summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdgpu
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu')
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c4
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c2
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_device.c41
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_display.c13
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c1
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h4
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c3
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h2
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c9
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h1
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c3
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c264
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h4
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h5
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c2
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c3
-rw-r--r--drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c155
-rw-r--r--drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c2
-rw-r--r--drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c7
-rw-r--r--drivers/gpu/drm/amd/amdgpu/mes_v11_0.c4
-rw-r--r--drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c9
-rw-r--r--drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c9
-rw-r--r--drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c9
-rw-r--r--drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c15
-rw-r--r--drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c5
-rw-r--r--drivers/gpu/drm/amd/amdgpu/soc15.c25
-rw-r--r--drivers/gpu/drm/amd/amdgpu/soc21.c2
-rw-r--r--drivers/gpu/drm/amd/amdgpu/vega10_ih.c4
-rw-r--r--drivers/gpu/drm/amd/amdgpu/vega20_ih.c4
29 files changed, 412 insertions, 199 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
index 130060834b4e..48bd660ddb85 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
@@ -1050,6 +1050,10 @@ bool amdgpu_acpi_should_gpu_reset(struct amdgpu_device *adev)
{
if (adev->flags & AMD_IS_APU)
return false;
+
+ if (amdgpu_sriov_vf(adev))
+ return false;
+
return pm_suspend_target_state != PM_SUSPEND_TO_IDLE;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index cbd593f7d553..2170db83e41d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -1728,7 +1728,7 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(
add_kgd_mem_to_kfd_bo_list(*mem, avm->process_info, user_addr);
if (user_addr) {
- pr_debug("creating userptr BO for user_addr = %llu\n", user_addr);
+ pr_debug("creating userptr BO for user_addr = %llx\n", user_addr);
ret = init_user_pages(*mem, user_addr, criu_resume);
if (ret)
goto allocate_init_user_pages_failed;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 1400abee9f40..25e1f5ed7ead 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2365,8 +2365,16 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev)
}
adev->ip_blocks[i].status.sw = true;
- /* need to do gmc hw init early so we can allocate gpu mem */
- if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GMC) {
+ if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_COMMON) {
+ /* need to do common hw init early so everything is set up for gmc */
+ r = adev->ip_blocks[i].version->funcs->hw_init((void *)adev);
+ if (r) {
+ DRM_ERROR("hw_init %d failed %d\n", i, r);
+ goto init_failed;
+ }
+ adev->ip_blocks[i].status.hw = true;
+ } else if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GMC) {
+ /* need to do gmc hw init early so we can allocate gpu mem */
/* Try to reserve bad pages early */
if (amdgpu_sriov_vf(adev))
amdgpu_virt_exchange_data(adev);
@@ -3052,8 +3060,8 @@ static int amdgpu_device_ip_reinit_early_sriov(struct amdgpu_device *adev)
int i, r;
static enum amd_ip_block_type ip_order[] = {
- AMD_IP_BLOCK_TYPE_GMC,
AMD_IP_BLOCK_TYPE_COMMON,
+ AMD_IP_BLOCK_TYPE_GMC,
AMD_IP_BLOCK_TYPE_PSP,
AMD_IP_BLOCK_TYPE_IH,
};
@@ -3144,7 +3152,8 @@ static int amdgpu_device_ip_resume_phase1(struct amdgpu_device *adev)
continue;
if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_COMMON ||
adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GMC ||
- adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_IH) {
+ adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_IH ||
+ (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_PSP && amdgpu_sriov_vf(adev))) {
r = adev->ip_blocks[i].version->funcs->resume(adev);
if (r) {
@@ -4056,12 +4065,20 @@ static void amdgpu_device_evict_resources(struct amdgpu_device *adev)
int amdgpu_device_suspend(struct drm_device *dev, bool fbcon)
{
struct amdgpu_device *adev = drm_to_adev(dev);
+ int r = 0;
if (dev->switch_power_state == DRM_SWITCH_POWER_OFF)
return 0;
adev->in_suspend = true;
+ if (amdgpu_sriov_vf(adev)) {
+ amdgpu_virt_fini_data_exchange(adev);
+ r = amdgpu_virt_request_full_gpu(adev, false);
+ if (r)
+ return r;
+ }
+
if (amdgpu_acpi_smart_shift_update(dev, AMDGPU_SS_DEV_D3))
DRM_WARN("smart shift update failed\n");
@@ -4085,6 +4102,9 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon)
amdgpu_device_ip_suspend_phase2(adev);
+ if (amdgpu_sriov_vf(adev))
+ amdgpu_virt_release_full_gpu(adev, false);
+
return 0;
}
@@ -4103,6 +4123,12 @@ int amdgpu_device_resume(struct drm_device *dev, bool fbcon)
struct amdgpu_device *adev = drm_to_adev(dev);
int r = 0;
+ if (amdgpu_sriov_vf(adev)) {
+ r = amdgpu_virt_request_full_gpu(adev, true);
+ if (r)
+ return r;
+ }
+
if (dev->switch_power_state == DRM_SWITCH_POWER_OFF)
return 0;
@@ -4117,6 +4143,13 @@ int amdgpu_device_resume(struct drm_device *dev, bool fbcon)
}
r = amdgpu_device_ip_resume(adev);
+
+ /* no matter what r is, always need to properly release full GPU */
+ if (amdgpu_sriov_vf(adev)) {
+ amdgpu_virt_init_data_exchange(adev);
+ amdgpu_virt_release_full_gpu(adev, true);
+ }
+
if (r) {
dev_err(adev->dev, "amdgpu_device_ip_resume failed (%d).\n", r);
return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
index c20922a5af9f..23998f727c7f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
@@ -38,6 +38,8 @@
#include <linux/pci.h>
#include <linux/pm_runtime.h>
#include <drm/drm_crtc_helper.h>
+#include <drm/drm_damage_helper.h>
+#include <drm/drm_drv.h>
#include <drm/drm_edid.h>
#include <drm/drm_gem_framebuffer_helper.h>
#include <drm/drm_fb_helper.h>
@@ -498,6 +500,12 @@ static const struct drm_framebuffer_funcs amdgpu_fb_funcs = {
.create_handle = drm_gem_fb_create_handle,
};
+static const struct drm_framebuffer_funcs amdgpu_fb_funcs_atomic = {
+ .destroy = drm_gem_fb_destroy,
+ .create_handle = drm_gem_fb_create_handle,
+ .dirty = drm_atomic_helper_dirtyfb,
+};
+
uint32_t amdgpu_display_supported_domains(struct amdgpu_device *adev,
uint64_t bo_flags)
{
@@ -1100,7 +1108,10 @@ static int amdgpu_display_gem_fb_verify_and_init(struct drm_device *dev,
if (ret)
goto err;
- ret = drm_framebuffer_init(dev, &rfb->base, &amdgpu_fb_funcs);
+ if (drm_drv_uses_atomic_modeset(dev))
+ ret = drm_framebuffer_init(dev, &rfb->base, &amdgpu_fb_funcs_atomic);
+ else
+ ret = drm_framebuffer_init(dev, &rfb->base, &amdgpu_fb_funcs);
if (ret)
goto err;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index 8adeb7469f1e..d0d99ed607dd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -400,7 +400,6 @@ unsigned amdgpu_fence_count_emitted(struct amdgpu_ring *ring)
/* We are not protected by ring lock when reading the last sequence
* but it's ok to report slightly wrong fence count here.
*/
- amdgpu_fence_process(ring);
emitted = 0x100000000ull;
emitted -= atomic_read(&ring->fence_drv.last_seq);
emitted += READ_ONCE(ring->fence_drv.sync_seq);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
index 23a696d38390..de5b936b016d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
@@ -304,6 +304,10 @@ struct amdgpu_gfx {
uint32_t rlc_srlg_feature_version;
uint32_t rlc_srls_fw_version;
uint32_t rlc_srls_feature_version;
+ uint32_t rlcp_ucode_version;
+ uint32_t rlcp_ucode_feature_version;
+ uint32_t rlcv_ucode_version;
+ uint32_t rlcv_ucode_feature_version;
uint32_t mec_feature_version;
uint32_t mec2_feature_version;
bool mec_fw_write_wait;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
index fe82b8b19a4e..0c546245793b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
@@ -181,6 +181,9 @@ int amdgpu_mes_init(struct amdgpu_device *adev)
for (i = 0; i < AMDGPU_MES_MAX_SDMA_PIPES; i++) {
if (adev->ip_versions[SDMA0_HWIP][0] < IP_VERSION(6, 0, 0))
adev->mes.sdma_hqd_mask[i] = i ? 0 : 0x3fc;
+ /* zero sdma_hqd_mask for non-existent engine */
+ else if (adev->sdma.num_instances == 1)
+ adev->mes.sdma_hqd_mask[i] = i ? 0 : 0xfc;
else
adev->mes.sdma_hqd_mask[i] = 0xfc;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h
index 7b46f6bf4187..ad980f4b66e1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h
@@ -222,6 +222,8 @@ struct mes_add_queue_input {
uint64_t tba_addr;
uint64_t tma_addr;
uint32_t is_kfd_process;
+ uint32_t is_aql_queue;
+ uint32_t queue_size;
};
struct mes_remove_queue_input {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 9f7a5e393f85..c9dec2434f37 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -486,11 +486,14 @@ static int psp_sw_fini(void *handle)
release_firmware(psp->ta_fw);
psp->ta_fw = NULL;
}
- if (adev->psp.cap_fw) {
+ if (psp->cap_fw) {
release_firmware(psp->cap_fw);
psp->cap_fw = NULL;
}
-
+ if (psp->toc_fw) {
+ release_firmware(psp->toc_fw);
+ psp->toc_fw = NULL;
+ }
if (adev->ip_versions[MP0_HWIP][0] == IP_VERSION(11, 0, 0) ||
adev->ip_versions[MP0_HWIP][0] == IP_VERSION(11, 0, 7))
psp_sysfs_fini(adev);
@@ -753,7 +756,7 @@ static int psp_tmr_init(struct psp_context *psp)
}
pptr = amdgpu_sriov_vf(psp->adev) ? &tmr_buf : NULL;
- ret = amdgpu_bo_create_kernel(psp->adev, tmr_size, PSP_TMR_SIZE(psp->adev),
+ ret = amdgpu_bo_create_kernel(psp->adev, tmr_size, PSP_TMR_ALIGNMENT,
AMDGPU_GEM_DOMAIN_VRAM,
&psp->tmr_bo, &psp->tmr_mc_addr, pptr);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
index c32b74bd970f..e593e8c2a54d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
@@ -36,6 +36,7 @@
#define PSP_CMD_BUFFER_SIZE 0x1000
#define PSP_1_MEG 0x100000
#define PSP_TMR_SIZE(adev) ((adev)->asic_type == CHIP_ALDEBARAN ? 0x800000 : 0x400000)
+#define PSP_TMR_ALIGNMENT 0x100000
#define PSP_FW_NAME_LEN 0x24
enum psp_shared_mem_size {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index ff5361f5c2d4..12c6f97945a5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -1811,7 +1811,8 @@ static void amdgpu_ras_log_on_err_counter(struct amdgpu_device *adev)
amdgpu_ras_query_error_status(adev, &info);
if (adev->ip_versions[MP0_HWIP][0] != IP_VERSION(11, 0, 2) &&
- adev->ip_versions[MP0_HWIP][0] != IP_VERSION(11, 0, 4)) {
+ adev->ip_versions[MP0_HWIP][0] != IP_VERSION(11, 0, 4) &&
+ adev->ip_versions[MP0_HWIP][0] != IP_VERSION(13, 0, 0)) {
if (amdgpu_ras_reset_error_status(adev, info.head.block))
dev_warn(adev->dev, "Failed to reset error counter and error status");
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c
index 6373bfb47d55..e23f6192c50e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c
@@ -272,3 +272,267 @@ void amdgpu_gfx_rlc_fini(struct amdgpu_device *adev)
&adev->gfx.rlc.cp_table_gpu_addr,
(void **)&adev->gfx.rlc.cp_table_ptr);
}
+
+static int amdgpu_gfx_rlc_init_microcode_v2_0(struct amdgpu_device *adev)
+{
+ const struct common_firmware_header *common_hdr;
+ const struct rlc_firmware_header_v2_0 *rlc_hdr;
+ struct amdgpu_firmware_info *info;
+ unsigned int *tmp;
+ unsigned int i;
+
+ rlc_hdr = (const struct rlc_firmware_header_v2_0 *)adev->gfx.rlc_fw->data;
+
+ adev->gfx.rlc_fw_version = le32_to_cpu(rlc_hdr->header.ucode_version);
+ adev->gfx.rlc_feature_version = le32_to_cpu(rlc_hdr->ucode_feature_version);
+ adev->gfx.rlc.save_and_restore_offset =
+ le32_to_cpu(rlc_hdr->save_and_restore_offset);
+ adev->gfx.rlc.clear_state_descriptor_offset =
+ le32_to_cpu(rlc_hdr->clear_state_descriptor_offset);
+ adev->gfx.rlc.avail_scratch_ram_locations =
+ le32_to_cpu(rlc_hdr->avail_scratch_ram_locations);
+ adev->gfx.rlc.reg_restore_list_size =
+ le32_to_cpu(rlc_hdr->reg_restore_list_size);
+ adev->gfx.rlc.reg_list_format_start =
+ le32_to_cpu(rlc_hdr->reg_list_format_start);
+ adev->gfx.rlc.reg_list_format_separate_start =
+ le32_to_cpu(rlc_hdr->reg_list_format_separate_start);
+ adev->gfx.rlc.starting_offsets_start =
+ le32_to_cpu(rlc_hdr->starting_offsets_start);
+ adev->gfx.rlc.reg_list_format_size_bytes =
+ le32_to_cpu(rlc_hdr->reg_list_format_size_bytes);
+ adev->gfx.rlc.reg_list_size_bytes =
+ le32_to_cpu(rlc_hdr->reg_list_size_bytes);
+ adev->gfx.rlc.register_list_format =
+ kmalloc(adev->gfx.rlc.reg_list_format_size_bytes +
+ adev->gfx.rlc.reg_list_size_bytes, GFP_KERNEL);
+ if (!adev->gfx.rlc.register_list_format) {
+ dev_err(adev->dev, "failed to allocate memory for rlc register_list_format\n");
+ return -ENOMEM;
+ }
+
+ tmp = (unsigned int *)((uintptr_t)rlc_hdr +
+ le32_to_cpu(rlc_hdr->reg_list_format_array_offset_bytes));
+ for (i = 0 ; i < (rlc_hdr->reg_list_format_size_bytes >> 2); i++)
+ adev->gfx.rlc.register_list_format[i] = le32_to_cpu(tmp[i]);
+
+ adev->gfx.rlc.register_restore = adev->gfx.rlc.register_list_format + i;
+
+ tmp = (unsigned int *)((uintptr_t)rlc_hdr +
+ le32_to_cpu(rlc_hdr->reg_list_array_offset_bytes));
+ for (i = 0 ; i < (rlc_hdr->reg_list_size_bytes >> 2); i++)
+ adev->gfx.rlc.register_restore[i] = le32_to_cpu(tmp[i]);
+
+ if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
+ info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_G];
+ info->ucode_id = AMDGPU_UCODE_ID_RLC_G;
+ info->fw = adev->gfx.rlc_fw;
+ if (info->fw) {
+ common_hdr = (const struct common_firmware_header *)info->fw->data;
+ adev->firmware.fw_size +=
+ ALIGN(le32_to_cpu(common_hdr->ucode_size_bytes), PAGE_SIZE);
+ }
+ }
+
+ return 0;
+}
+
+static void amdgpu_gfx_rlc_init_microcode_v2_1(struct amdgpu_device *adev)
+{
+ const struct rlc_firmware_header_v2_1 *rlc_hdr;
+ struct amdgpu_firmware_info *info;
+
+ rlc_hdr = (const struct rlc_firmware_header_v2_1 *)adev->gfx.rlc_fw->data;
+ adev->gfx.rlc_srlc_fw_version = le32_to_cpu(rlc_hdr->save_restore_list_cntl_ucode_ver);
+ adev->gfx.rlc_srlc_feature_version = le32_to_cpu(rlc_hdr->save_restore_list_cntl_feature_ver);
+ adev->gfx.rlc.save_restore_list_cntl_size_bytes = le32_to_cpu(rlc_hdr->save_restore_list_cntl_size_bytes);
+ adev->gfx.rlc.save_restore_list_cntl = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->save_restore_list_cntl_offset_bytes);
+ adev->gfx.rlc_srlg_fw_version = le32_to_cpu(rlc_hdr->save_restore_list_gpm_ucode_ver);
+ adev->gfx.rlc_srlg_feature_version = le32_to_cpu(rlc_hdr->save_restore_list_gpm_feature_ver);
+ adev->gfx.rlc.save_restore_list_gpm_size_bytes = le32_to_cpu(rlc_hdr->save_restore_list_gpm_size_bytes);
+ adev->gfx.rlc.save_restore_list_gpm = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->save_restore_list_gpm_offset_bytes);
+ adev->gfx.rlc_srls_fw_version = le32_to_cpu(rlc_hdr->save_restore_list_srm_ucode_ver);
+ adev->gfx.rlc_srls_feature_version = le32_to_cpu(rlc_hdr->save_restore_list_srm_feature_ver);
+ adev->gfx.rlc.save_restore_list_srm_size_bytes = le32_to_cpu(rlc_hdr->save_restore_list_srm_size_bytes);
+ adev->gfx.rlc.save_restore_list_srm = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->save_restore_list_srm_offset_bytes);
+ adev->gfx.rlc.reg_list_format_direct_reg_list_length =
+ le32_to_cpu(rlc_hdr->reg_list_format_direct_reg_list_length);
+
+ if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
+ if (adev->gfx.rlc.save_restore_list_gpm_size_bytes) {
+ info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_RESTORE_LIST_GPM_MEM];
+ info->ucode_id = AMDGPU_UCODE_ID_RLC_RESTORE_LIST_GPM_MEM;
+ info->fw = adev->gfx.rlc_fw;
+ adev->firmware.fw_size +=
+ ALIGN(adev->gfx.rlc.save_restore_list_gpm_size_bytes, PAGE_SIZE);
+ }
+
+ if (adev->gfx.rlc.save_restore_list_srm_size_bytes) {
+ info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM];
+ info->ucode_id = AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM;
+ info->fw = adev->gfx.rlc_fw;
+ adev->firmware.fw_size +=
+ ALIGN(adev->gfx.rlc.save_restore_list_srm_size_bytes, PAGE_SIZE);
+ }
+ }
+}
+
+static void amdgpu_gfx_rlc_init_microcode_v2_2(struct amdgpu_device *adev)
+{
+ const struct rlc_firmware_header_v2_2 *rlc_hdr;
+ struct amdgpu_firmware_info *info;
+
+ rlc_hdr = (const struct rlc_firmware_header_v2_2 *)adev->gfx.rlc_fw->data;
+ adev->gfx.rlc.rlc_iram_ucode_size_bytes = le32_to_cpu(rlc_hdr->rlc_iram_ucode_size_bytes);
+ adev->gfx.rlc.rlc_iram_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->rlc_iram_ucode_offset_bytes);
+ adev->gfx.rlc.rlc_dram_ucode_size_bytes = le32_to_cpu(rlc_hdr->rlc_dram_ucode_size_bytes);
+ adev->gfx.rlc.rlc_dram_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->rlc_dram_ucode_offset_bytes);
+
+ if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
+ if (adev->gfx.rlc.rlc_iram_ucode_size_bytes) {
+ info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_IRAM];
+ info->ucode_id = AMDGPU_UCODE_ID_RLC_IRAM;
+ info->fw = adev->gfx.rlc_fw;
+ adev->firmware.fw_size +=
+ ALIGN(adev->gfx.rlc.rlc_iram_ucode_size_bytes, PAGE_SIZE);
+ }
+
+ if (adev->gfx.rlc.rlc_dram_ucode_size_bytes) {
+ info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_DRAM];
+ info->ucode_id = AMDGPU_UCODE_ID_RLC_DRAM;
+ info->fw = adev->gfx.rlc_fw;
+ adev->firmware.fw_size +=
+ ALIGN(adev->gfx.rlc.rlc_dram_ucode_size_bytes, PAGE_SIZE);
+ }
+ }
+}
+
+static void amdgpu_gfx_rlc_init_microcode_v2_3(struct amdgpu_device *adev)
+{
+ const struct rlc_firmware_header_v2_3 *rlc_hdr;
+ struct amdgpu_firmware_info *info;
+
+ rlc_hdr = (const struct rlc_firmware_header_v2_3 *)adev->gfx.rlc_fw->data;
+ adev->gfx.rlcp_ucode_version = le32_to_cpu(rlc_hdr->rlcp_ucode_version);
+ adev->gfx.rlcp_ucode_feature_version = le32_to_cpu(rlc_hdr->rlcp_ucode_feature_version);
+ adev->gfx.rlc.rlcp_ucode_size_bytes = le32_to_cpu(rlc_hdr->rlcp_ucode_size_bytes);
+ adev->gfx.rlc.rlcp_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->rlcp_ucode_offset_bytes);
+
+ adev->gfx.rlcv_ucode_version = le32_to_cpu(rlc_hdr->rlcv_ucode_version);
+ adev->gfx.rlcv_ucode_feature_version = le32_to_cpu(rlc_hdr->rlcv_ucode_feature_version);
+ adev->gfx.rlc.rlcv_ucode_size_bytes = le32_to_cpu(rlc_hdr->rlcv_ucode_size_bytes);
+ adev->gfx.rlc.rlcv_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->rlcv_ucode_offset_bytes);
+
+ if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
+ if (adev->gfx.rlc.rlcp_ucode_size_bytes) {
+ info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_P];
+ info->ucode_id = AMDGPU_UCODE_ID_RLC_P;
+ info->fw = adev->gfx.rlc_fw;
+ adev->firmware.fw_size +=
+ ALIGN(adev->gfx.rlc.rlcp_ucode_size_bytes, PAGE_SIZE);
+ }
+
+ if (adev->gfx.rlc.rlcv_ucode_size_bytes) {
+ info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_V];
+ info->ucode_id = AMDGPU_UCODE_ID_RLC_V;
+ info->fw = adev->gfx.rlc_fw;
+ adev->firmware.fw_size +=
+ ALIGN(adev->gfx.rlc.rlcv_ucode_size_bytes, PAGE_SIZE);
+ }
+ }
+}
+
+static void amdgpu_gfx_rlc_init_microcode_v2_4(struct amdgpu_device *adev)
+{
+ const struct rlc_firmware_header_v2_4 *rlc_hdr;
+ struct amdgpu_firmware_info *info;
+
+ rlc_hdr = (const struct rlc_firmware_header_v2_4 *)adev->gfx.rlc_fw->data;
+ adev->gfx.rlc.global_tap_delays_ucode_size_bytes = le32_to_cpu(rlc_hdr->global_tap_delays_ucode_size_bytes);
+ adev->gfx.rlc.global_tap_delays_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->global_tap_delays_ucode_offset_bytes);
+ adev->gfx.rlc.se0_tap_delays_ucode_size_bytes = le32_to_cpu(rlc_hdr->se0_tap_delays_ucode_size_bytes);
+ adev->gfx.rlc.se0_tap_delays_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->se0_tap_delays_ucode_offset_bytes);
+ adev->gfx.rlc.se1_tap_delays_ucode_size_bytes = le32_to_cpu(rlc_hdr->se1_tap_delays_ucode_size_bytes);
+ adev->gfx.rlc.se1_tap_delays_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->se1_tap_delays_ucode_offset_bytes);
+ adev->gfx.rlc.se2_tap_delays_ucode_size_bytes = le32_to_cpu(rlc_hdr->se2_tap_delays_ucode_size_bytes);
+ adev->gfx.rlc.se2_tap_delays_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->se2_tap_delays_ucode_offset_bytes);
+ adev->gfx.rlc.se3_tap_delays_ucode_size_bytes = le32_to_cpu(rlc_hdr->se3_tap_delays_ucode_size_bytes);
+ adev->gfx.rlc.se3_tap_delays_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->se3_tap_delays_ucode_offset_bytes);
+
+ if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
+ if (adev->gfx.rlc.global_tap_delays_ucode_size_bytes) {
+ info = &adev->firmware.ucode[AMDGPU_UCODE_ID_GLOBAL_TAP_DELAYS];
+ info->ucode_id = AMDGPU_UCODE_ID_GLOBAL_TAP_DELAYS;
+ info->fw = adev->gfx.rlc_fw;
+ adev->firmware.fw_size +=
+ ALIGN(adev->gfx.rlc.global_tap_delays_ucode_size_bytes, PAGE_SIZE);
+ }
+
+ if (adev->gfx.rlc.se0_tap_delays_ucode_size_bytes) {
+ info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SE0_TAP_DELAYS];
+ info->ucode_id = AMDGPU_UCODE_ID_SE0_TAP_DELAYS;
+ info->fw = adev->gfx.rlc_fw;
+ adev->firmware.fw_size +=
+ ALIGN(adev->gfx.rlc.se0_tap_delays_ucode_size_bytes, PAGE_SIZE);
+ }
+
+ if (adev->gfx.rlc.se1_tap_delays_ucode_size_bytes) {
+ info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SE1_TAP_DELAYS];
+ info->ucode_id = AMDGPU_UCODE_ID_SE1_TAP_DELAYS;
+ info->fw = adev->gfx.rlc_fw;
+ adev->firmware.fw_size +=
+ ALIGN(adev->gfx.rlc.se1_tap_delays_ucode_size_bytes, PAGE_SIZE);
+ }
+
+ if (adev->gfx.rlc.se2_tap_delays_ucode_size_bytes) {
+ info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SE2_TAP_DELAYS];
+ info->ucode_id = AMDGPU_UCODE_ID_SE2_TAP_DELAYS;
+ info->fw = adev->gfx.rlc_fw;
+ adev->firmware.fw_size +=
+ ALIGN(adev->gfx.rlc.se2_tap_delays_ucode_size_bytes, PAGE_SIZE);
+ }
+
+ if (adev->gfx.rlc.se3_tap_delays_ucode_size_bytes) {
+ info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SE3_TAP_DELAYS];
+ info->ucode_id = AMDGPU_UCODE_ID_SE3_TAP_DELAYS;
+ info->fw = adev->gfx.rlc_fw;
+ adev->firmware.fw_size +=
+ ALIGN(adev->gfx.rlc.se3_tap_delays_ucode_size_bytes, PAGE_SIZE);
+ }
+ }
+}
+
+int amdgpu_gfx_rlc_init_microcode(struct amdgpu_device *adev,
+ uint16_t version_major,
+ uint16_t version_minor)
+{
+ int err;
+
+ if (version_major < 2) {
+ /* only support rlc_hdr v2.x and onwards */
+ dev_err(adev->dev, "unsupported rlc fw hdr\n");
+ return -EINVAL;
+ }
+
+ /* is_rlc_v2_1 is still used in APU code path */
+ if (version_major == 2 && version_minor == 1)
+ adev->gfx.rlc.is_rlc_v2_1 = true;
+
+ if (version_minor >= 0) {
+ err = amdgpu_gfx_rlc_init_microcode_v2_0(adev);
+ if (err) {
+ dev_err(adev->dev, "fail to init rlc v2_0 microcode\n");
+ return err;
+ }
+ }
+ if (version_minor >= 1)
+ amdgpu_gfx_rlc_init_microcode_v2_1(adev);
+ if (version_minor >= 2)
+ amdgpu_gfx_rlc_init_microcode_v2_2(adev);
+ if (version_minor == 3)
+ amdgpu_gfx_rlc_init_microcode_v2_3(adev);
+ if (version_minor == 4)
+ amdgpu_gfx_rlc_init_microcode_v2_4(adev);
+
+ return 0;
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h
index 03ac36b2c2cf..23f060db9255 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h
@@ -267,5 +267,7 @@ int amdgpu_gfx_rlc_init_csb(struct amdgpu_device *adev);
int amdgpu_gfx_rlc_init_cpt(struct amdgpu_device *adev);
void amdgpu_gfx_rlc_setup_cp_table(struct amdgpu_device *adev);
void amdgpu_gfx_rlc_fini(struct amdgpu_device *adev);
-
+int amdgpu_gfx_rlc_init_microcode(struct amdgpu_device *adev,
+ uint16_t version_major,
+ uint16_t version_minor);
#endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
index ebed3f5226db..59edf32f775e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
@@ -260,8 +260,12 @@ struct rlc_firmware_header_v2_2 {
/* version_major=2, version_minor=3 */
struct rlc_firmware_header_v2_3 {
struct rlc_firmware_header_v2_2 v2_2;
+ uint32_t rlcp_ucode_version;
+ uint32_t rlcp_ucode_feature_version;
uint32_t rlcp_ucode_size_bytes;
uint32_t rlcp_ucode_offset_bytes;
+ uint32_t rlcv_ucode_version;
+ uint32_t rlcv_ucode_feature_version;
uint32_t rlcv_ucode_size_bytes;
uint32_t rlcv_ucode_offset_bytes;
};
@@ -390,6 +394,7 @@ union amdgpu_firmware_header {
struct rlc_firmware_header_v2_1 rlc_v2_1;
struct rlc_firmware_header_v2_2 rlc_v2_2;
struct rlc_firmware_header_v2_3 rlc_v2_3;
+ struct rlc_firmware_header_v2_4 rlc_v2_4;
struct sdma_firmware_header_v1_0 sdma;
struct sdma_firmware_header_v1_1 sdma_v1_1;
struct sdma_firmware_header_v2_0 sdma_v2_0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index f36e4f08db6d..0b52af415b28 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -191,7 +191,7 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev)
fw_name = FIRMWARE_VCN4_0_2;
if ((adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) &&
(adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG))
- adev->vcn.indirect_sram = false;
+ adev->vcn.indirect_sram = true;
break;
case IP_VERSION(4, 0, 4):
fw_name = FIRMWARE_VCN4_0_4;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 59cac347baa3..690fd4f639f1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -2484,8 +2484,7 @@ bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid,
/* Intentionally setting invalid PTE flag
* combination to force a no-retry-fault
*/
- flags = AMDGPU_PTE_EXECUTABLE | AMDGPU_PDE_PTE |
- AMDGPU_PTE_TF;
+ flags = AMDGPU_PTE_SNOOPED | AMDGPU_PTE_PRT;
value = 0;
} else if (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_NEVER) {
/* Redirect the access to the dummy page */
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index f6b1bb40e503..daf8ba8235cd 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -474,49 +474,6 @@ static void gfx_v11_0_free_microcode(struct amdgpu_device *adev)
kfree(adev->gfx.rlc.register_list_format);
}
-static void gfx_v11_0_init_rlc_ext_microcode(struct amdgpu_device *adev)
-{
- const struct rlc_firmware_header_v2_1 *rlc_hdr;
-
- rlc_hdr = (const struct rlc_firmware_header_v2_1 *)adev->gfx.rlc_fw->data;
- adev->gfx.rlc_srlc_fw_version = le32_to_cpu(rlc_hdr->save_restore_list_cntl_ucode_ver);
- adev->gfx.rlc_srlc_feature_version = le32_to_cpu(rlc_hdr->save_restore_list_cntl_feature_ver);
- adev->gfx.rlc.save_restore_list_cntl_size_bytes = le32_to_cpu(rlc_hdr->save_restore_list_cntl_size_bytes);
- adev->gfx.rlc.save_restore_list_cntl = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->save_restore_list_cntl_offset_bytes);
- adev->gfx.rlc_srlg_fw_version = le32_to_cpu(rlc_hdr->save_restore_list_gpm_ucode_ver);
- adev->gfx.rlc_srlg_feature_version = le32_to_cpu(rlc_hdr->save_restore_list_gpm_feature_ver);
- adev->gfx.rlc.save_restore_list_gpm_size_bytes = le32_to_cpu(rlc_hdr->save_restore_list_gpm_size_bytes);
- adev->gfx.rlc.save_restore_list_gpm = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->save_restore_list_gpm_offset_bytes);
- adev->gfx.rlc_srls_fw_version = le32_to_cpu(rlc_hdr->save_restore_list_srm_ucode_ver);
- adev->gfx.rlc_srls_feature_version = le32_to_cpu(rlc_hdr->save_restore_list_srm_feature_ver);
- adev->gfx.rlc.save_restore_list_srm_size_bytes = le32_to_cpu(rlc_hdr->save_restore_list_srm_size_bytes);
- adev->gfx.rlc.save_restore_list_srm = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->save_restore_list_srm_offset_bytes);
- adev->gfx.rlc.reg_list_format_direct_reg_list_length =
- le32_to_cpu(rlc_hdr->reg_list_format_direct_reg_list_length);
-}
-
-static void gfx_v11_0_init_rlc_iram_dram_microcode(struct amdgpu_device *adev)
-{
- const struct rlc_firmware_header_v2_2 *rlc_hdr;
-
- rlc_hdr = (const struct rlc_firmware_header_v2_2 *)adev->gfx.rlc_fw->data;
- adev->gfx.rlc.rlc_iram_ucode_size_bytes = le32_to_cpu(rlc_hdr->rlc_iram_ucode_size_bytes);
- adev->gfx.rlc.rlc_iram_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->rlc_iram_ucode_offset_bytes);
- adev->gfx.rlc.rlc_dram_ucode_size_bytes = le32_to_cpu(rlc_hdr->rlc_dram_ucode_size_bytes);
- adev->gfx.rlc.rlc_dram_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->rlc_dram_ucode_offset_bytes);
-}
-
-static void gfx_v11_0_init_rlcp_rlcv_microcode(struct amdgpu_device *adev)
-{
- const struct rlc_firmware_header_v2_3 *rlc_hdr;
-
- rlc_hdr = (const struct rlc_firmware_header_v2_3 *)adev->gfx.rlc_fw->data;
- adev->gfx.rlc.rlcp_ucode_size_bytes = le32_to_cpu(rlc_hdr->rlcp_ucode_size_bytes);
- adev->gfx.rlc.rlcp_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->rlcp_ucode_offset_bytes);
- adev->gfx.rlc.rlcv_ucode_size_bytes = le32_to_cpu(rlc_hdr->rlcv_ucode_size_bytes);
- adev->gfx.rlc.rlcv_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->rlcv_ucode_offset_bytes);
-}
-
static int gfx_v11_0_init_microcode(struct amdgpu_device *adev)
{
char fw_name[40];
@@ -527,8 +484,6 @@ static int gfx_v11_0_init_microcode(struct amdgpu_device *adev)
const struct gfx_firmware_header_v1_0 *cp_hdr;
const struct gfx_firmware_header_v2_0 *cp_hdr_v2_0;
const struct rlc_firmware_header_v2_0 *rlc_hdr;
- unsigned int *tmp = NULL;
- unsigned int i = 0;
uint16_t version_major;
uint16_t version_minor;
@@ -583,58 +538,14 @@ static int gfx_v11_0_init_microcode(struct amdgpu_device *adev)
if (err)
goto out;
err = amdgpu_ucode_validate(adev->gfx.rlc_fw);
+ if (err)
+ goto out;
rlc_hdr = (const struct rlc_firmware_header_v2_0 *)adev->gfx.rlc_fw->data;
version_major = le16_to_cpu(rlc_hdr->header.header_version_major);
version_minor = le16_to_cpu(rlc_hdr->header.header_version_minor);
-
- adev->gfx.rlc_fw_version = le32_to_cpu(rlc_hdr->header.ucode_version);
- adev->gfx.rlc_feature_version = le32_to_cpu(rlc_hdr->ucode_feature_version);
- adev->gfx.rlc.save_and_restore_offset =
- le32_to_cpu(rlc_hdr->save_and_restore_offset);
- adev->gfx.rlc.clear_state_descriptor_offset =
- le32_to_cpu(rlc_hdr->clear_state_descriptor_offset);
- adev->gfx.rlc.avail_scratch_ram_locations =
- le32_to_cpu(rlc_hdr->avail_scratch_ram_locations);
- adev->gfx.rlc.reg_restore_list_size =
- le32_to_cpu(rlc_hdr->reg_restore_list_size);
- adev->gfx.rlc.reg_list_format_start =
- le32_to_cpu(rlc_hdr->reg_list_format_start);
- adev->gfx.rlc.reg_list_format_separate_start =
- le32_to_cpu(rlc_hdr->reg_list_format_separate_start);
- adev->gfx.rlc.starting_offsets_start =
- le32_to_cpu(rlc_hdr->starting_offsets_start);
- adev->gfx.rlc.reg_list_format_size_bytes =
- le32_to_cpu(rlc_hdr->reg_list_format_size_bytes);
- adev->gfx.rlc.reg_list_size_bytes =
- le32_to_cpu(rlc_hdr->reg_list_size_bytes);
- adev->gfx.rlc.register_list_format =
- kmalloc(adev->gfx.rlc.reg_list_format_size_bytes +
- adev->gfx.rlc.reg_list_size_bytes, GFP_KERNEL);
- if (!adev->gfx.rlc.register_list_format) {
- err = -ENOMEM;
+ err = amdgpu_gfx_rlc_init_microcode(adev, version_major, version_minor);
+ if (err)
goto out;
- }
-
- tmp = (unsigned int *)((uintptr_t)rlc_hdr +
- le32_to_cpu(rlc_hdr->reg_list_format_array_offset_bytes));
- for (i = 0 ; i < (rlc_hdr->reg_list_format_size_bytes >> 2); i++)
- adev->gfx.rlc.register_list_format[i] = le32_to_cpu(tmp[i]);
-
- adev->gfx.rlc.register_restore = adev->gfx.rlc.register_list_format + i;
-
- tmp = (unsigned int *)((uintptr_t)rlc_hdr +
- le32_to_cpu(rlc_hdr->reg_list_array_offset_bytes));
- for (i = 0 ; i < (rlc_hdr->reg_list_size_bytes >> 2); i++)
- adev->gfx.rlc.register_restore[i] = le32_to_cpu(tmp[i]);
-
- if (version_major == 2) {
- if (version_minor >= 1)
- gfx_v11_0_init_rlc_ext_microcode(adev);
- if (version_minor >= 2)
- gfx_v11_0_init_rlc_iram_dram_microcode(adev);
- if (version_minor == 3)
- gfx_v11_0_init_rlcp_rlcv_microcode(adev);
- }
}
snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec.bin", ucode_prefix);
@@ -769,60 +680,6 @@ static int gfx_v11_0_init_microcode(struct amdgpu_device *adev)
adev->firmware.fw_size +=
ALIGN(le32_to_cpu(cp_hdr->jt_size) * 4, PAGE_SIZE);
}
-
- info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_G];
- info->ucode_id = AMDGPU_UCODE_ID_RLC_G;
- info->fw = adev->gfx.rlc_fw;
- if (info->fw) {
- header = (const struct common_firmware_header *)info->fw->data;
- adev->firmware.fw_size +=
- ALIGN(le32_to_cpu(header->ucode_size_bytes), PAGE_SIZE);
- }
- if (adev->gfx.rlc.save_restore_list_gpm_size_bytes &&
- adev->gfx.rlc.save_restore_list_srm_size_bytes) {
- info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_RESTORE_LIST_GPM_MEM];
- info->ucode_id = AMDGPU_UCODE_ID_RLC_RESTORE_LIST_GPM_MEM;
- info->fw = adev->gfx.rlc_fw;
- adev->firmware.fw_size +=
- ALIGN(adev->gfx.rlc.save_restore_list_gpm_size_bytes, PAGE_SIZE);
-
- info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM];
- info->ucode_id = AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM;
- info->fw = adev->gfx.rlc_fw;
- adev->firmware.fw_size +=
- ALIGN(adev->gfx.rlc.save_restore_list_srm_size_bytes, PAGE_SIZE);
- }
-
- if (adev->gfx.rlc.rlc_iram_ucode_size_bytes &&
- adev->gfx.rlc.rlc_dram_ucode_size_bytes) {
- info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_IRAM];
- info->ucode_id = AMDGPU_UCODE_ID_RLC_IRAM;
- info->fw = adev->gfx.rlc_fw;
- adev->firmware.fw_size +=
- ALIGN(adev->gfx.rlc.rlc_iram_ucode_size_bytes, PAGE_SIZE);
-
- info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_DRAM];
- info->ucode_id = AMDGPU_UCODE_ID_RLC_DRAM;
- info->fw = adev->gfx.rlc_fw;
- adev->firmware.fw_size +=
- ALIGN(adev->gfx.rlc.rlc_dram_ucode_size_bytes, PAGE_SIZE);
- }
-
- if (adev->gfx.rlc.rlcp_ucode_size_bytes) {
- info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_P];
- info->ucode_id = AMDGPU_UCODE_ID_RLC_P;
- info->fw = adev->gfx.rlc_fw;
- adev->firmware.fw_size +=
- ALIGN(adev->gfx.rlc.rlcp_ucode_size_bytes, PAGE_SIZE);
- }
-
- if (adev->gfx.rlc.rlcv_ucode_size_bytes) {
- info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_V];
- info->ucode_id = AMDGPU_UCODE_ID_RLC_V;
- info->fw = adev->gfx.rlc_fw;
- adev->firmware.fw_size +=
- ALIGN(adev->gfx.rlc.rlcv_ucode_size_bytes, PAGE_SIZE);
- }
}
out:
@@ -5260,6 +5117,8 @@ static void gfx_v11_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid)
{
u32 reg, data;
+ amdgpu_gfx_off_ctrl(adev, false);
+
reg = SOC15_REG_OFFSET(GC, 0, regRLC_SPM_MC_CNTL);
if (amdgpu_sriov_is_pp_one_vf(adev))
data = RREG32_NO_KIQ(reg);
@@ -5273,6 +5132,8 @@ static void gfx_v11_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid)
WREG32_SOC15_NO_KIQ(GC, 0, regRLC_SPM_MC_CNTL, data);
else
WREG32_SOC15(GC, 0, regRLC_SPM_MC_CNTL, data);
+
+ amdgpu_gfx_off_ctrl(adev, true);
}
static const struct amdgpu_rlc_funcs gfx_v11_0_rlc_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index fc9c1043244c..037af8352677 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -5597,7 +5597,7 @@ static void gfx_v9_0_ring_emit_patch_cond_exec(struct amdgpu_ring *ring, unsigne
BUG_ON(offset > ring->buf_mask);
BUG_ON(ring->ring[offset] != 0x55aa55aa);
- cur = (ring->wptr & ring->buf_mask) - 1;
+ cur = (ring->wptr - 1) & ring->buf_mask;
if (likely(cur > offset))
ring->ring[offset] = cur - offset;
else
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 4603653916f5..67ca16a8027c 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -1103,10 +1103,13 @@ static void gmc_v9_0_get_vm_pde(struct amdgpu_device *adev, int level,
*flags |= AMDGPU_PDE_BFS(0x9);
} else if (level == AMDGPU_VM_PDB0) {
- if (*flags & AMDGPU_PDE_PTE)
+ if (*flags & AMDGPU_PDE_PTE) {
*flags &= ~AMDGPU_PDE_PTE;
- else
+ if (!(*flags & AMDGPU_PTE_VALID))
+ *addr |= 1 << PAGE_SHIFT;
+ } else {
*flags |= AMDGPU_PTE_TF;
+ }
}
}
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
index cc3fdbbcd314..f92744b8d79d 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
@@ -185,6 +185,10 @@ static int mes_v11_0_add_hw_queue(struct amdgpu_mes *mes,
mes_add_queue_pkt.is_kfd_process = input->is_kfd_process;
mes_add_queue_pkt.trap_en = 1;
+ /* For KFD, gds_size is re-used for queue size (needed in MES for AQL queues) */
+ mes_add_queue_pkt.is_aql_queue = input->is_aql_queue;
+ mes_add_queue_pkt.gds_size = input->queue_size;
+
return mes_v11_0_submit_pkt_and_poll_completion(mes,
&mes_add_queue_pkt, sizeof(mes_add_queue_pkt),
offsetof(union MESAPI__ADD_QUEUE, api_status));
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c b/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c
index b465baa26762..aa761ff3a5fa 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c
@@ -380,6 +380,7 @@ static void nbio_v2_3_enable_aspm(struct amdgpu_device *adev,
WREG32_PCIE(smnPCIE_LC_CNTL, data);
}
+#ifdef CONFIG_PCIEASPM
static void nbio_v2_3_program_ltr(struct amdgpu_device *adev)
{
uint32_t def, data;
@@ -401,9 +402,11 @@ static void nbio_v2_3_program_ltr(struct amdgpu_device *adev)
if (def != data)
WREG32_PCIE(smnBIF_CFG_DEV0_EPF0_DEVICE_CNTL2, data);
}
+#endif
static void nbio_v2_3_program_aspm(struct amdgpu_device *adev)
{
+#ifdef CONFIG_PCIEASPM
uint32_t def, data;
def = data = RREG32_PCIE(smnPCIE_LC_CNTL);
@@ -459,7 +462,10 @@ static void nbio_v2_3_program_aspm(struct amdgpu_device *adev)
if (def != data)
WREG32_PCIE(smnPCIE_LC_CNTL6, data);
- nbio_v2_3_program_ltr(adev);
+ /* Don't bother about LTR if LTR is not enabled
+ * in the path */
+ if (adev->pdev->ltr_path)
+ nbio_v2_3_program_ltr(adev);
def = data = RREG32_SOC15(NBIO, 0, mmRCC_BIF_STRAP3);
data |= 0x5DE0 << RCC_BIF_STRAP3__STRAP_VLINK_ASPM_IDLE_TIMER__SHIFT;
@@ -483,6 +489,7 @@ static void nbio_v2_3_program_aspm(struct amdgpu_device *adev)
data &= ~PCIE_LC_CNTL3__LC_DSC_DONT_ENTER_L23_AFTER_PME_ACK_MASK;
if (def != data)
WREG32_PCIE(smnPCIE_LC_CNTL3, data);
+#endif
}
static void nbio_v2_3_apply_lc_spc_mode_wa(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c b/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c
index f7f6ddebd3e4..37615a77287b 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c
@@ -282,6 +282,7 @@ static void nbio_v6_1_init_registers(struct amdgpu_device *adev)
mmBIF_BX_DEV0_EPF0_VF0_HDP_MEM_COHERENCY_FLUSH_CNTL) << 2;
}
+#ifdef CONFIG_PCIEASPM
static void nbio_v6_1_program_ltr(struct amdgpu_device *adev)
{
uint32_t def, data;
@@ -303,9 +304,11 @@ static void nbio_v6_1_program_ltr(struct amdgpu_device *adev)
if (def != data)
WREG32_PCIE(smnBIF_CFG_DEV0_EPF0_DEVICE_CNTL2, data);
}
+#endif
static void nbio_v6_1_program_aspm(struct amdgpu_device *adev)
{
+#ifdef CONFIG_PCIEASPM
uint32_t def, data;
def = data = RREG32_PCIE(smnPCIE_LC_CNTL);
@@ -361,7 +364,10 @@ static void nbio_v6_1_program_aspm(struct amdgpu_device *adev)
if (def != data)
WREG32_PCIE(smnPCIE_LC_CNTL6, data);
- nbio_v6_1_program_ltr(adev);
+ /* Don't bother about LTR if LTR is not enabled
+ * in the path */
+ if (adev->pdev->ltr_path)
+ nbio_v6_1_program_ltr(adev);
def = data = RREG32_PCIE(smnRCC_BIF_STRAP3);
data |= 0x5DE0 << RCC_BIF_STRAP3__STRAP_VLINK_ASPM_IDLE_TIMER__SHIFT;
@@ -385,6 +391,7 @@ static void nbio_v6_1_program_aspm(struct amdgpu_device *adev)
data &= ~PCIE_LC_CNTL3__LC_DSC_DONT_ENTER_L23_AFTER_PME_ACK_MASK;
if (def != data)
WREG32_PCIE(smnPCIE_LC_CNTL3, data);
+#endif
}
const struct amdgpu_nbio_funcs nbio_v6_1_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
index 11848d1e238b..19455a725939 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
@@ -673,6 +673,7 @@ struct amdgpu_nbio_ras nbio_v7_4_ras = {
};
+#ifdef CONFIG_PCIEASPM
static void nbio_v7_4_program_ltr(struct amdgpu_device *adev)
{
uint32_t def, data;
@@ -694,9 +695,11 @@ static void nbio_v7_4_program_ltr(struct amdgpu_device *adev)
if (def != data)
WREG32_PCIE(smnBIF_CFG_DEV0_EPF0_DEVICE_CNTL2, data);
}
+#endif
static void nbio_v7_4_program_aspm(struct amdgpu_device *adev)
{
+#ifdef CONFIG_PCIEASPM
uint32_t def, data;
if (adev->ip_versions[NBIO_HWIP][0] == IP_VERSION(7, 4, 4))
@@ -755,7 +758,10 @@ static void nbio_v7_4_program_aspm(struct amdgpu_device *adev)
if (def != data)
WREG32_PCIE(smnPCIE_LC_CNTL6, data);
- nbio_v7_4_program_ltr(adev);
+ /* Don't bother about LTR if LTR is not enabled
+ * in the path */
+ if (adev->pdev->ltr_path)
+ nbio_v7_4_program_ltr(adev);
def = data = RREG32_PCIE(smnRCC_BIF_STRAP3);
data |= 0x5DE0 << RCC_BIF_STRAP3__STRAP_VLINK_ASPM_IDLE_TIMER__SHIFT;
@@ -779,6 +785,7 @@ static void nbio_v7_4_program_aspm(struct amdgpu_device *adev)
data &= ~PCIE_LC_CNTL3__LC_DSC_DONT_ENTER_L23_AFTER_PME_ACK_MASK;
if (def != data)
WREG32_PCIE(smnPCIE_LC_CNTL3, data);
+#endif
}
const struct amdgpu_nbio_funcs nbio_v7_4_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c
index 1dc95ef21da6..def89379b51a 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c
@@ -28,6 +28,14 @@
#include "nbio/nbio_7_7_0_sh_mask.h"
#include <uapi/linux/kfd_ioctl.h>
+static void nbio_v7_7_remap_hdp_registers(struct amdgpu_device *adev)
+{
+ WREG32_SOC15(NBIO, 0, regBIF_BX0_REMAP_HDP_MEM_FLUSH_CNTL,
+ adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL);
+ WREG32_SOC15(NBIO, 0, regBIF_BX0_REMAP_HDP_REG_FLUSH_CNTL,
+ adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_REG_FLUSH_CNTL);
+}
+
static u32 nbio_v7_7_get_rev_id(struct amdgpu_device *adev)
{
u32 tmp;
@@ -68,12 +76,6 @@ static void nbio_v7_7_sdma_doorbell_range(struct amdgpu_device *adev, int instan
doorbell_range = REG_SET_FIELD(doorbell_range,
GDC0_BIF_CSDMA_DOORBELL_RANGE,
SIZE, doorbell_size);
- doorbell_range = REG_SET_FIELD(doorbell_range,
- GDC0_BIF_SDMA0_DOORBELL_RANGE,
- OFFSET, doorbell_index);
- doorbell_range = REG_SET_FIELD(doorbell_range,
- GDC0_BIF_SDMA0_DOORBELL_RANGE,
- SIZE, doorbell_size);
} else {
doorbell_range = REG_SET_FIELD(doorbell_range,
GDC0_BIF_SDMA0_DOORBELL_RANGE,
@@ -342,4 +344,5 @@ const struct amdgpu_nbio_funcs nbio_v7_7_funcs = {
.get_clockgating_state = nbio_v7_7_get_clockgating_state,
.ih_control = nbio_v7_7_ih_control,
.init_registers = nbio_v7_7_init_registers,
+ .remap_hdp_registers = nbio_v7_7_remap_hdp_registers,
};
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
index 65181efba50e..56424f75dd2c 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
@@ -1504,6 +1504,11 @@ static int sdma_v4_0_start(struct amdgpu_device *adev)
WREG32_SDMA(i, mmSDMA0_CNTL, temp);
if (!amdgpu_sriov_vf(adev)) {
+ ring = &adev->sdma.instance[i].ring;
+ adev->nbio.funcs->sdma_doorbell_range(adev, i,
+ ring->use_doorbell, ring->doorbell_index,
+ adev->doorbell_index.sdma_doorbell_range);
+
/* unhalt engine */
temp = RREG32_SDMA(i, mmSDMA0_F32_CNTL);
temp = REG_SET_FIELD(temp, SDMA0_F32_CNTL, HALT, 0);
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index fde6154f2009..183024d7c184 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -1211,25 +1211,6 @@ static int soc15_common_sw_fini(void *handle)
return 0;
}
-static void soc15_doorbell_range_init(struct amdgpu_device *adev)
-{
- int i;
- struct amdgpu_ring *ring;
-
- /* sdma/ih doorbell range are programed by hypervisor */
- if (!amdgpu_sriov_vf(adev)) {
- for (i = 0; i < adev->sdma.num_instances; i++) {
- ring = &adev->sdma.instance[i].ring;
- adev->nbio.funcs->sdma_doorbell_range(adev, i,
- ring->use_doorbell, ring->doorbell_index,
- adev->doorbell_index.sdma_doorbell_range);
- }
-
- adev->nbio.funcs->ih_doorbell_range(adev, adev->irq.ih.use_doorbell,
- adev->irq.ih.doorbell_index);
- }
-}
-
static int soc15_common_hw_init(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
@@ -1249,12 +1230,6 @@ static int soc15_common_hw_init(void *handle)
/* enable the doorbell aperture */
soc15_enable_doorbell_aperture(adev, true);
- /* HW doorbell routing policy: doorbell writing not
- * in SDMA/IH/MM/ACV range will be routed to CP. So
- * we need to init SDMA/IH/MM/ACV doorbell range prior
- * to CP ip block init and ring test.
- */
- soc15_doorbell_range_init(adev);
return 0;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c
index 55284b24f113..6e564b549b9f 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc21.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc21.c
@@ -421,6 +421,7 @@ static bool soc21_need_full_reset(struct amdgpu_device *adev)
{
switch (adev->ip_versions[GC_HWIP][0]) {
case IP_VERSION(11, 0, 0):
+ return amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__UMC);
case IP_VERSION(11, 0, 2):
return false;
default:
@@ -624,6 +625,7 @@ static int soc21_common_early_init(void *handle)
AMD_CG_SUPPORT_JPEG_MGCG;
adev->pg_flags =
AMD_PG_SUPPORT_GFX_PG |
+ AMD_PG_SUPPORT_VCN_DPG |
AMD_PG_SUPPORT_JPEG;
adev->external_rev_id = adev->rev_id + 0x1;
break;
diff --git a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
index 03b7066471f9..1e83db0c5438 100644
--- a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
@@ -289,6 +289,10 @@ static int vega10_ih_irq_init(struct amdgpu_device *adev)
}
}
+ if (!amdgpu_sriov_vf(adev))
+ adev->nbio.funcs->ih_doorbell_range(adev, adev->irq.ih.use_doorbell,
+ adev->irq.ih.doorbell_index);
+
pci_set_master(adev->pdev);
/* enable interrupts */
diff --git a/drivers/gpu/drm/amd/amdgpu/vega20_ih.c b/drivers/gpu/drm/amd/amdgpu/vega20_ih.c
index 2022ffbb8dba..59dfca093155 100644
--- a/drivers/gpu/drm/amd/amdgpu/vega20_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/vega20_ih.c
@@ -340,6 +340,10 @@ static int vega20_ih_irq_init(struct amdgpu_device *adev)
}
}
+ if (!amdgpu_sriov_vf(adev))
+ adev->nbio.funcs->ih_doorbell_range(adev, adev->irq.ih.use_doorbell,
+ adev->irq.ih.doorbell_index);
+
pci_set_master(adev->pdev);
/* enable interrupts */