summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2021-04-28 10:01:40 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2021-04-28 10:01:40 -0700
commit68a32ba14177d4a21c4a9a941cf1d7aea86d436f (patch)
tree945c20860766c22b19d1806d5b5db5b37bc65b65 /drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
parent3aa139aa9fdc138a84243dc49dc18d9b40e1c6e4 (diff)
parenta1a1ca70deb3ec600eeabb21de7f3f48aaae5695 (diff)
Merge tag 'drm-next-2021-04-28' of git://anongit.freedesktop.org/drm/drm
Pull drm updates from Dave Airlie: "The usual lots of work all over the place. i915 has gotten some Alderlake work and prelim DG1 code, along with a major locking rework over the GEM code, and brings back the property of timing out long running jobs using a watchdog. amdgpu has some Alderbran support (new GPU), freesync HDMI support along with a lot other fixes. Outside of the drm, there is a new printf specifier added which should have all the correct acks/sobs: - printk fourcc modifier support added %p4cc Summary: core: - drm_crtc_commit_wait - atomic plane state helpers reworked for full state - dma-buf heaps API rework - edid: rework and improvements for displayid dp-mst: - better topology logging bridge: - Chipone ICN6211 - Lontium LT8912B - anx7625 regulator support panel: - fix lt9611 4k panels handling simple-kms: - add plane state helpers ttm: - debugfs support - removal of unused sysfs - ignore signaled moved fences - ioremap buffer according to mem caching i915: - Alderlake S enablement - Conversion to dma_resv_locking - Bring back watchdog timeout support - legacy ioctl cleanups - add GEM TDDO and RFC process - DG1 LMEM preparation work - intel_display.c refactoring - Gen9/TGL PCH combination support - eDP MSO Support - multiple PSR instance support - Link training debug updates - Disable PSR2 support on JSL/EHL - DDR5/LPDDR5 support for bw calcs - LSPCON limited to gen9/10 platforms - HSW/BDW async flip/VTd corruption workaround - SAGV watermark fixes - SNB hard hang on ring resume fix - Limit imported dma-buf size - move to use new tasklet API - refactor KBL/TGL/ADL-S display/gt steppings - refactoring legacy DP/HDMI, FB plane code out amdgpu: - uapi: add ioctl to query video capabilities - Iniital AMD Freesync HDMI support - Initial Adebaran support - 10bpc dithering improvements - DCN secure display support - Drop legacy IO BAR requirements - PCIE/S0ix/RAS/Prime/Reset fixes - Display ASSR support - SMU gfx busy queues for RV/PCO - Initial LTTPR display work amdkfd: - MMU notifier fixes - APU fixes radeon: - debugfs cleanps - fw error handling ifix - Flexible array cleanups msm: - big DSI phy/pll cleanup - sc7280 initial support - commong bandwidth scaling path - shrinker locking contention fixes - unpin/swap support for GEM objcets ast: - cursor plane handling reworked tegra: - don't register DP AUX channels before connectors zynqmp: - fix OOB struct padding memset gma500: - drop ttm and medfield support exynos: - request_irq cleanup function mediatek: - fine tune line time for EOTp - MT8192 dpi support - atomic crtc config updates - don't support HDMI connector creation mxsdb: - imx8mm support panfrost: - MMU IRQ handling rework qxl: - locking fixes - resource deallocation changes sun4i: - add alpha properties to UI/VI layers vc4: - RPi4 CEC support vmwgfx: - doc cleanups arc: - moved to drm/tiny" * tag 'drm-next-2021-04-28' of git://anongit.freedesktop.org/drm/drm: (1390 commits) drm/ttm: Don't count pages in SG BOs against pages_limit drm/ttm: fix return value check drm/bridge: lt8912b: fix incorrect handling of of_* return values drm: bridge: fix LONTIUM use of mipi_dsi_() functions drm: bridge: fix ANX7625 use of mipi_dsi_() functions drm/amdgpu: page retire over debugfs mechanism drm/radeon: Fix a missing check bug in radeon_dp_mst_detect() drm/amd/display: Fix the Wunused-function warning drm/radeon/r600: Fix variables that are not used after assignment drm/amdgpu/smu7: fix CAC setting on TOPAZ drm/amd/display: Update DCN302 SR Exit Latency drm/amdgpu: enable ras eeprom on aldebaran drm/amdgpu: RAS harvest on driver load drm/amdgpu: add ras aldebaran ras eeprom driver drm/amd/pm: increase time out value when sending msg to SMU drm/amdgpu: add DMUB outbox event IRQ source define/complete/debug flag drm/amd/pm: add the callback to get vbios bootup values for vangogh drm/radeon: Fix size overflow drm/amdgpu: Fix size overflow drm/amdgpu: move mmhub ras_func init to ip specific file ...
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c')
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c43
1 files changed, 29 insertions, 14 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
index 659b385b27b5..8567d5d77346 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
@@ -24,7 +24,6 @@
#include <linux/list.h>
#include "amdgpu.h"
#include "amdgpu_xgmi.h"
-#include "amdgpu_smu.h"
#include "amdgpu_ras.h"
#include "soc15.h"
#include "df/df_3_6_offset.h"
@@ -217,7 +216,7 @@ static ssize_t amdgpu_xgmi_show_device_id(struct device *dev,
struct drm_device *ddev = dev_get_drvdata(dev);
struct amdgpu_device *adev = drm_to_adev(ddev);
- return snprintf(buf, PAGE_SIZE, "%llu\n", adev->gmc.xgmi.node_id);
+ return sysfs_emit(buf, "%llu\n", adev->gmc.xgmi.node_id);
}
@@ -246,7 +245,7 @@ static ssize_t amdgpu_xgmi_show_error(struct device *dev,
adev->df.funcs->set_fica(adev, ficaa_pie_status_in, 0, 0);
- return snprintf(buf, PAGE_SIZE, "%u\n", error_count);
+ return sysfs_emit(buf, "%u\n", error_count);
}
@@ -468,15 +467,22 @@ int amdgpu_xgmi_update_topology(struct amdgpu_hive_info *hive, struct amdgpu_dev
}
+/*
+ * NOTE psp_xgmi_node_info.num_hops layout is as follows:
+ * num_hops[7:6] = link type (0 = xGMI2, 1 = xGMI3, 2/3 = reserved)
+ * num_hops[5:3] = reserved
+ * num_hops[2:0] = number of hops
+ */
int amdgpu_xgmi_get_hops_count(struct amdgpu_device *adev,
struct amdgpu_device *peer_adev)
{
struct psp_xgmi_topology_info *top = &adev->psp.xgmi_context.top_info;
+ uint8_t num_hops_mask = 0x7;
int i;
for (i = 0 ; i < top->num_nodes; ++i)
if (top->nodes[i].node_id == peer_adev->gmc.xgmi.node_id)
- return top->nodes[i].num_hops;
+ return top->nodes[i].num_hops & num_hops_mask;
return -EINVAL;
}
@@ -492,7 +498,8 @@ int amdgpu_xgmi_add_device(struct amdgpu_device *adev)
if (!adev->gmc.xgmi.supported)
return 0;
- if (amdgpu_device_ip_get_ip_block(adev, AMD_IP_BLOCK_TYPE_PSP)) {
+ if (!adev->gmc.xgmi.pending_reset &&
+ amdgpu_device_ip_get_ip_block(adev, AMD_IP_BLOCK_TYPE_PSP)) {
ret = psp_xgmi_initialize(&adev->psp);
if (ret) {
dev_err(adev->dev,
@@ -538,7 +545,8 @@ int amdgpu_xgmi_add_device(struct amdgpu_device *adev)
task_barrier_add_task(&hive->tb);
- if (amdgpu_device_ip_get_ip_block(adev, AMD_IP_BLOCK_TYPE_PSP)) {
+ if (!adev->gmc.xgmi.pending_reset &&
+ amdgpu_device_ip_get_ip_block(adev, AMD_IP_BLOCK_TYPE_PSP)) {
list_for_each_entry(tmp_adev, &hive->device_list, gmc.xgmi.head) {
/* update node list for other device in the hive */
if (tmp_adev != adev) {
@@ -567,7 +575,7 @@ int amdgpu_xgmi_add_device(struct amdgpu_device *adev)
}
}
- if (!ret)
+ if (!ret && !adev->gmc.xgmi.pending_reset)
ret = amdgpu_xgmi_sysfs_add_dev_info(adev, hive);
exit_unlock:
@@ -620,7 +628,7 @@ int amdgpu_xgmi_remove_device(struct amdgpu_device *adev)
return psp_xgmi_terminate(&adev->psp);
}
-int amdgpu_xgmi_ras_late_init(struct amdgpu_device *adev)
+static int amdgpu_xgmi_ras_late_init(struct amdgpu_device *adev)
{
int r;
struct ras_ih_if ih_info = {
@@ -634,7 +642,7 @@ int amdgpu_xgmi_ras_late_init(struct amdgpu_device *adev)
adev->gmc.xgmi.num_physical_nodes == 0)
return 0;
- amdgpu_xgmi_reset_ras_error_count(adev);
+ adev->gmc.xgmi.ras_funcs->reset_ras_error_count(adev);
if (!adev->gmc.xgmi.ras_if) {
adev->gmc.xgmi.ras_if = kmalloc(sizeof(struct ras_common_if), GFP_KERNEL);
@@ -656,7 +664,7 @@ int amdgpu_xgmi_ras_late_init(struct amdgpu_device *adev)
return r;
}
-void amdgpu_xgmi_ras_fini(struct amdgpu_device *adev)
+static void amdgpu_xgmi_ras_fini(struct amdgpu_device *adev)
{
if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__XGMI_WAFL) &&
adev->gmc.xgmi.ras_if) {
@@ -683,7 +691,7 @@ static void pcs_clear_status(struct amdgpu_device *adev, uint32_t pcs_status_reg
WREG32_PCIE(pcs_status_reg, 0);
}
-void amdgpu_xgmi_reset_ras_error_count(struct amdgpu_device *adev)
+static void amdgpu_xgmi_reset_ras_error_count(struct amdgpu_device *adev)
{
uint32_t i;
@@ -743,8 +751,8 @@ static int amdgpu_xgmi_query_pcs_error_status(struct amdgpu_device *adev,
return 0;
}
-int amdgpu_xgmi_query_ras_error_count(struct amdgpu_device *adev,
- void *ras_error_status)
+static int amdgpu_xgmi_query_ras_error_count(struct amdgpu_device *adev,
+ void *ras_error_status)
{
struct ras_err_data *err_data = (struct ras_err_data *)ras_error_status;
int i;
@@ -793,10 +801,17 @@ int amdgpu_xgmi_query_ras_error_count(struct amdgpu_device *adev,
break;
}
- amdgpu_xgmi_reset_ras_error_count(adev);
+ adev->gmc.xgmi.ras_funcs->reset_ras_error_count(adev);
err_data->ue_count += ue_cnt;
err_data->ce_count += ce_cnt;
return 0;
}
+
+const struct amdgpu_xgmi_ras_funcs xgmi_ras_funcs = {
+ .ras_late_init = amdgpu_xgmi_ras_late_init,
+ .ras_fini = amdgpu_xgmi_ras_fini,
+ .query_ras_error_count = amdgpu_xgmi_query_ras_error_count,
+ .reset_ras_error_count = amdgpu_xgmi_reset_ras_error_count,
+};