple: add BOE BP082WX1-100 8.2" panel plus DT bindungs panel-orientation-quirks: - GPD Win Mini amdgpu: - Validate DMABuf imports in compute VMs - Add RAS ACA framework - PSP 13 fixes - Misc code cleanups - Replay fixes - Atom interpretor PS, WS bounds checking - DML2 fixes - Audio fixes - DCN 3.5 Z state fixes - Remove deprecated ida_simple usage - UBSAN fixes - RAS fixes - Enable seq64 infrastructure - DC color block enablement - Documentation updates - DC documentation updates - DMCUB updates - ATHUB 4.1 support - LSDMA 7.0 support - JPEG DPG support - IH 7.0 support - HDP 7.0 support - VCN 5.0 support - SMU 13.0.6 updates - NBIO 7.11 updates - SDMA 6.1 updates - MMHUB 3.3 updates - DCN 3.5.1 support - NBIF 6.3.1 support - VPE 6.1.1 support amdkfd: - Validate DMABuf imports in compute VMs - SVM fixes - Trap handler updates and enhancements - Fix cache size reporting - Relocate the trap handler radeon: - Atom interpretor PS, WS bounds checking - Misc code cleanups xe: - new query for GuC submission version - Remove unused persistent exec_queues - Add vram frequency sysfs attributes - Add the flag XE_VM_BIND_FLAG_DUMPABLE - Drop pre-production workarounds - Drop kunit tests for unsupported platforms - Start pumbling SR-IOV support with memory based interrupts for VF - Allow to map BO in GGTT with PAT index corresponding to XE_CACHE_UC to work with memory based interrupts - Add GuC Doorbells Manager as prep work SR-IOV - Implement additional workarounds for xe2 and MTL - Program a few registers according to perfomance guide spec for Xe2 - Fix remaining 32b build issues and enable it back - Fix build with CONFIG_DEBUG_FS=n - Fix warnings from GuC ABI headers - Introduce Relay Communication for SR-IOV for VF <-> GuC <-> PF - Release mmap mappings on rpm suspend - Disable mid-thread preemption when not properly supported by hardware - Fix xe_exec by reserving extra fence slot for CPU bind - Fix xe_exec with full long running exec queue - Canonicalize addresses where needed for Xe2 and add to devcoredum - Toggle USM support for Xe2 - Only allow 1 ufence per exec / bind IOCTL - Add GuC firmware loading for Lunar Lake - Add XE_VMA_PTE_64K VMA flag i915: - Add more ADL-N PCI IDs - Enable fastboot also on older platforms - Early transport for panel replay and PSR - New ARL PCI IDs - DP TPS4 PHY test pattern support - Unify and improve VSC SDP for PSR and non-PSR cases - Refactor memory regions and improve debug logging - Rework global state serialization - Remove unused CDCLK divider fields - Unify HDCP connector logging format - Use display instead of graphics version in display code - Move VBT and opregion debugfs next to the implementation - Abstract opregion interface, use opaque type - MTL fixes - HPD handling fixes - Add GuC submission interface version query - Atomically invalidate userptr on mmu-notifier - Update handling of MMIO triggered reports - Don't make assumptions about intel_wakeref_t type - Extend driver code of Xe_LPG to Xe_LPG+ - Add flex arrays to struct i915_syncmap - Allow for very slow HuC loading - DP tunneling and bandwidth allocation support msm: - Correct bindings for MSM8976 and SM8650 platforms - Start migration of MDP5 platforms to DPU driver - X1E80100 MDSS support - DPU: - Improve DSC allocation, fixing several important corner cases - Add support for SDM630/SDM660 platforms - Simplify dpu_encoder_phys_ops - Apply fixes targeting DSC support with a single DSC encoder - Apply fixes for HCTL_EN timing configuration - X1E80100 support - Add support for YUV420 over DP - GPU: - fix sc7180 UBWC config - fix a7xx LLC config - new gpu support: a305B, a750, a702 - machine support: SM7150 (different power levels than other a618) - a7xx devcoredump support habanalabs: - configure IRQ affinity according to NUMA node - move HBM MMU page tables inside the HBM - improve device reset - check extended PCIe errors ivpu: - updates to firmware API - refactor BO allocation imx: - use devm_ functions during init hisilicon: - fix EDID includes mgag200: - improve ioremap usage - convert to struct drm_edid - Work around PCI write bursts nouveau: - disp: use kmemdup() - fix EDID includes - documentation fixes qaic: - fixes to BO handling - make use of DRM managed release - fix order of remove operations rockchip: - analogix_dp: get encoder port from DT - inno_hdmi: support HDMI for RK3128 - lvds: error-handling fixes ssd130x: - support SSD133x plus DT bindings tegra: - fix error handling tilcdc: - make use of DRM managed release v3d: - show memory stats in debugfs - Support display MMU page size vc4: - fix error handling in plane prepare_fb - fix framebuffer test in plane helpers virtio: - add venus capset defines vkms: - fix OOB access when programming the LUT - Kconfig improvements vmwgfx: - unmap surface before changing plane state - fix memory leak in error handling - documentation fixes - list command SVGA_3D_CMD_DEFINE_GB_SURFACE_V4 as invalid - fix null-pointer deref in execbuf - refactor display-mode probing - fix fencing for creating cursor MOBs - fix cursor-memory lifetime xlnx: - fix live video input for ZynqMP DPSUB lima: - fix memory leak loongson: - fail if no VRAM present meson: - switch to new drm_bridge_read_edid() interface renesas: - add RZ/G2L DU support plus DT bindings mxsfb: - Use managed mode config sun4i: - HDMI: updates to atomic mode setting mediatek: - Add display driver for MT8188 VDOSYS1 - DSI driver cleanups - Filter modes according to hardware capability - Fix a null pointer crash in mtk_drm_crtc_finish_page_flip etnaviv: - enhancements for NPU and MRT support" * tag 'drm-next-2024-03-13' of https://gitlab.freedesktop.org/drm/kernel: (1420 commits) drm/amd/display: Removed redundant @ symbol to fix kernel-doc warnings in -next repo drm/amd/pm: wait for completion of the EnableGfxImu message drm/amdgpu/soc21: add mode2 asic reset for SMU IP v14.0.1 drm/amdgpu: add smu 14.0.1 support drm/amdgpu: add VPE 6.1.1 discovery support drm/amdgpu/vpe: add VPE 6.1.1 support drm/amdgpu/vpe: don't emit cond exec command under collaborate mode drm/amdgpu/vpe: add collaborate mode support for VPE drm/amdgpu/vpe: add PRED_EXE and COLLAB_SYNC OPCODE drm/amdgpu/vpe: add multi instance VPE support drm/amdgpu/discovery: add nbif v6_3_1 ip block drm/amdgpu: Add nbif v6_3_1 ip block support drm/amdgpu: Add pcie v6_1_0 ip headers (v5) drm/amdgpu: Add nbif v6_3_1 ip headers (v5) arch/powerpc: Remove <linux/fb.h> from backlight code macintosh/via-pmu-backlight: Include <linux/backlight.h> fbdev/chipsfb: Include <linux/backlight.h> drm/etnaviv: Restore some id values drm/amdkfd: make kfd_class constant drm/amdgpu: add ring timeout information in devcoredump ...
Diffstat (limited to 'drivers/gpu/drm/xe/xe_vm.c')
-rw-r--r--drivers/gpu/drm/xe/xe_vm.c199
1 files changed, 197 insertions, 2 deletions
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 3b21afe5b488..d28260351af2 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -13,11 +13,14 @@
#include <drm/ttm/ttm_execbuf_util.h>
#include <drm/ttm/ttm_tt.h>
#include <drm/xe_drm.h>
+#include <linux/ascii85.h>
#include <linux/delay.h>
#include <linux/kthread.h>
#include <linux/mm.h>
#include <linux/swap.h>
+#include <generated/xe_wa_oob.h>
+
#include "xe_assert.h"
#include "xe_bo.h"
#include "xe_device.h"
@@ -34,7 +37,6 @@
#include "xe_res_cursor.h"
#include "xe_sync.h"
#include "xe_trace.h"
-#include "generated/xe_wa_oob.h"
#include "xe_wa.h"
static struct drm_gem_object *xe_vm_obj(struct xe_vm *vm)
@@ -792,6 +794,7 @@ static void xe_vma_free(struct xe_vma *vma)
#define VMA_CREATE_FLAG_READ_ONLY BIT(0)
#define VMA_CREATE_FLAG_IS_NULL BIT(1)
+#define VMA_CREATE_FLAG_DUMPABLE BIT(2)
static struct xe_vma *xe_vma_create(struct xe_vm *vm,
struct xe_bo *bo,
@@ -804,6 +807,7 @@ static struct xe_vma *xe_vma_create(struct xe_vm *vm,
u8 id;
bool read_only = (flags & VMA_CREATE_FLAG_READ_ONLY);
bool is_null = (flags & VMA_CREATE_FLAG_IS_NULL);
+ bool dumpable = (flags & VMA_CREATE_FLAG_DUMPABLE);
xe_assert(vm->xe, start < end);
xe_assert(vm->xe, end < vm->size);
@@ -838,6 +842,8 @@ static struct xe_vma *xe_vma_create(struct xe_vm *vm,
vma->gpuva.va.range = end - start + 1;
if (read_only)
vma->gpuva.flags |= XE_VMA_READ_ONLY;
+ if (dumpable)
+ vma->gpuva.flags |= XE_VMA_DUMPABLE;
for_each_tile(tile, vm->xe, id)
vma->tile_mask |= 0x1 << id;
@@ -1056,7 +1062,9 @@ static int xe_vm_insert_vma(struct xe_vm *vm, struct xe_vma *vma)
xe_assert(vm->xe, xe_vma_vm(vma) == vm);
lockdep_assert_held(&vm->lock);
+ mutex_lock(&vm->snap_mutex);
err = drm_gpuva_insert(&vm->gpuvm, &vma->gpuva);
+ mutex_unlock(&vm->snap_mutex);
XE_WARN_ON(err); /* Shouldn't be possible */
return err;
@@ -1067,7 +1075,9 @@ static void xe_vm_remove_vma(struct xe_vm *vm, struct xe_vma *vma)
xe_assert(vm->xe, xe_vma_vm(vma) == vm);
lockdep_assert_held(&vm->lock);
+ mutex_lock(&vm->snap_mutex);
drm_gpuva_remove(&vma->gpuva);
+ mutex_unlock(&vm->snap_mutex);
if (vm->usm.last_fault_vma == vma)
vm->usm.last_fault_vma = NULL;
}
@@ -1086,7 +1096,7 @@ static struct drm_gpuva_op *xe_vm_op_alloc(void)
static void xe_vm_free(struct drm_gpuvm *gpuvm);
-static struct drm_gpuvm_ops gpuvm_ops = {
+static const struct drm_gpuvm_ops gpuvm_ops = {
.op_alloc = xe_vm_op_alloc,
.vm_bo_validate = xe_gpuvm_validate,
.vm_free = xe_vm_free,
@@ -1294,6 +1304,7 @@ struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags)
vm->flags = flags;
init_rwsem(&vm->lock);
+ mutex_init(&vm->snap_mutex);
INIT_LIST_HEAD(&vm->rebind_list);
@@ -1419,6 +1430,7 @@ err_close:
return ERR_PTR(err);
err_no_resv:
+ mutex_destroy(&vm->snap_mutex);
for_each_tile(tile, xe, id)
xe_range_fence_tree_fini(&vm->rftree[id]);
kfree(vm);
@@ -1543,6 +1555,8 @@ static void vm_destroy_work_func(struct work_struct *w)
/* xe_vm_close_and_put was not called? */
xe_assert(xe, !vm->size);
+ mutex_destroy(&vm->snap_mutex);
+
if (!(vm->flags & XE_VM_FLAG_MIGRATION)) {
xe_device_mem_access_put(xe);
@@ -2155,6 +2169,7 @@ vm_bind_ioctl_ops_create(struct xe_vm *vm, struct xe_bo *bo,
if (__op->op == DRM_GPUVA_OP_MAP) {
op->map.is_null = flags & DRM_XE_VM_BIND_FLAG_NULL;
+ op->map.dumpable = flags & DRM_XE_VM_BIND_FLAG_DUMPABLE;
op->map.pat_index = pat_index;
} else if (__op->op == DRM_GPUVA_OP_PREFETCH) {
op->prefetch.region = prefetch_region;
@@ -2320,6 +2335,7 @@ static int vm_bind_ioctl_ops_parse(struct xe_vm *vm, struct xe_exec_queue *q,
struct xe_sync_entry *syncs, u32 num_syncs,
struct list_head *ops_list, bool last)
{
+ struct xe_device *xe = vm->xe;
struct xe_vma_op *last_op = NULL;
struct drm_gpuva_op *__op;
int err = 0;
@@ -2348,6 +2364,8 @@ static int vm_bind_ioctl_ops_parse(struct xe_vm *vm, struct xe_exec_queue *q,
{
flags |= op->map.is_null ?
VMA_CREATE_FLAG_IS_NULL : 0;
+ flags |= op->map.dumpable ?
+ VMA_CREATE_FLAG_DUMPABLE : 0;
vma = new_vma(vm, &op->base.map, op->map.pat_index,
flags);
@@ -2372,6 +2390,9 @@ static int vm_bind_ioctl_ops_parse(struct xe_vm *vm, struct xe_exec_queue *q,
flags |= op->base.remap.unmap->va->flags &
DRM_GPUVA_SPARSE ?
VMA_CREATE_FLAG_IS_NULL : 0;
+ flags |= op->base.remap.unmap->va->flags &
+ XE_VMA_DUMPABLE ?
+ VMA_CREATE_FLAG_DUMPABLE : 0;
vma = new_vma(vm, op->base.remap.prev,
old->pat_index, flags);
@@ -2393,6 +2414,9 @@ static int vm_bind_ioctl_ops_parse(struct xe_vm *vm, struct xe_exec_queue *q,
xe_vma_end(vma) -
xe_vma_start(old);
op->remap.start = xe_vma_end(vma);
+ vm_dbg(&xe->drm, "REMAP:SKIP_PREV: addr=0x%016llx, range=0x%016llx",
+ (ULL)op->remap.start,
+ (ULL)op->remap.range);
}
}
@@ -2403,6 +2427,9 @@ static int vm_bind_ioctl_ops_parse(struct xe_vm *vm, struct xe_exec_queue *q,
flags |= op->base.remap.unmap->va->flags &
DRM_GPUVA_SPARSE ?
VMA_CREATE_FLAG_IS_NULL : 0;
+ flags |= op->base.remap.unmap->va->flags &
+ XE_VMA_DUMPABLE ?
+ VMA_CREATE_FLAG_DUMPABLE : 0;
vma = new_vma(vm, op->base.remap.next,
old->pat_index, flags);
@@ -2423,6 +2450,9 @@ static int vm_bind_ioctl_ops_parse(struct xe_vm *vm, struct xe_exec_queue *q,
op->remap.range -=
xe_vma_end(old) -
xe_vma_start(vma);
+ vm_dbg(&xe->drm, "REMAP:SKIP_NEXT: addr=0x%016llx, range=0x%016llx",
+ (ULL)op->remap.start,
+ (ULL)op->remap.range);
}
}
break;
@@ -3277,3 +3307,168 @@ int xe_analyze_vm(struct drm_printer *p, struct xe_vm *vm, int gt_id)
return 0;
}
+
+struct xe_vm_snapshot {
+ unsigned long num_snaps;
+ struct {
+ u64 ofs, bo_ofs;
+ unsigned long len;
+ struct xe_bo *bo;
+ void *data;
+ struct mm_struct *mm;
+ } snap[];
+};
+
+struct xe_vm_snapshot *xe_vm_snapshot_capture(struct xe_vm *vm)
+{
+ unsigned long num_snaps = 0, i;
+ struct xe_vm_snapshot *snap = NULL;
+ struct drm_gpuva *gpuva;
+
+ if (!vm)
+ return NULL;
+
+ mutex_lock(&vm->snap_mutex);
+ drm_gpuvm_for_each_va(gpuva, &vm->gpuvm) {
+ if (gpuva->flags & XE_VMA_DUMPABLE)
+ num_snaps++;
+ }
+
+ if (num_snaps)
+ snap = kvzalloc(offsetof(struct xe_vm_snapshot, snap[num_snaps]), GFP_NOWAIT);
+ if (!snap)
+ goto out_unlock;
+
+ snap->num_snaps = num_snaps;
+ i = 0;
+ drm_gpuvm_for_each_va(gpuva, &vm->gpuvm) {
+ struct xe_vma *vma = gpuva_to_vma(gpuva);
+ struct xe_bo *bo = vma->gpuva.gem.obj ?
+ gem_to_xe_bo(vma->gpuva.gem.obj) : NULL;
+
+ if (!(gpuva->flags & XE_VMA_DUMPABLE))
+ continue;
+
+ snap->snap[i].ofs = xe_vma_start(vma);
+ snap->snap[i].len = xe_vma_size(vma);
+ if (bo) {
+ snap->snap[i].bo = xe_bo_get(bo);
+ snap->snap[i].bo_ofs = xe_vma_bo_offset(vma);
+ } else if (xe_vma_is_userptr(vma)) {
+ struct mm_struct *mm =
+ to_userptr_vma(vma)->userptr.notifier.mm;
+
+ if (mmget_not_zero(mm))
+ snap->snap[i].mm = mm;
+ else
+ snap->snap[i].data = ERR_PTR(-EFAULT);
+
+ snap->snap[i].bo_ofs = xe_vma_userptr(vma);
+ } else {
+ snap->snap[i].data = ERR_PTR(-ENOENT);
+ }
+ i++;
+ }
+
+out_unlock:
+ mutex_unlock(&vm->snap_mutex);
+ return snap;
+}
+
+void xe_vm_snapshot_capture_delayed(struct xe_vm_snapshot *snap)
+{
+ for (int i = 0; i < snap->num_snaps; i++) {
+ struct xe_bo *bo = snap->snap[i].bo;
+ struct iosys_map src;
+ int err;
+
+ if (IS_ERR(snap->snap[i].data))
+ continue;
+
+ snap->snap[i].data = kvmalloc(snap->snap[i].len, GFP_USER);
+ if (!snap->snap[i].data) {
+ snap->snap[i].data = ERR_PTR(-ENOMEM);
+ goto cleanup_bo;
+ }
+
+ if (bo) {
+ dma_resv_lock(bo->ttm.base.resv, NULL);
+ err = ttm_bo_vmap(&bo->ttm, &src);
+ if (!err) {
+ xe_map_memcpy_from(xe_bo_device(bo),
+ snap->snap[i].data,
+ &src, snap->snap[i].bo_ofs,
+ snap->snap[i].len);
+ ttm_bo_vunmap(&bo->ttm, &src);
+ }
+ dma_resv_unlock(bo->ttm.base.resv);
+ } else {
+ void __user *userptr = (void __user *)(size_t)snap->snap[i].bo_ofs;
+
+ kthread_use_mm(snap->snap[i].mm);
+ if (!copy_from_user(snap->snap[i].data, userptr, snap->snap[i].len))
+ err = 0;
+ else
+ err = -EFAULT;
+ kthread_unuse_mm(snap->snap[i].mm);
+
+ mmput(snap->snap[i].mm);
+ snap->snap[i].mm = NULL;
+ }
+
+ if (err) {
+ kvfree(snap->snap[i].data);
+ snap->snap[i].data = ERR_PTR(err);
+ }
+
+cleanup_bo:
+ xe_bo_put(bo);
+ snap->snap[i].bo = NULL;
+ }
+}
+
+void xe_vm_snapshot_print(struct xe_vm_snapshot *snap, struct drm_printer *p)
+{
+ unsigned long i, j;
+
+ for (i = 0; i < snap->num_snaps; i++) {
+ if (IS_ERR(snap->snap[i].data))
+ goto uncaptured;
+
+ drm_printf(p, "[%llx].length: 0x%lx\n", snap->snap[i].ofs, snap->snap[i].len);
+ drm_printf(p, "[%llx].data: ",
+ snap->snap[i].ofs);
+
+ for (j = 0; j < snap->snap[i].len; j += sizeof(u32)) {
+ u32 *val = snap->snap[i].data + j;
+ char dumped[ASCII85_BUFSZ];
+
+ drm_puts(p, ascii85_encode(*val, dumped));
+ }
+
+ drm_puts(p, "\n");
+ continue;
+
+uncaptured:
+ drm_printf(p, "Unable to capture range [%llx-%llx]: %li\n",
+ snap->snap[i].ofs, snap->snap[i].ofs + snap->snap[i].len - 1,
+ PTR_ERR(snap->snap[i].data));
+ }
+}
+
+void xe_vm_snapshot_free(struct xe_vm_snapshot *snap)
+{
+ unsigned long i;
+
+ if (!snap)
+ return;
+
+ for (i = 0; i < snap->num_snaps; i++) {
+ if (!IS_ERR(snap->snap[i].data))
+ kvfree(snap->snap[i].data);
+ xe_bo_put(snap->snap[i].bo);
+ if (snap->snap[i].mm)
+ mmput(snap->snap[i].mm);
+ }
+ kvfree(snap);
+}