Pull drm fixes from Dave Airlie:
 "Fixes for rc2, the usual amdgpu/xe double header, I think xe had a
  couple of weeks combined due to some maintainer access issues,
  otherwise there's just a few misc fixes and documentation fixups.

  core and helpers:
   - calculate framebuffer geometry with format helpers
   - fix docs

  amdgpu:
   - GFX12 fix for CONFIG_DRM_DEBUG_MM configs
   - Fix DC analog support
   - Userq fixes
   - GART placement fix
   - Aldebaran SMU fixes
   - AMDGPU_INFO_READ_MMR_REG fix
   - UVD 3.1 fix
   - GC 6 TCC fix
   - Fix root reservation in amdgpu_vm_handle_fault()
   - RAS fix
   - Module reload fix for APUs
   - Fix build for CONFIG_DRM_FBDEV_EMULATION=n
   - IGT DWB regression fix
   - GC 11.5.4 fix
   - VCN user fence fixes
   - JPEG user fence fixes
   - SMU 13.0.6 fix
   - VCN 3/4 IB parser fixes
   - NV3x+ dGPU vblank fix
   - DCE6/8 fixes for LVDS/eDP panels without an EDID

  amdkfd:
   - Fix for when CONFIG_HSA_AMD is not set
   - SVM fixes

  xe:
   - uapi: Add missing pad and extensions check
   - uapi: Reject unsafe PAT indices for CPU cached memory
   - Drop registration of guc_submit_wedged_fini from xe_guc_submit_wedge
   - Xe3p tuning and workaround fixes
   - USE drm mm instead of drm SA for CCS read/write
   - Fix leaks and null derefs
   - Fix Wa_18022495364

  appletbdrm:
   - allocate protocol buffers with kvzalloc()

  dma-buf:
   - fix docs

  imagination:
   - avoid segfault in debugfs

  ofdrm:
   - put PCI device reference on errors

  udl:
   - increase USB timeout"

* tag 'drm-fixes-2026-05-02' of https://gitlab.freedesktop.org/drm/kernel: (77 commits)
  drm/xe/uapi: Reject coh_none PAT index for CPU_ADDR_MIRROR
  drm/xe/uapi: Reject coh_none PAT index for CPU cached memory in madvise
  drm/xe/xelp: Fix Wa_18022495364
  drm/xe/gsc: Fix BO leak on error in query_compatibility_version()
  drm/xe/eustall: Fix drm_dev_put called before stream disable in close
  drm/xe: Fix error cleanup in xe_exec_queue_create_ioctl()
  drm/xe: Fix dma-buf attachment leak in xe_gem_prime_import()
  drm/xe: Fix bo leak in xe_dma_buf_init_obj() on allocation failure
  drm/xe/bo: Fix bo leak on GGTT flag validation in xe_bo_init_locked()
  drm/xe/bo: Fix bo leak on unaligned size validation in xe_bo_init_locked()
  drm/xe: Fix potential NULL deref in xe_exec_queue_tlb_inval_last_fence_put_unlocked
  drm/xe/vf: Use drm mm instead of drm sa for CCS read/write
  drm/xe: Add memory pool with shadow support
  drm/xe/debugfs: Correct printing of register whitelist ranges
  drm/xe: Mark ROW_CHICKEN5 as a masked register
  drm/xe/tuning: Use proper register offset for GAMSTLB_CTRL
  drm/xe/xe3p_lpg: Add missing indirect ring state feature flag
  drm/xe: Drop redundant rtp entries for Wa_14019988906 & Wa_14019877138
  drm/xe/vm: Add missing pad and extensions check
  drm/xe: Drop registration of guc_submit_wedged_fini from xe_guc_submit_wedge()
  ...
This commit is contained in:
Linus Torvalds
2026-05-01 16:56:08 -07:00
88 changed files with 1085 additions and 269 deletions
+1
View File
@@ -19,6 +19,7 @@ Abhinav Kumar <quic_abhinavk@quicinc.com> <abhinavk@codeaurora.org>
Ahmad Masri <quic_amasri@quicinc.com> <amasri@codeaurora.org>
Adam Oldham <oldhamca@gmail.com>
Adam Radford <aradford@gmail.com>
Aditya Garg <gargaditya08@proton.me> <gargaditya08@live.com>
Adriana Reus <adi.reus@gmail.com> <adriana.reus@intel.com>
Adrian Bunk <bunk@stusta.de>
Ajay Kaher <ajay.kaher@broadcom.com> <akaher@vmware.com>
+1 -1
View File
@@ -7873,7 +7873,7 @@ F: drivers/gpu/drm/sun4i/sun8i*
DRM DRIVER FOR APPLE TOUCH BARS
M: Aun-Ali Zaidi <admin@kodeit.net>
M: Aditya Garg <gargaditya08@live.com>
M: Aditya Garg <gargaditya08@proton.me>
L: dri-devel@lists.freedesktop.org
S: Maintained
T: git https://gitlab.freedesktop.org/drm/misc/kernel.git
+5 -1
View File
@@ -2839,8 +2839,12 @@ static int amdgpu_device_ip_fini_early(struct amdgpu_device *adev)
* that checks whether the PSP is running. A solution for those issues
* in the APU is to trigger a GPU reset, but this should be done during
* the unload phase to avoid adding boot latency and screen flicker.
* GFX V11 has GC block as default off IP. Every time AMDGPU driver sends
* a request to PMFW to unload MP1, PMFW will put GC in reset and power down
* the voltage. Hence, skipping reset for APUs with GFX V11 or later.
*/
if ((adev->flags & AMD_IS_APU) && !adev->gmc.is_app_apu) {
if ((adev->flags & AMD_IS_APU) && !adev->gmc.is_app_apu &&
amdgpu_ip_version(adev, GC_HWIP, 0) < IP_VERSION(11, 0, 0)) {
r = amdgpu_asic_reset(adev);
if (r)
dev_err(adev->dev, "asic reset on %s failed\n", __func__);
@@ -3090,10 +3090,8 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev)
case IP_VERSION(11, 5, 1):
case IP_VERSION(11, 5, 2):
case IP_VERSION(11, 5, 3):
adev->family = AMDGPU_FAMILY_GC_11_5_0;
break;
case IP_VERSION(11, 5, 4):
adev->family = AMDGPU_FAMILY_GC_11_5_4;
adev->family = AMDGPU_FAMILY_GC_11_5_0;
break;
case IP_VERSION(12, 0, 0):
case IP_VERSION(12, 0, 1):
+4 -2
View File
@@ -3158,8 +3158,10 @@ static int __init amdgpu_init(void)
amdgpu_register_atpx_handler();
amdgpu_acpi_detect();
/* Ignore KFD init failures. Normal when CONFIG_HSA_AMD is not set. */
amdgpu_amdkfd_init();
/* Ignore KFD init failures when CONFIG_HSA_AMD is not set. */
r = amdgpu_amdkfd_init();
if (r && r != -ENOENT)
goto error_fence;
if (amdgpu_pp_feature_mask & PP_OVERDRIVE_MASK) {
add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK);
+4 -1
View File
@@ -314,7 +314,10 @@ void amdgpu_gmc_gart_location(struct amdgpu_device *adev, struct amdgpu_gmc *mc,
mc->gart_start = max_mc_address - mc->gart_size + 1;
break;
case AMDGPU_GART_PLACEMENT_LOW:
mc->gart_start = 0;
if (size_bf >= mc->gart_size)
mc->gart_start = 0;
else
mc->gart_start = ALIGN(mc->fb_end, four_gb);
break;
case AMDGPU_GART_PLACEMENT_BEST_FIT:
default:
+24 -33
View File
@@ -873,68 +873,59 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
? -EFAULT : 0;
}
case AMDGPU_INFO_READ_MMR_REG: {
int ret = 0;
unsigned int n, alloc_size;
uint32_t *regs;
unsigned int se_num = (info->read_mmr_reg.instance >>
AMDGPU_INFO_MMR_SE_INDEX_SHIFT) &
AMDGPU_INFO_MMR_SE_INDEX_MASK;
unsigned int sh_num = (info->read_mmr_reg.instance >>
AMDGPU_INFO_MMR_SH_INDEX_SHIFT) &
AMDGPU_INFO_MMR_SH_INDEX_MASK;
if (!down_read_trylock(&adev->reset_domain->sem))
return -ENOENT;
unsigned int alloc_size;
uint32_t *regs;
int ret;
/* set full masks if the userspace set all bits
* in the bitfields
*/
if (se_num == AMDGPU_INFO_MMR_SE_INDEX_MASK) {
if (se_num == AMDGPU_INFO_MMR_SE_INDEX_MASK)
se_num = 0xffffffff;
} else if (se_num >= AMDGPU_GFX_MAX_SE) {
ret = -EINVAL;
goto out;
}
else if (se_num >= AMDGPU_GFX_MAX_SE)
return -EINVAL;
if (sh_num == AMDGPU_INFO_MMR_SH_INDEX_MASK) {
if (sh_num == AMDGPU_INFO_MMR_SH_INDEX_MASK)
sh_num = 0xffffffff;
} else if (sh_num >= AMDGPU_GFX_MAX_SH_PER_SE) {
ret = -EINVAL;
goto out;
}
else if (sh_num >= AMDGPU_GFX_MAX_SH_PER_SE)
return -EINVAL;
if (info->read_mmr_reg.count > 128) {
ret = -EINVAL;
goto out;
}
if (info->read_mmr_reg.count > 128)
return -EINVAL;
regs = kmalloc_array(info->read_mmr_reg.count, sizeof(*regs), GFP_KERNEL);
if (!regs) {
ret = -ENOMEM;
goto out;
}
regs = kmalloc_array(info->read_mmr_reg.count, sizeof(*regs),
GFP_KERNEL);
if (!regs)
return -ENOMEM;
down_read(&adev->reset_domain->sem);
alloc_size = info->read_mmr_reg.count * sizeof(*regs);
amdgpu_gfx_off_ctrl(adev, false);
ret = 0;
for (i = 0; i < info->read_mmr_reg.count; i++) {
if (amdgpu_asic_read_register(adev, se_num, sh_num,
info->read_mmr_reg.dword_offset + i,
&regs[i])) {
DRM_DEBUG_KMS("unallowed offset %#x\n",
info->read_mmr_reg.dword_offset + i);
kfree(regs);
amdgpu_gfx_off_ctrl(adev, true);
ret = -EFAULT;
goto out;
break;
}
}
amdgpu_gfx_off_ctrl(adev, true);
n = copy_to_user(out, regs, min(size, alloc_size));
kfree(regs);
ret = (n ? -EFAULT : 0);
out:
up_read(&adev->reset_domain->sem);
if (!ret) {
ret = copy_to_user(out, regs, min(size, alloc_size))
? -EFAULT : 0;
}
kfree(regs);
return ret;
}
case AMDGPU_INFO_DEV_INFO: {
@@ -1950,7 +1950,7 @@ void amdgpu_ras_check_bad_page_status(struct amdgpu_device *adev)
if (!control || amdgpu_bad_page_threshold == 0)
return;
if (control->ras_num_bad_pages >= ras->bad_page_cnt_threshold) {
if (control->ras_num_bad_pages > ras->bad_page_cnt_threshold) {
if (amdgpu_dpm_send_rma_reason(adev))
dev_warn(adev->dev, "Unable to send out-of-band RMA CPER");
else
+3
View File
@@ -75,6 +75,9 @@ static int amdgpu_ttm_init_on_chip(struct amdgpu_device *adev,
unsigned int type,
uint64_t size_in_page)
{
if (!size_in_page)
return 0;
return ttm_range_man_init(&adev->mman.bdev, type,
false, size_in_page);
}
+15 -7
View File
@@ -205,6 +205,19 @@ void amdgpu_userq_start_hang_detect_work(struct amdgpu_usermode_queue *queue)
msecs_to_jiffies(timeout_ms));
}
void amdgpu_userq_process_fence_irq(struct amdgpu_device *adev, u32 doorbell)
{
struct xarray *xa = &adev->userq_doorbell_xa;
struct amdgpu_usermode_queue *queue;
unsigned long flags;
xa_lock_irqsave(xa, flags);
queue = xa_load(xa, doorbell);
if (queue)
amdgpu_userq_fence_driver_process(queue->fence_drv);
xa_unlock_irqrestore(xa, flags);
}
static void amdgpu_userq_init_hang_detect_work(struct amdgpu_usermode_queue *queue)
{
INIT_DELAYED_WORK(&queue->hang_detect_work, amdgpu_userq_hang_detect_work);
@@ -643,12 +656,6 @@ amdgpu_userq_destroy(struct amdgpu_userq_mgr *uq_mgr, struct amdgpu_usermode_que
#endif
amdgpu_userq_detect_and_reset_queues(uq_mgr);
r = amdgpu_userq_unmap_helper(queue);
/*TODO: It requires a reset for userq hw unmap error*/
if (r) {
drm_warn(adev_to_drm(uq_mgr->adev), "trying to destroy a HW mapping userq\n");
queue->state = AMDGPU_USERQ_STATE_HUNG;
}
atomic_dec(&uq_mgr->userq_count[queue->queue_type]);
amdgpu_userq_cleanup(queue);
mutex_unlock(&uq_mgr->userq_mutex);
@@ -1187,7 +1194,7 @@ retry_lock:
bo = range->bo;
ret = amdgpu_ttm_tt_get_user_pages(bo, range);
if (ret)
goto unlock_all;
goto free_ranges;
}
invalidated = true;
@@ -1214,6 +1221,7 @@ retry_lock:
unlock_all:
drm_exec_fini(&exec);
free_ranges:
xa_for_each(&xa, tmp_key, range) {
if (!range)
continue;
@@ -156,6 +156,7 @@ void amdgpu_userq_reset_work(struct work_struct *work);
void amdgpu_userq_pre_reset(struct amdgpu_device *adev);
int amdgpu_userq_post_reset(struct amdgpu_device *adev, bool vram_lost);
void amdgpu_userq_start_hang_detect_work(struct amdgpu_usermode_queue *queue);
void amdgpu_userq_process_fence_irq(struct amdgpu_device *adev, u32 doorbell);
int amdgpu_userq_input_va_validate(struct amdgpu_device *adev,
struct amdgpu_usermode_queue *queue,
+14 -3
View File
@@ -3023,11 +3023,22 @@ bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid,
is_compute_context = vm->is_compute_context;
if (is_compute_context && !svm_range_restore_pages(adev, pasid, vmid,
node_id, addr >> PAGE_SHIFT, ts, write_fault)) {
if (is_compute_context) {
/* Unreserve root since svm_range_restore_pages might try to reserve it. */
/* TODO: rework svm_range_restore_pages so that this isn't necessary. */
amdgpu_bo_unreserve(root);
if (!svm_range_restore_pages(adev, pasid, vmid,
node_id, addr >> PAGE_SHIFT, ts, write_fault)) {
amdgpu_bo_unref(&root);
return true;
}
amdgpu_bo_unref(&root);
return true;
/* Re-acquire the VM lock, could be that the VM was freed in between. */
vm = amdgpu_vm_lock_by_pasid(adev, &root, pasid);
if (!vm)
return false;
}
addr /= AMDGPU_GPU_PAGE_SIZE;
+1 -9
View File
@@ -6523,15 +6523,7 @@ static int gfx_v11_0_eop_irq(struct amdgpu_device *adev,
DRM_DEBUG("IH: CP EOP\n");
if (adev->enable_mes && doorbell_offset) {
struct amdgpu_usermode_queue *queue;
struct xarray *xa = &adev->userq_doorbell_xa;
unsigned long flags;
xa_lock_irqsave(xa, flags);
queue = xa_load(xa, doorbell_offset);
if (queue)
amdgpu_userq_fence_driver_process(queue->fence_drv);
xa_unlock_irqrestore(xa, flags);
amdgpu_userq_process_fence_irq(adev, doorbell_offset);
} else {
me_id = (entry->ring_id & 0x0c) >> 2;
pipe_id = (entry->ring_id & 0x03) >> 0;
+1 -9
View File
@@ -4854,15 +4854,7 @@ static int gfx_v12_0_eop_irq(struct amdgpu_device *adev,
DRM_DEBUG("IH: CP EOP\n");
if (adev->enable_mes && doorbell_offset) {
struct xarray *xa = &adev->userq_doorbell_xa;
struct amdgpu_usermode_queue *queue;
unsigned long flags;
xa_lock_irqsave(xa, flags);
queue = xa_load(xa, doorbell_offset);
if (queue)
amdgpu_userq_fence_driver_process(queue->fence_drv);
xa_unlock_irqrestore(xa, flags);
amdgpu_userq_process_fence_irq(adev, doorbell_offset);
} else {
me_id = (entry->ring_id & 0x0c) >> 2;
pipe_id = (entry->ring_id & 0x03) >> 0;
+1 -10
View File
@@ -3643,16 +3643,7 @@ static int gfx_v12_1_eop_irq(struct amdgpu_device *adev,
DRM_DEBUG("IH: CP EOP\n");
if (adev->enable_mes && doorbell_offset) {
struct xarray *xa = &adev->userq_doorbell_xa;
struct amdgpu_usermode_queue *queue;
unsigned long flags;
xa_lock_irqsave(xa, flags);
queue = xa_load(xa, doorbell_offset);
if (queue)
amdgpu_userq_fence_driver_process(queue->fence_drv);
xa_unlock_irqrestore(xa, flags);
amdgpu_userq_process_fence_irq(adev, doorbell_offset);
} else {
me_id = (entry->ring_id & 0x0c) >> 2;
pipe_id = (entry->ring_id & 0x03) >> 0;
+66
View File
@@ -1571,6 +1571,71 @@ static void gfx_v6_0_setup_spi(struct amdgpu_device *adev)
mutex_unlock(&adev->grbm_idx_mutex);
}
/**
* gfx_v6_0_setup_tcc() - setup which TCCs are used
*
* @adev: amdgpu_device pointer
*
* Verify whether the current GPU has any TCCs disabled,
* which can happen when the GPU is harvested and some
* memory channels are disabled, reducing the memory bus width.
* For example, on the Radeon HD 7870 XT (Tahiti LE).
*
* If some TCCs are disabled, we need to make sure that
* the disabled TCCs are not used, and the remaining TCCs
* are used optimally.
*
* TCP_CHAN_STEER_LO/HI control which TCC is used by TCP channels.
* TCP_ADDR_CONFIG.NUM_TCC_BANKS controls how many channels are used.
*
* For optimal performance:
* - Rely on the CHAN_STEER from the golden registers table,
* only skip disabled TCCs but keep the mapping order.
* - Limit NUM_TCC_BANKS to number of active TCCs to avoid thrashing,
* which performs better than using the same TCC twice.
*/
static void gfx_v6_0_setup_tcc(struct amdgpu_device *adev)
{
u32 i, tcc, tcp_addr_config, num_active_tcc = 0;
u64 chan_steer, patched_chan_steer = 0;
const u32 num_max_tcc = adev->gfx.config.max_texture_channel_caches;
const u32 dis_tcc_mask =
amdgpu_gfx_create_bitmask(num_max_tcc) &
(REG_GET_FIELD(RREG32(mmCGTS_TCC_DISABLE),
CGTS_TCC_DISABLE, TCC_DISABLE) |
REG_GET_FIELD(RREG32(mmCGTS_USER_TCC_DISABLE),
CGTS_USER_TCC_DISABLE, TCC_DISABLE));
/* When no TCC is disabled, the golden registers table already has optimal TCC setup */
if (!dis_tcc_mask)
return;
/* Each 4-bit nibble contains the index of a TCC used by all TCPs */
chan_steer = RREG32(mmTCP_CHAN_STEER_LO) | ((u64)RREG32(mmTCP_CHAN_STEER_HI) << 32ull);
/* Patch the TCP to TCC mapping to skip disabled TCCs */
for (i = 0; i < num_max_tcc; ++i) {
tcc = (chan_steer >> (u64)(4 * i)) & 0xf;
if (!((1 << tcc) & dis_tcc_mask)) {
/* Copy enabled TCC indices to the patched register value. */
patched_chan_steer |= (u64)tcc << (u64)(4 * num_active_tcc);
++num_active_tcc;
}
}
WARN_ON(num_active_tcc != num_max_tcc - hweight32(dis_tcc_mask));
/* Patch number of TCCs used by TCPs */
tcp_addr_config = REG_SET_FIELD(RREG32(mmTCP_ADDR_CONFIG),
TCP_ADDR_CONFIG, NUM_TCC_BANKS,
num_active_tcc - 1);
WREG32(mmTCP_ADDR_CONFIG, tcp_addr_config);
WREG32(mmTCP_CHAN_STEER_HI, upper_32_bits(patched_chan_steer));
WREG32(mmTCP_CHAN_STEER_LO, lower_32_bits(patched_chan_steer));
}
static void gfx_v6_0_config_init(struct amdgpu_device *adev)
{
adev->gfx.config.double_offchip_lds_buf = 0;
@@ -1729,6 +1794,7 @@ static void gfx_v6_0_constants_init(struct amdgpu_device *adev)
gfx_v6_0_tiling_mode_table_init(adev);
gfx_v6_0_setup_rb(adev);
gfx_v6_0_setup_tcc(adev);
gfx_v6_0_setup_spi(adev);
+1
View File
@@ -802,6 +802,7 @@ static const struct amd_ip_funcs jpeg_v2_0_ip_funcs = {
static const struct amdgpu_ring_funcs jpeg_v2_0_dec_ring_vm_funcs = {
.type = AMDGPU_RING_TYPE_VCN_JPEG,
.align_mask = 0xf,
.no_user_fence = true,
.get_rptr = jpeg_v2_0_dec_ring_get_rptr,
.get_wptr = jpeg_v2_0_dec_ring_get_wptr,
.set_wptr = jpeg_v2_0_dec_ring_set_wptr,
+2
View File
@@ -693,6 +693,7 @@ static const struct amd_ip_funcs jpeg_v2_6_ip_funcs = {
static const struct amdgpu_ring_funcs jpeg_v2_5_dec_ring_vm_funcs = {
.type = AMDGPU_RING_TYPE_VCN_JPEG,
.align_mask = 0xf,
.no_user_fence = true,
.get_rptr = jpeg_v2_5_dec_ring_get_rptr,
.get_wptr = jpeg_v2_5_dec_ring_get_wptr,
.set_wptr = jpeg_v2_5_dec_ring_set_wptr,
@@ -724,6 +725,7 @@ static const struct amdgpu_ring_funcs jpeg_v2_5_dec_ring_vm_funcs = {
static const struct amdgpu_ring_funcs jpeg_v2_6_dec_ring_vm_funcs = {
.type = AMDGPU_RING_TYPE_VCN_JPEG,
.align_mask = 0xf,
.no_user_fence = true,
.get_rptr = jpeg_v2_5_dec_ring_get_rptr,
.get_wptr = jpeg_v2_5_dec_ring_get_wptr,
.set_wptr = jpeg_v2_5_dec_ring_set_wptr,
+1
View File
@@ -594,6 +594,7 @@ static const struct amd_ip_funcs jpeg_v3_0_ip_funcs = {
static const struct amdgpu_ring_funcs jpeg_v3_0_dec_ring_vm_funcs = {
.type = AMDGPU_RING_TYPE_VCN_JPEG,
.align_mask = 0xf,
.no_user_fence = true,
.get_rptr = jpeg_v3_0_dec_ring_get_rptr,
.get_wptr = jpeg_v3_0_dec_ring_get_wptr,
.set_wptr = jpeg_v3_0_dec_ring_set_wptr,
+1
View File
@@ -759,6 +759,7 @@ static const struct amd_ip_funcs jpeg_v4_0_ip_funcs = {
static const struct amdgpu_ring_funcs jpeg_v4_0_dec_ring_vm_funcs = {
.type = AMDGPU_RING_TYPE_VCN_JPEG,
.align_mask = 0xf,
.no_user_fence = true,
.get_rptr = jpeg_v4_0_dec_ring_get_rptr,
.get_wptr = jpeg_v4_0_dec_ring_get_wptr,
.set_wptr = jpeg_v4_0_dec_ring_set_wptr,

Some files were not shown because too many files have changed in this diff Show More