summaryrefslogtreecommitdiffstats
path: root/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c')
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c256
1 files changed, 108 insertions, 148 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 25adf2b847e8..3f6f14ce1511 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -43,6 +43,8 @@
#include "amdgpu_amdkfd.h"
+#include "amdgpu_ras.h"
+
/*
* KMS wrapper.
* - 3.0.0 - initial driver
@@ -82,13 +84,12 @@
* - 3.33.0 - Fixes for GDS ENOMEM failures in AMDGPU_CS.
* - 3.34.0 - Non-DC can flip correctly between buffers with different pitches
* - 3.35.0 - Add drm_amdgpu_info_device::tcc_disabled_mask
+ * - 3.36.0 - Allow reading more status registers on si/cik
*/
#define KMS_DRIVER_MAJOR 3
-#define KMS_DRIVER_MINOR 35
+#define KMS_DRIVER_MINOR 36
#define KMS_DRIVER_PATCHLEVEL 0
-#define AMDGPU_MAX_TIMEOUT_PARAM_LENTH 256
-
int amdgpu_vram_limit = 0;
int amdgpu_vis_vram_limit = 0;
int amdgpu_gart_size = -1; /* auto */
@@ -101,7 +102,7 @@ int amdgpu_disp_priority = 0;
int amdgpu_hw_i2c = 0;
int amdgpu_pcie_gen2 = -1;
int amdgpu_msi = -1;
-char amdgpu_lockup_timeout[AMDGPU_MAX_TIMEOUT_PARAM_LENTH];
+char amdgpu_lockup_timeout[AMDGPU_MAX_TIMEOUT_PARAM_LENGTH];
int amdgpu_dpm = -1;
int amdgpu_fw_load_type = -1;
int amdgpu_aspm = -1;
@@ -128,11 +129,7 @@ char *amdgpu_disable_cu = NULL;
char *amdgpu_virtual_display = NULL;
/* OverDrive(bit 14) disabled by default*/
uint amdgpu_pp_feature_mask = 0xffffbfff;
-int amdgpu_ngg = 0;
-int amdgpu_prim_buf_per_se = 0;
-int amdgpu_pos_buf_per_se = 0;
-int amdgpu_cntl_sb_buf_per_se = 0;
-int amdgpu_param_buf_per_se = 0;
+uint amdgpu_force_long_training = 0;
int amdgpu_job_hang_limit = 0;
int amdgpu_lbpw = -1;
int amdgpu_compute_multipipe = -1;
@@ -146,12 +143,13 @@ int amdgpu_mcbp = 0;
int amdgpu_discovery = -1;
int amdgpu_mes = 0;
int amdgpu_noretry = 1;
+int amdgpu_force_asic_type = -1;
struct amdgpu_mgpu_info mgpu_info = {
.mutex = __MUTEX_INITIALIZER(mgpu_info.mutex),
};
int amdgpu_ras_enable = -1;
-uint amdgpu_ras_mask = 0xfffffffb;
+uint amdgpu_ras_mask = 0xffffffff;
/**
* DOC: vramlimit (int)
@@ -244,16 +242,21 @@ module_param_named(msi, amdgpu_msi, int, 0444);
*
* The format can be [Non-Compute] or [GFX,Compute,SDMA,Video]. That is there can be one or
* multiple values specified. 0 and negative values are invalidated. They will be adjusted
- * to default timeout.
- * - With one value specified, the setting will apply to all non-compute jobs.
- * - With multiple values specified, the first one will be for GFX. The second one is for Compute.
- * And the third and fourth ones are for SDMA and Video.
+ * to the default timeout.
+ *
+ * - With one value specified, the setting will apply to all non-compute jobs.
+ * - With multiple values specified, the first one will be for GFX.
+ * The second one is for Compute. The third and fourth ones are
+ * for SDMA and Video.
+ *
* By default(with no lockup_timeout settings), the timeout for all non-compute(GFX, SDMA and Video)
* jobs is 10000. And there is no timeout enforced on compute jobs.
*/
-MODULE_PARM_DESC(lockup_timeout, "GPU lockup timeout in ms (default: 10000 for non-compute jobs and infinity timeout for compute jobs."
+MODULE_PARM_DESC(lockup_timeout, "GPU lockup timeout in ms (default: for bare metal 10000 for non-compute jobs and infinity timeout for compute jobs; "
+ "for passthrough or sriov, 10000 for all jobs."
" 0: keep default value. negative: infinity timeout), "
- "format is [Non-Compute] or [GFX,Compute,SDMA,Video]");
+ "format: for bare metal [Non-Compute] or [GFX,Compute,SDMA,Video]; "
+ "for passthrough or sriov [all jobs] or [GFX,Compute,SDMA,Video].");
module_param_string(lockup_timeout, amdgpu_lockup_timeout, sizeof(amdgpu_lockup_timeout), 0444);
/**
@@ -392,6 +395,14 @@ MODULE_PARM_DESC(ppfeaturemask, "all power features enabled (default))");
module_param_named(ppfeaturemask, amdgpu_pp_feature_mask, uint, 0444);
/**
+ * DOC: forcelongtraining (uint)
+ * Force long memory training in resume.
+ * The default is zero, indicates short training in resume.
+ */
+MODULE_PARM_DESC(forcelongtraining, "force memory long training");
+module_param_named(forcelongtraining, amdgpu_force_long_training, uint, 0444);
+
+/**
* DOC: pcie_gen_cap (uint)
* Override PCIE gen speed capabilities. See the CAIL flags in drivers/gpu/drm/amd/include/amd_pcie.h.
* The default is 0 (automatic for each asic).
@@ -449,42 +460,6 @@ MODULE_PARM_DESC(virtual_display,
module_param_named(virtual_display, amdgpu_virtual_display, charp, 0444);
/**
- * DOC: ngg (int)
- * Set to enable Next Generation Graphics (1 = enable). The default is 0 (disabled).
- */
-MODULE_PARM_DESC(ngg, "Next Generation Graphics (1 = enable, 0 = disable(default depending on gfx))");
-module_param_named(ngg, amdgpu_ngg, int, 0444);
-
-/**
- * DOC: prim_buf_per_se (int)
- * Override the size of Primitive Buffer per Shader Engine in Byte. The default is 0 (depending on gfx).
- */
-MODULE_PARM_DESC(prim_buf_per_se, "the size of Primitive Buffer per Shader Engine (default depending on gfx)");
-module_param_named(prim_buf_per_se, amdgpu_prim_buf_per_se, int, 0444);
-
-/**
- * DOC: pos_buf_per_se (int)
- * Override the size of Position Buffer per Shader Engine in Byte. The default is 0 (depending on gfx).
- */
-MODULE_PARM_DESC(pos_buf_per_se, "the size of Position Buffer per Shader Engine (default depending on gfx)");
-module_param_named(pos_buf_per_se, amdgpu_pos_buf_per_se, int, 0444);
-
-/**
- * DOC: cntl_sb_buf_per_se (int)
- * Override the size of Control Sideband per Shader Engine in Byte. The default is 0 (depending on gfx).
- */
-MODULE_PARM_DESC(cntl_sb_buf_per_se, "the size of Control Sideband per Shader Engine (default depending on gfx)");
-module_param_named(cntl_sb_buf_per_se, amdgpu_cntl_sb_buf_per_se, int, 0444);
-
-/**
- * DOC: param_buf_per_se (int)
- * Override the size of Off-Chip Parameter Cache per Shader Engine in Byte.
- * The default is 0 (depending on gfx).
- */
-MODULE_PARM_DESC(param_buf_per_se, "the size of Off-Chip Parameter Cache per Shader Engine (default depending on gfx)");
-module_param_named(param_buf_per_se, amdgpu_param_buf_per_se, int, 0444);
-
-/**
* DOC: job_hang_limit (int)
* Set how much time allow a job hang and not drop it. The default is 0.
*/
@@ -616,6 +591,16 @@ MODULE_PARM_DESC(noretry,
"Disable retry faults (0 = retry enabled, 1 = retry disabled (default))");
module_param_named(noretry, amdgpu_noretry, int, 0644);
+/**
+ * DOC: force_asic_type (int)
+ * A non negative value used to specify the asic type for all supported GPUs.
+ */
+MODULE_PARM_DESC(force_asic_type,
+ "A non negative value used to specify the asic type for all supported GPUs");
+module_param_named(force_asic_type, amdgpu_force_asic_type, int, 0444);
+
+
+
#ifdef CONFIG_HSA_AMD
/**
* DOC: sched_policy (int)
@@ -1013,15 +998,17 @@ static const struct pci_device_id pciidlist[] = {
{0x1002, 0x731B, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10},
{0x1002, 0x731F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10},
/* Navi14 */
- {0x1002, 0x7340, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14|AMD_EXP_HW_SUPPORT},
- {0x1002, 0x7341, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14|AMD_EXP_HW_SUPPORT},
- {0x1002, 0x7347, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14|AMD_EXP_HW_SUPPORT},
+ {0x1002, 0x7340, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14},
+ {0x1002, 0x7341, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14},
+ {0x1002, 0x7347, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14},
+ {0x1002, 0x734F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14},
/* Renoir */
{0x1002, 0x1636, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RENOIR|AMD_IS_APU|AMD_EXP_HW_SUPPORT},
/* Navi12 */
{0x1002, 0x7360, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI12|AMD_EXP_HW_SUPPORT},
+ {0x1002, 0x7362, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI12|AMD_EXP_HW_SUPPORT},
{0, 0, 0}
};
@@ -1127,7 +1114,10 @@ amdgpu_pci_remove(struct pci_dev *pdev)
{
struct drm_device *dev = pci_get_drvdata(pdev);
- DRM_ERROR("Device removal is currently not supported outside of fbcon\n");
+#ifdef MODULE
+ if (THIS_MODULE->state != MODULE_STATE_GOING)
+#endif
+ DRM_ERROR("Hotplug removal is not supported\n");
drm_dev_unplug(dev);
drm_dev_put(dev);
pci_disable_device(pdev);
@@ -1140,6 +1130,9 @@ amdgpu_pci_shutdown(struct pci_dev *pdev)
struct drm_device *dev = pci_get_drvdata(pdev);
struct amdgpu_device *adev = dev->dev_private;
+ if (amdgpu_ras_intr_triggered())
+ return;
+
/* if we are running in a VM, make sure the device
* torn down properly on reboot/shutdown.
* unfortunately we can't detect certain
@@ -1154,7 +1147,7 @@ static int amdgpu_pmops_suspend(struct device *dev)
{
struct drm_device *drm_dev = dev_get_drvdata(dev);
- return amdgpu_device_suspend(drm_dev, true, true);
+ return amdgpu_device_suspend(drm_dev, true);
}
static int amdgpu_pmops_resume(struct device *dev)
@@ -1162,66 +1155,82 @@ static int amdgpu_pmops_resume(struct device *dev)
struct drm_device *drm_dev = dev_get_drvdata(dev);
/* GPU comes up enabled by the bios on resume */
- if (amdgpu_device_is_px(drm_dev)) {
+ if (amdgpu_device_supports_boco(drm_dev) ||
+ amdgpu_device_supports_baco(drm_dev)) {
pm_runtime_disable(dev);
pm_runtime_set_active(dev);
pm_runtime_enable(dev);
}
- return amdgpu_device_resume(drm_dev, true, true);
+ return amdgpu_device_resume(drm_dev, true);
}
static int amdgpu_pmops_freeze(struct device *dev)
{
struct drm_device *drm_dev = dev_get_drvdata(dev);
+ struct amdgpu_device *adev = drm_dev->dev_private;
+ int r;
- return amdgpu_device_suspend(drm_dev, false, true);
+ r = amdgpu_device_suspend(drm_dev, true);
+ if (r)
+ return r;
+ return amdgpu_asic_reset(adev);
}
static int amdgpu_pmops_thaw(struct device *dev)
{
struct drm_device *drm_dev = dev_get_drvdata(dev);
- return amdgpu_device_resume(drm_dev, false, true);
+ return amdgpu_device_resume(drm_dev, true);
}
static int amdgpu_pmops_poweroff(struct device *dev)
{
struct drm_device *drm_dev = dev_get_drvdata(dev);
- return amdgpu_device_suspend(drm_dev, true, true);
+ return amdgpu_device_suspend(drm_dev, true);
}
static int amdgpu_pmops_restore(struct device *dev)
{
struct drm_device *drm_dev = dev_get_drvdata(dev);
- return amdgpu_device_resume(drm_dev, false, true);
+ return amdgpu_device_resume(drm_dev, true);
}
static int amdgpu_pmops_runtime_suspend(struct device *dev)
{
struct pci_dev *pdev = to_pci_dev(dev);
struct drm_device *drm_dev = pci_get_drvdata(pdev);
+ struct amdgpu_device *adev = drm_dev->dev_private;
int ret;
- if (!amdgpu_device_is_px(drm_dev)) {
+ if (!adev->runpm) {
pm_runtime_forbid(dev);
return -EBUSY;
}
- drm_dev->switch_power_state = DRM_SWITCH_POWER_CHANGING;
+ if (amdgpu_device_supports_boco(drm_dev))
+ drm_dev->switch_power_state = DRM_SWITCH_POWER_CHANGING;
drm_kms_helper_poll_disable(drm_dev);
- ret = amdgpu_device_suspend(drm_dev, false, false);
- pci_save_state(pdev);
- pci_disable_device(pdev);
- pci_ignore_hotplug(pdev);
- if (amdgpu_is_atpx_hybrid())
- pci_set_power_state(pdev, PCI_D3cold);
- else if (!amdgpu_has_atpx_dgpu_power_cntl())
- pci_set_power_state(pdev, PCI_D3hot);
- drm_dev->switch_power_state = DRM_SWITCH_POWER_DYNAMIC_OFF;
+ ret = amdgpu_device_suspend(drm_dev, false);
+ if (amdgpu_device_supports_boco(drm_dev)) {
+ /* Only need to handle PCI state in the driver for ATPX
+ * PCI core handles it for _PR3.
+ */
+ if (amdgpu_is_atpx_hybrid()) {
+ pci_ignore_hotplug(pdev);
+ } else {
+ pci_save_state(pdev);
+ pci_disable_device(pdev);
+ pci_ignore_hotplug(pdev);
+ pci_set_power_state(pdev, PCI_D3cold);
+ }
+ drm_dev->switch_power_state = DRM_SWITCH_POWER_DYNAMIC_OFF;
+ } else if (amdgpu_device_supports_baco(drm_dev)) {
+ amdgpu_device_baco_enter(drm_dev);
+ }
return 0;
}
@@ -1230,34 +1239,45 @@ static int amdgpu_pmops_runtime_resume(struct device *dev)
{
struct pci_dev *pdev = to_pci_dev(dev);
struct drm_device *drm_dev = pci_get_drvdata(pdev);
+ struct amdgpu_device *adev = drm_dev->dev_private;
int ret;
- if (!amdgpu_device_is_px(drm_dev))
+ if (!adev->runpm)
return -EINVAL;
- drm_dev->switch_power_state = DRM_SWITCH_POWER_CHANGING;
+ if (amdgpu_device_supports_boco(drm_dev)) {
+ drm_dev->switch_power_state = DRM_SWITCH_POWER_CHANGING;
- if (amdgpu_is_atpx_hybrid() ||
- !amdgpu_has_atpx_dgpu_power_cntl())
- pci_set_power_state(pdev, PCI_D0);
- pci_restore_state(pdev);
- ret = pci_enable_device(pdev);
- if (ret)
- return ret;
- pci_set_master(pdev);
-
- ret = amdgpu_device_resume(drm_dev, false, false);
+ /* Only need to handle PCI state in the driver for ATPX
+ * PCI core handles it for _PR3.
+ */
+ if (amdgpu_is_atpx_hybrid()) {
+ pci_set_master(pdev);
+ } else {
+ pci_set_power_state(pdev, PCI_D0);
+ pci_restore_state(pdev);
+ ret = pci_enable_device(pdev);
+ if (ret)
+ return ret;
+ pci_set_master(pdev);
+ }
+ } else if (amdgpu_device_supports_baco(drm_dev)) {
+ amdgpu_device_baco_exit(drm_dev);
+ }
+ ret = amdgpu_device_resume(drm_dev, false);
drm_kms_helper_poll_enable(drm_dev);
- drm_dev->switch_power_state = DRM_SWITCH_POWER_ON;
+ if (amdgpu_device_supports_boco(drm_dev))
+ drm_dev->switch_power_state = DRM_SWITCH_POWER_ON;
return 0;
}
static int amdgpu_pmops_runtime_idle(struct device *dev)
{
struct drm_device *drm_dev = dev_get_drvdata(dev);
+ struct amdgpu_device *adev = drm_dev->dev_private;
struct drm_crtc *crtc;
- if (!amdgpu_device_is_px(drm_dev)) {
+ if (!adev->runpm) {
pm_runtime_forbid(dev);
return -EBUSY;
}
@@ -1347,66 +1367,6 @@ int amdgpu_file_to_fpriv(struct file *filp, struct amdgpu_fpriv **fpriv)
return 0;
}
-int amdgpu_device_get_job_timeout_settings(struct amdgpu_device *adev)
-{
- char *input = amdgpu_lockup_timeout;
- char *timeout_setting = NULL;
- int index = 0;
- long timeout;
- int ret = 0;
-
- /*
- * By default timeout for non compute jobs is 10000.
- * And there is no timeout enforced on compute jobs.
- */
- adev->gfx_timeout = msecs_to_jiffies(10000);
- adev->sdma_timeout = adev->video_timeout = adev->gfx_timeout;
- adev->compute_timeout = MAX_SCHEDULE_TIMEOUT;
-
- if (strnlen(input, AMDGPU_MAX_TIMEOUT_PARAM_LENTH)) {
- while ((timeout_setting = strsep(&input, ",")) &&
- strnlen(timeout_setting, AMDGPU_MAX_TIMEOUT_PARAM_LENTH)) {
- ret = kstrtol(timeout_setting, 0, &timeout);
- if (ret)
- return ret;
-
- if (timeout == 0) {
- index++;
- continue;
- } else if (timeout < 0) {
- timeout = MAX_SCHEDULE_TIMEOUT;
- } else {
- timeout = msecs_to_jiffies(timeout);
- }
-
- switch (index++) {
- case 0:
- adev->gfx_timeout = timeout;
- break;
- case 1:
- adev->compute_timeout = timeout;
- break;
- case 2:
- adev->sdma_timeout = timeout;
- break;
- case 3:
- adev->video_timeout = timeout;
- break;
- default:
- break;
- }
- }
- /*
- * There is only one value specified and
- * it should apply to all non-compute jobs.
- */
- if (index == 1)
- adev->sdma_timeout = adev->video_timeout = adev->gfx_timeout;
- }
-
- return ret;
-}
-
static bool
amdgpu_get_crtc_scanout_position(struct drm_device *dev, unsigned int pipe,
bool in_vblank_irq, int *vpos, int *hpos,
generated by cgit v1.2.3 (git 2.39.1) at 2025-05-13 13:27:07 +0000