summaryrefslogtreecommitdiffstats
path: root/drivers/gpu/drm/amd/amdkfd/kfd_device.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2018-12-25 11:48:26 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2018-12-25 11:48:26 -0800
commit4971f090aa7f6ce5daa094ce4334f6618f93a7eb (patch)
tree45d75782b7dedbec76a3ab82d2769f7707668071 /drivers/gpu/drm/amd/amdkfd/kfd_device.c
parentc76cd634eb5bfd497617ea224a54a03b545c8c4d (diff)
parent2a3c83f5fe0770d13bbb71b23674886ff4111f44 (diff)
Merge tag 'drm-next-2018-12-14' of git://anongit.freedesktop.org/drm/drm
Pull drm updates from Dave Airlie: "Core: - shared fencing staging removal - drop transactional atomic helpers and move helpers to new location - DP/MST atomic cleanup - Leasing cleanups and drop EXPORT_SYMBOL - Convert drivers to atomic helpers and generic fbdev. - removed deprecated obj_ref/unref in favour of get/put - Improve dumb callback documentation - MODESET_LOCK_BEGIN/END helpers panels: - CDTech panels, Banana Pi Panel, DLC1010GIG, - Olimex LCD-O-LinuXino, Samsung S6D16D0, Truly NT35597 WQXGA, - Himax HX8357D, simulated RTSM AEMv8. - GPD Win2 panel - AUO G101EVN010 vgem: - render node support ttm: - move global init out of drivers - fix LRU handling for ghost objects - Support for simultaneous submissions to multiple engines scheduler: - timeout/fault handling changes to help GPU recovery - helpers for hw with preemption support i915: - Scaler/Watermark fixes - DP MST + powerwell fixes - PSR fixes - Break long get/put shmemfs pages - Icelake fixes - Icelake DSI video mode enablement - Engine workaround improvements amdgpu: - freesync support - GPU reset enabled on CI, VI, SOC15 dGPUs - ABM support in DC - KFD support for vega12/polaris12 - SDMA paging queue on vega - More amdkfd code sharing - DCC scanout on GFX9 - DC kerneldoc - Updated SMU firmware for GFX8 chips - XGMI PSP + hive reset support - GPU reset - DC trace support - Powerplay updates for newer Polaris - Cursor plane update fast path - kfd dma-buf support virtio-gpu: - add EDID support vmwgfx: - pageflip with damage support nouveau: - Initial Turing TU104/TU106 modesetting support msm: - a2xx gpu support for apq8060 and imx5 - a2xx gpummu support - mdp4 display support for apq8060 - DPU fixes and cleanups - enhanced profiling support - debug object naming interface - get_iova/page pinning decoupling tegra: - Tegra194 host1x, VIC and display support enabled - Audio over HDMI for Tegra186 and Tegra194 exynos: - DMA/IOMMU refactoring - plane alpha + blend mode support - Color format fixes for mixer driver rcar-du: - R8A7744 and R8A77470 support - R8A77965 LVDS support imx: - fbdev emulation fix - multi-tiled scalling fixes - SPDX identifiers rockchip - dw_hdmi support - dw-mipi-dsi + dual dsi support - mailbox read size fix qxl: - fix cursor pinning vc4: - YUV support (scaling + cursor) v3d: - enable TFU (Texture Formatting Unit) mali-dp: - add support for linear tiled formats sun4i: - Display Engine 3 support - H6 DE3 mixer 0 support - H6 display engine support - dw-hdmi support - H6 HDMI phy support - implicit fence waiting - BGRX8888 support meson: - Overlay plane support - implicit fence waiting - HDMI 1.4 4k modes bridge: - i2c fixes for sii902x" * tag 'drm-next-2018-12-14' of git://anongit.freedesktop.org/drm/drm: (1403 commits) drm/amd/display: Add fast path for cursor plane updates drm/amdgpu: Enable GPU recovery by default for CI drm/amd/display: Fix duplicating scaling/underscan connector state drm/amd/display: Fix unintialized max_bpc state values Revert "drm/amd/display: Set RMX_ASPECT as default" drm/amdgpu: Fix stub function name drm/msm/dpu: Fix clock issue after bind failure drm/msm/dpu: Clean up dpu_media_info.h static inline functions drm/msm/dpu: Further cleanups for static inline functions drm/msm/dpu: Cleanup the debugfs functions drm/msm/dpu: Remove dpu_irq and unused functions drm/msm: Make irq_postinstall optional drm/msm/dpu: Cleanup callers of dpu_hw_blk_init drm/msm/dpu: Remove unused functions drm/msm/dpu: Remove dpu_crtc_is_enabled() drm/msm/dpu: Remove dpu_crtc_get_mixer_height drm/msm/dpu: Remove dpu_dbg drm/msm: dpu: Remove crtc_lock drm/msm: dpu: Remove vblank_requested flag from dpu_crtc drm/msm: dpu: Separate crtc assignment from vblank enable ...
Diffstat (limited to 'drivers/gpu/drm/amd/amdkfd/kfd_device.c')
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_device.c57
1 files changed, 52 insertions, 5 deletions
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index e4ded890b1cb..8be9677c0c07 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -28,6 +28,7 @@
#include "kfd_pm4_headers_vi.h"
#include "cwsr_trap_handler.h"
#include "kfd_iommu.h"
+#include "amdgpu_amdkfd.h"
#define MQD_SIZE_ALIGNED 768
@@ -204,6 +205,22 @@ static const struct kfd_device_info polaris11_device_info = {
.num_sdma_queues_per_engine = 2,
};
+static const struct kfd_device_info polaris12_device_info = {
+ .asic_family = CHIP_POLARIS12,
+ .max_pasid_bits = 16,
+ .max_no_of_hqd = 24,
+ .doorbell_size = 4,
+ .ih_ring_entry_size = 4 * sizeof(uint32_t),
+ .event_interrupt_class = &event_interrupt_class_cik,
+ .num_of_watch_points = 4,
+ .mqd_size_aligned = MQD_SIZE_ALIGNED,
+ .supports_cwsr = true,
+ .needs_iommu_device = false,
+ .needs_pci_atomics = true,
+ .num_sdma_engines = 2,
+ .num_sdma_queues_per_engine = 2,
+};
+
static const struct kfd_device_info vega10_device_info = {
.asic_family = CHIP_VEGA10,
.max_pasid_bits = 16,
@@ -236,6 +253,22 @@ static const struct kfd_device_info vega10_vf_device_info = {
.num_sdma_queues_per_engine = 2,
};
+static const struct kfd_device_info vega12_device_info = {
+ .asic_family = CHIP_VEGA12,
+ .max_pasid_bits = 16,
+ .max_no_of_hqd = 24,
+ .doorbell_size = 8,
+ .ih_ring_entry_size = 8 * sizeof(uint32_t),
+ .event_interrupt_class = &event_interrupt_class_v9,
+ .num_of_watch_points = 4,
+ .mqd_size_aligned = MQD_SIZE_ALIGNED,
+ .supports_cwsr = true,
+ .needs_iommu_device = false,
+ .needs_pci_atomics = false,
+ .num_sdma_engines = 2,
+ .num_sdma_queues_per_engine = 2,
+};
+
static const struct kfd_device_info vega20_device_info = {
.asic_family = CHIP_VEGA20,
.max_pasid_bits = 16,
@@ -330,6 +363,14 @@ static const struct kfd_deviceid supported_devices[] = {
{ 0x67EB, &polaris11_device_info }, /* Polaris11 */
{ 0x67EF, &polaris11_device_info }, /* Polaris11 */
{ 0x67FF, &polaris11_device_info }, /* Polaris11 */
+ { 0x6980, &polaris12_device_info }, /* Polaris12 */
+ { 0x6981, &polaris12_device_info }, /* Polaris12 */
+ { 0x6985, &polaris12_device_info }, /* Polaris12 */
+ { 0x6986, &polaris12_device_info }, /* Polaris12 */
+ { 0x6987, &polaris12_device_info }, /* Polaris12 */
+ { 0x6995, &polaris12_device_info }, /* Polaris12 */
+ { 0x6997, &polaris12_device_info }, /* Polaris12 */
+ { 0x699F, &polaris12_device_info }, /* Polaris12 */
{ 0x6860, &vega10_device_info }, /* Vega10 */
{ 0x6861, &vega10_device_info }, /* Vega10 */
{ 0x6862, &vega10_device_info }, /* Vega10 */
@@ -345,6 +386,11 @@ static const struct kfd_deviceid supported_devices[] = {
{ 0x686E, &vega10_device_info }, /* Vega10 */
{ 0x686F, &vega10_device_info }, /* Vega10 */
{ 0x687F, &vega10_device_info }, /* Vega10 */
+ { 0x69A0, &vega12_device_info }, /* Vega12 */
+ { 0x69A1, &vega12_device_info }, /* Vega12 */
+ { 0x69A2, &vega12_device_info }, /* Vega12 */
+ { 0x69A3, &vega12_device_info }, /* Vega12 */
+ { 0x69AF, &vega12_device_info }, /* Vega12 */
{ 0x66a0, &vega20_device_info }, /* Vega20 */
{ 0x66a1, &vega20_device_info }, /* Vega20 */
{ 0x66a2, &vega20_device_info }, /* Vega20 */
@@ -485,7 +531,7 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd,
/* add another 512KB for all other allocations on gart (HPD, fences) */
size += 512 * 1024;
- if (kfd->kfd2kgd->init_gtt_mem_allocation(
+ if (amdgpu_amdkfd_alloc_gtt_mem(
kfd->kgd, size, &kfd->gtt_mem,
&kfd->gtt_start_gpu_addr, &kfd->gtt_start_cpu_ptr,
false)) {
@@ -559,7 +605,7 @@ kfd_topology_add_device_error:
kfd_doorbell_error:
kfd_gtt_sa_fini(kfd);
kfd_gtt_sa_init_error:
- kfd->kfd2kgd->free_gtt_mem(kfd->kgd, kfd->gtt_mem);
+ amdgpu_amdkfd_free_gtt_mem(kfd->kgd, kfd->gtt_mem);
dev_err(kfd_device,
"device %x:%x NOT added due to errors\n",
kfd->pdev->vendor, kfd->pdev->device);
@@ -576,7 +622,7 @@ void kgd2kfd_device_exit(struct kfd_dev *kfd)
kfd_topology_remove_device(kfd);
kfd_doorbell_fini(kfd);
kfd_gtt_sa_fini(kfd);
- kfd->kfd2kgd->free_gtt_mem(kfd->kgd, kfd->gtt_mem);
+ amdgpu_amdkfd_free_gtt_mem(kfd->kgd, kfd->gtt_mem);
}
kfree(kfd);
@@ -688,6 +734,7 @@ void kgd2kfd_interrupt(struct kfd_dev *kfd, const void *ih_ring_entry)
{
uint32_t patched_ihre[KFD_MAX_RING_ENTRY_SIZE];
bool is_patched = false;
+ unsigned long flags;
if (!kfd->init_complete)
return;
@@ -697,7 +744,7 @@ void kgd2kfd_interrupt(struct kfd_dev *kfd, const void *ih_ring_entry)
return;
}
- spin_lock(&kfd->interrupt_lock);
+ spin_lock_irqsave(&kfd->interrupt_lock, flags);
if (kfd->interrupts_active
&& interrupt_is_wanted(kfd, ih_ring_entry,
@@ -706,7 +753,7 @@ void kgd2kfd_interrupt(struct kfd_dev *kfd, const void *ih_ring_entry)
is_patched ? patched_ihre : ih_ring_entry))
queue_work(kfd->ih_wq, &kfd->interrupt_work);
- spin_unlock(&kfd->interrupt_lock);
+ spin_unlock_irqrestore(&kfd->interrupt_lock, flags);
}
int kgd2kfd_quiesce_mm(struct mm_struct *mm)