summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2023-08-30 13:34:34 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2023-08-30 13:34:34 -0700
commit461f35f014466c4e26dca6be0f431f57297df3f2 (patch)
tree0bd2fded69ba0752ca16c304d3e1880d5f1eb30b /drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
parent53ea7f624fb91074c2f9458832ed74975ee5d64c (diff)
parent3698a75f5a98d0a6599e2878ab25d30a82dd836a (diff)
Merge tag 'drm-next-2023-08-30' of git://anongit.freedesktop.org/drm/drm
Pull drm updates from Dave Airlie: "The drm core grew a new generic gpu virtual address manager, and new execution locking helpers. These are used by nouveau now to provide uAPI support for the userspace Vulkan driver. AMD had a bunch of new IP core support, loads of refactoring around fbdev, but mostly just the usual amount of stuff across the board. core: - fix gfp flags in drmm_kmalloc gpuva: - add new generic GPU VA manager (for nouveau initially) syncobj: - add new DRM_IOCTL_SYNCOBJ_EVENTFD ioctl dma-buf: - acquire resv lock for mmap() in exporters - support dma-buf self import automatically - docs fixes backlight: - fix fbdev interactions atomic: - improve logging prime: - remove struct gem_prim_mmap plus driver updates gem: - drm_exec: add locking over multiple GEM objects - fix lockdep checking fbdev: - make fbdev userspace interfaces optional - use linux device instead of fbdev device - use deferred i/o helper macros in various drivers - Make FB core selectable without drivers - Remove obsolete flags FBINFO_DEFAULT and FBINFO_FLAG_DEFAULT - Add helper macros and Kconfig tokens for DMA-allocated framebuffer ttm: - support init_on_free - swapout fixes panel: - panel-edp: Support AUO B116XAB01.4 - Support Visionox R66451 plus DT bindings - ld9040: - Backlight support - magic improved - Kconfig fix - Convert to of_device_get_match_data() - Fix Kconfig dependencies - simple: - Set bpc value to fix warning - Set connector type for AUO T215HVN01 - Support Innolux G156HCE-L01 plus DT bindings - ili9881: Support TDO TL050HDV35 LCD panel plus DT bindings - startek: Support KD070FHFID015 MIPI-DSI panel plus DT bindings - sitronix-st7789v: - Support Inanbo T28CP45TN89 plus DT bindings - Support EDT ET028013DMA plus DT bindings - Various cleanups - edp: Add timings for N140HCA-EAC - Allow panels and touchscreens to power sequence together - Fix Innolux G156HCE-L01 LVDS clock bridge: - debugfs for chains support - dw-hdmi: - Improve support for YUV420 bus format - CEC suspend/resume - update EDID on HDMI detect - dw-mipi-dsi: Fix enable/disable of DSI controller - lt9611uxc: Use MODULE_FIRMWARE() - ps8640: Remove broken EDID code - samsung-dsim: Fix command transfer - tc358764: - Handle HS/VS polarity - Use BIT() macro - Various cleanups - adv7511: Fix low refresh rate - anx7625: - Switch to macros instead of hardcoded values - locking fixes - tc358767: fix hardware delays - sitronix-st7789v: - Support panel orientation - Support rotation property - Add support for Jasonic JT240MHQS-HWT-EK-E3 plus DT bindings amdgpu: - SDMA 6.1.0 support - HDP 6.1 support - SMUIO 14.0 support - PSP 14.0 support - IH 6.1 support - Lots of checkpatch cleanups - GFX 9.4.3 updates - Add USB PD and IFWI flashing documentation - GPUVM updates - RAS fixes - DRR fixes - FAMS fixes - Virtual display fixes - Soft IH fixes - SMU13 fixes - Rework PSP firmware loading for other IPs - Kernel doc fixes - DCN 3.0.1 fixes - LTTPR fixes - DP MST fixes - DCN 3.1.6 fixes - SMU 13.x fixes - PSP 13.x fixes - SubVP fixes - GC 9.4.3 fixes - Display bandwidth calculation fixes - VCN4 secure submission fixes - Allow building DC on RISC-V - Add visible FB info to bo_print_info - HBR3 fixes - GFX9 MCBP fix - GMC10 vmhub index fix - GMC11 vmhub index fix - Create a new doorbell manager - SR-IOV fixes - initial freesync panel replay support - revert zpos properly until igt regression is fixeed - use TTM to manage doorbell BAR - Expose both current and average power via hwmon if supported amdkfd: - Cleanup CRIU dma-buf handling - Use KIQ to unmap HIQ - GFX 9.4.3 debugger updates - GFX 9.4.2 debugger fixes - Enable cooperative groups fof gfx11 - SVM fixes - Convert older APUs to use dGPU path like newer APUs - Drop IOMMUv2 path as it is no longer used - TBA fix for aldebaran i915: - ICL+ DSI modeset sequence - HDCP improvements - MTL display fixes and cleanups - HSW/BDW PSR1 restored - Init DDI ports in VBT order - General display refactors - Start using plane scale factor for relative data rate - Use shmem for dpt objects - Expose RPS thresholds in sysfs - Apply GuC SLPC min frequency softlimit correctly - Extend Wa_14015795083 to TGL, RKL, DG1 and ADL - Fix a VMA UAF for multi-gt platform - Do not use stolen on MTL due to HW bug - Check HuC and GuC version compatibility on MTL - avoid infinite GPU waits due to premature release of request memory - Fixes and updates for GSC memory allocation - Display SDVO fixes - Take stolen handling out of FBC code - Make i915_coherent_map_type GT-centric - Simplify shmem_create_from_object map_type msm: - SM6125 MDSS support - DPU: SM6125 DPU support - DSI: runtime PM support, burst mode support - DSI PHY: SM6125 support in 14nm DSI PHY driver - GPU: prepare for a7xx - fix a690 firmware - disable relocs on a6xx and newer radeon: - Lots of checkpatch cleanups ast: - improve device-model detection - Represent BMV as virtual connector - Report DP connection status nouveau: - add new exec/bind interface to support Vulkan - document some getparam ioctls - improve VRAM detection - various fixes/cleanups - workraound DPCD issues ivpu: - MMU updates - debugfs support - Support vpu4 virtio: - add sync object support atmel-hlcdc: - Support inverted pixclock polarity etnaviv: - runtime PM cleanups - hang handling fixes exynos: - use fbdev DMA helpers - fix possible NULL ptr dereference komeda: - always attach encoder omapdrm: - use fbdev DMA helpers ingenic: - kconfig regmap fixes loongson: - support display controller mediatek: - Small mtk-dpi cleanups - DisplayPort: support eDP and aux-bus - Fix coverity issues - Fix potential memory leak if vmap() fail mgag200: - minor fixes mxsfb: - support disabling overlay planes panfrost: - fix sync in IRQ handling ssd130x: - Support per-controller default resolution plus DT bindings - Reduce memory-allocation overhead - Improve intermediate buffer size computation - Fix allocation of temporary buffers - Fix pitch computation - Fix shadow plane allocation tegra: - use fbdev DMA helpers - Convert to devm_platform_ioremap_resource() - support bridge/connector - enable PM tidss: - Support TI AM625 plus DT bindings - Implement new connector model plus driver updates vkms: - improve write back support - docs fixes - support gamma LUT zynqmp-dpsub: - misc fixes" * tag 'drm-next-2023-08-30' of git://anongit.freedesktop.org/drm/drm: (1327 commits) drm/gpuva_mgr: remove unused prev pointer in __drm_gpuva_sm_map() drm/tests/drm_kunit_helpers: Place correct function name in the comment header drm/nouveau: uapi: don't pass NO_PREFETCH flag implicitly drm/nouveau: uvmm: fix unset region pointer on remap drm/nouveau: sched: avoid job races between entities drm/i915: Fix HPD polling, reenabling the output poll work as needed drm: Add an HPD poll helper to reschedule the poll work drm/i915: Fix TLB-Invalidation seqno store drm/ttm/tests: Fix type conversion in ttm_pool_test drm/msm/a6xx: Bail out early if setting GPU OOB fails drm/msm/a6xx: Move LLC accessors to the common header drm/msm/a6xx: Introduce a6xx_llc_read drm/ttm/tests: Require MMU when testing drm/panel: simple: Fix Innolux G156HCE-L01 LVDS clock Revert "Revert "drm/amdgpu/display: change pipe policy for DCN 2.0"" drm/amdgpu: Add memory vendor information drm/amd: flush any delayed gfxoff on suspend entry drm/amdgpu: skip fence GFX interrupts disable/enable for S0ix drm/amdgpu: Remove gfxoff check in GFX v9.4.3 drm/amd/pm: Update pci link speed for smu v13.0.6 ...
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c')
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c115
1 files changed, 57 insertions, 58 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index 74055cba3dc9..ca4d2d430e28 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -33,6 +33,7 @@
#include <drm/amdgpu_drm.h>
#include <drm/drm_drv.h>
+#include <drm/drm_exec.h>
#include <drm/drm_gem_ttm_helper.h>
#include <drm/ttm/ttm_tt.h>
@@ -181,11 +182,10 @@ static int amdgpu_gem_object_open(struct drm_gem_object *obj,
return r;
bo_va = amdgpu_vm_bo_find(vm, abo);
- if (!bo_va) {
+ if (!bo_va)
bo_va = amdgpu_vm_bo_add(adev, vm, abo);
- } else {
+ else
++bo_va->ref_count;
- }
amdgpu_bo_unreserve(abo);
return 0;
}
@@ -198,29 +198,24 @@ static void amdgpu_gem_object_close(struct drm_gem_object *obj,
struct amdgpu_fpriv *fpriv = file_priv->driver_priv;
struct amdgpu_vm *vm = &fpriv->vm;
- struct amdgpu_bo_list_entry vm_pd;
- struct list_head list, duplicates;
struct dma_fence *fence = NULL;
- struct ttm_validate_buffer tv;
- struct ww_acquire_ctx ticket;
struct amdgpu_bo_va *bo_va;
+ struct drm_exec exec;
long r;
- INIT_LIST_HEAD(&list);
- INIT_LIST_HEAD(&duplicates);
-
- tv.bo = &bo->tbo;
- tv.num_shared = 2;
- list_add(&tv.head, &list);
-
- amdgpu_vm_get_pd_bo(vm, &list, &vm_pd);
-
- r = ttm_eu_reserve_buffers(&ticket, &list, false, &duplicates);
- if (r) {
- dev_err(adev->dev, "leaking bo va because "
- "we fail to reserve bo (%ld)\n", r);
- return;
+ drm_exec_init(&exec, DRM_EXEC_IGNORE_DUPLICATES);
+ drm_exec_until_all_locked(&exec) {
+ r = drm_exec_prepare_obj(&exec, &bo->tbo.base, 1);
+ drm_exec_retry_on_contention(&exec);
+ if (unlikely(r))
+ goto out_unlock;
+
+ r = amdgpu_vm_lock_pd(vm, &exec, 0);
+ drm_exec_retry_on_contention(&exec);
+ if (unlikely(r))
+ goto out_unlock;
}
+
bo_va = amdgpu_vm_bo_find(vm, bo);
if (!bo_va || --bo_va->ref_count)
goto out_unlock;
@@ -230,6 +225,9 @@ static void amdgpu_gem_object_close(struct drm_gem_object *obj,
goto out_unlock;
r = amdgpu_vm_clear_freed(adev, vm, &fence);
+ if (unlikely(r < 0))
+ dev_err(adev->dev, "failed to clear page "
+ "tables on GEM object close (%ld)\n", r);
if (r || !fence)
goto out_unlock;
@@ -237,10 +235,9 @@ static void amdgpu_gem_object_close(struct drm_gem_object *obj,
dma_fence_put(fence);
out_unlock:
- if (unlikely(r < 0))
- dev_err(adev->dev, "failed to clear page "
- "tables on GEM object close (%ld)\n", r);
- ttm_eu_backoff_reservation(&ticket, &list);
+ if (r)
+ dev_err(adev->dev, "leaking bo va (%ld)\n", r);
+ drm_exec_fini(&exec);
}
static int amdgpu_gem_object_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma)
@@ -292,6 +289,10 @@ int amdgpu_gem_create_ioctl(struct drm_device *dev, void *data,
uint32_t handle, initial_domain;
int r;
+ /* reject DOORBELLs until userspace code to use it is available */
+ if (args->in.domains & AMDGPU_GEM_DOMAIN_DOORBELL)
+ return -EINVAL;
+
/* reject invalid gem flags */
if (flags & ~(AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED |
AMDGPU_GEM_CREATE_NO_CPU_ACCESS |
@@ -463,9 +464,9 @@ int amdgpu_mode_dumb_mmap(struct drm_file *filp,
struct amdgpu_bo *robj;
gobj = drm_gem_object_lookup(filp, handle);
- if (gobj == NULL) {
+ if (!gobj)
return -ENOENT;
- }
+
robj = gem_to_amdgpu_bo(gobj);
if (amdgpu_ttm_tt_get_usermm(robj->tbo.ttm) ||
(robj->flags & AMDGPU_GEM_CREATE_NO_CPU_ACCESS)) {
@@ -482,6 +483,7 @@ int amdgpu_gem_mmap_ioctl(struct drm_device *dev, void *data,
{
union drm_amdgpu_gem_mmap *args = data;
uint32_t handle = args->in.handle;
+
memset(args, 0, sizeof(*args));
return amdgpu_mode_dumb_mmap(filp, dev, handle, &args->out.addr_ptr);
}
@@ -508,7 +510,7 @@ unsigned long amdgpu_gem_timeout(uint64_t timeout_ns)
timeout_jiffies = nsecs_to_jiffies(ktime_to_ns(timeout));
/* clamp timeout to avoid unsigned-> signed overflow */
- if (timeout_jiffies > MAX_SCHEDULE_TIMEOUT )
+ if (timeout_jiffies > MAX_SCHEDULE_TIMEOUT)
return MAX_SCHEDULE_TIMEOUT - 1;
return timeout_jiffies;
@@ -526,9 +528,9 @@ int amdgpu_gem_wait_idle_ioctl(struct drm_device *dev, void *data,
long ret;
gobj = drm_gem_object_lookup(filp, handle);
- if (gobj == NULL) {
+ if (!gobj)
return -ENOENT;
- }
+
robj = gem_to_amdgpu_bo(gobj);
ret = dma_resv_wait_timeout(robj->tbo.base.resv, DMA_RESV_USAGE_READ,
true, timeout);
@@ -555,7 +557,7 @@ int amdgpu_gem_metadata_ioctl(struct drm_device *dev, void *data,
struct amdgpu_bo *robj;
int r = -1;
- DRM_DEBUG("%d \n", args->handle);
+ DRM_DEBUG("%d\n", args->handle);
gobj = drm_gem_object_lookup(filp, args->handle);
if (gobj == NULL)
return -ENOENT;
@@ -675,17 +677,14 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data,
struct amdgpu_fpriv *fpriv = filp->driver_priv;
struct amdgpu_bo *abo;
struct amdgpu_bo_va *bo_va;
- struct amdgpu_bo_list_entry vm_pd;
- struct ttm_validate_buffer tv;
- struct ww_acquire_ctx ticket;
- struct list_head list, duplicates;
+ struct drm_exec exec;
uint64_t va_flags;
uint64_t vm_size;
int r = 0;
if (args->va_address < AMDGPU_VA_RESERVED_SIZE) {
dev_dbg(dev->dev,
- "va_address 0x%LX is in reserved area 0x%LX\n",
+ "va_address 0x%llx is in reserved area 0x%llx\n",
args->va_address, AMDGPU_VA_RESERVED_SIZE);
return -EINVAL;
}
@@ -693,7 +692,7 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data,
if (args->va_address >= AMDGPU_GMC_HOLE_START &&
args->va_address < AMDGPU_GMC_HOLE_END) {
dev_dbg(dev->dev,
- "va_address 0x%LX is in VA hole 0x%LX-0x%LX\n",
+ "va_address 0x%llx is in VA hole 0x%llx-0x%llx\n",
args->va_address, AMDGPU_GMC_HOLE_START,
AMDGPU_GMC_HOLE_END);
return -EINVAL;
@@ -728,36 +727,38 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data,
return -EINVAL;
}
- INIT_LIST_HEAD(&list);
- INIT_LIST_HEAD(&duplicates);
if ((args->operation != AMDGPU_VA_OP_CLEAR) &&
!(args->flags & AMDGPU_VM_PAGE_PRT)) {
gobj = drm_gem_object_lookup(filp, args->handle);
if (gobj == NULL)
return -ENOENT;
abo = gem_to_amdgpu_bo(gobj);
- tv.bo = &abo->tbo;
- if (abo->flags & AMDGPU_GEM_CREATE_VM_ALWAYS_VALID)
- tv.num_shared = 1;
- else
- tv.num_shared = 0;
- list_add(&tv.head, &list);
} else {
gobj = NULL;
abo = NULL;
}
- amdgpu_vm_get_pd_bo(&fpriv->vm, &list, &vm_pd);
+ drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT |
+ DRM_EXEC_IGNORE_DUPLICATES);
+ drm_exec_until_all_locked(&exec) {
+ if (gobj) {
+ r = drm_exec_lock_obj(&exec, gobj);
+ drm_exec_retry_on_contention(&exec);
+ if (unlikely(r))
+ goto error;
+ }
- r = ttm_eu_reserve_buffers(&ticket, &list, true, &duplicates);
- if (r)
- goto error_unref;
+ r = amdgpu_vm_lock_pd(&fpriv->vm, &exec, 2);
+ drm_exec_retry_on_contention(&exec);
+ if (unlikely(r))
+ goto error;
+ }
if (abo) {
bo_va = amdgpu_vm_bo_find(&fpriv->vm, abo);
if (!bo_va) {
r = -ENOENT;
- goto error_backoff;
+ goto error;
}
} else if (args->operation != AMDGPU_VA_OP_CLEAR) {
bo_va = fpriv->prt_va;
@@ -794,10 +795,8 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data,
amdgpu_gem_va_update_vm(adev, &fpriv->vm, bo_va,
args->operation);
-error_backoff:
- ttm_eu_backoff_reservation(&ticket, &list);
-
-error_unref:
+error:
+ drm_exec_fini(&exec);
drm_gem_object_put(gobj);
return r;
}
@@ -813,9 +812,9 @@ int amdgpu_gem_op_ioctl(struct drm_device *dev, void *data,
int r;
gobj = drm_gem_object_lookup(filp, args->handle);
- if (gobj == NULL) {
+ if (!gobj)
return -ENOENT;
- }
+
robj = gem_to_amdgpu_bo(gobj);
r = amdgpu_bo_reserve(robj, false);
@@ -941,9 +940,9 @@ int amdgpu_mode_dumb_create(struct drm_file *file_priv,
r = drm_gem_handle_create(file_priv, gobj, &handle);
/* drop reference from allocate - handle holds it now */
drm_gem_object_put(gobj);
- if (r) {
+ if (r)
return r;
- }
+
args->handle = handle;
return 0;
}