From ec01fe2dbf8cf2b2a25c6ac73eac357988f1bf7d Mon Sep 17 00:00:00 2001 From: Hawking Zhang Date: Fri, 21 Feb 2020 21:37:15 +0800 Subject: drm/amdgpu: enable PCS error report on VG20 Now driver will report XGMI/WAFL PCS error through sysfs xgmi_wafl_err_count node on Vega20 Signed-off-by: Hawking Zhang Reviewed-by: Guchun Chen Reviewed-by: Tao Zhou Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index 930633a0ed64..e1e8fd4b2b89 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -721,6 +721,9 @@ int amdgpu_ras_error_query(struct amdgpu_device *adev, if (adev->nbio.funcs->query_ras_error_count) adev->nbio.funcs->query_ras_error_count(adev, &err_data); break; + case AMDGPU_RAS_BLOCK__XGMI_WAFL: + amdgpu_xgmi_query_ras_error_count(adev, &err_data); + break; default: break; } -- cgit v1.2.3 From f9317014ea517e13a59b9d437948c5ab17ce4ed7 Mon Sep 17 00:00:00 2001 From: Tao Zhou Date: Fri, 6 Mar 2020 11:59:16 +0800 Subject: drm/amdgpu: add function to creat all ras debugfs node centralize all debugfs creation in one place for ras this is required to fix ras when the driver does not use the drm load and unload callbacks due to ordering issues with the drm device node. Signed-off-by: Tao Zhou Signed-off-by: Stanley.Yang Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 29 +++++++++++++++++++++++++++++ drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h | 2 ++ 2 files changed, 31 insertions(+) (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index e1e8fd4b2b89..7f29e704936e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -1113,6 +1113,35 @@ void amdgpu_ras_debugfs_create(struct amdgpu_device *adev, &amdgpu_ras_debugfs_ops); } +void amdgpu_ras_debugfs_create_all(struct amdgpu_device *adev) +{ + struct amdgpu_ras *con = amdgpu_ras_get_context(adev); + struct ras_manager *obj, *tmp; + struct ras_fs_if fs_info; + + /* + * it won't be called in resume path, no need to check + * suspend and gpu reset status + */ + if (!con) + return; + + amdgpu_ras_debugfs_create_ctrl_node(adev); + + list_for_each_entry_safe(obj, tmp, &con->head, node) { + if (!obj) + continue; + + if (amdgpu_ras_is_supported(adev, obj->head.block) && + (obj->attr_inuse == 1)) { + sprintf(fs_info.debugfs_name, "%s_err_inject", + ras_block_str(obj->head.block)); + fs_info.head = obj->head; + amdgpu_ras_debugfs_create(adev, &fs_info); + } + } +} + void amdgpu_ras_debugfs_remove(struct amdgpu_device *adev, struct ras_common_if *head) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h index a5fe29a9373e..55c3eceb390d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h @@ -592,6 +592,8 @@ int amdgpu_ras_sysfs_remove(struct amdgpu_device *adev, void amdgpu_ras_debugfs_create(struct amdgpu_device *adev, struct ras_fs_if *head); +void amdgpu_ras_debugfs_create_all(struct amdgpu_device *adev); + void amdgpu_ras_debugfs_remove(struct amdgpu_device *adev, struct ras_common_if *head); -- cgit v1.2.3 From 204eaac625d57d32d8b4c42b57271a359b76db5a Mon Sep 17 00:00:00 2001 From: Tao Zhou Date: Fri, 6 Mar 2020 12:24:06 +0800 Subject: drm/amdgpu: call ras_debugfs_create_all in debugfs_init and remove each ras IP's own debugfs creation this is required to fix ras when the driver does not use the drm load and unload callbacks due to ordering issues with the drm device node. Signed-off-by: Tao Zhou Signed-off-by: Stanley.Yang Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c | 3 +++ drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c | 1 - drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.c | 1 - drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.c | 1 - drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 5 ----- drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c | 1 - drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c | 1 - drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c | 1 - 8 files changed, 3 insertions(+), 11 deletions(-) (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c index 831f70dc8b59..c573edf02afc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c @@ -1294,6 +1294,7 @@ DEFINE_SIMPLE_ATTRIBUTE(fops_ib_preempt, NULL, DEFINE_SIMPLE_ATTRIBUTE(fops_sclk_set, NULL, amdgpu_debugfs_sclk_set, "%llu\n"); +extern void amdgpu_ras_debugfs_create_all(struct amdgpu_device *adev); int amdgpu_debugfs_init(struct amdgpu_device *adev) { int r, i; @@ -1366,6 +1367,8 @@ int amdgpu_debugfs_init(struct amdgpu_device *adev) } } + amdgpu_ras_debugfs_create_all(adev); + return amdgpu_debugfs_add_files(adev, amdgpu_debugfs_list, ARRAY_SIZE(amdgpu_debugfs_list)); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c index 952725e7243c..6b9c9193cdfa 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c @@ -573,7 +573,6 @@ int amdgpu_gfx_ras_late_init(struct amdgpu_device *adev) int r; struct ras_fs_if fs_info = { .sysfs_name = "gfx_err_count", - .debugfs_name = "gfx_err_inject", }; struct ras_ih_if ih_info = { .cb = amdgpu_gfx_process_ras_data_cb, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.c index 676c48c02d77..ead3dc572ec5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.c @@ -32,7 +32,6 @@ int amdgpu_mmhub_ras_late_init(struct amdgpu_device *adev) }; struct ras_fs_if fs_info = { .sysfs_name = "mmhub_err_count", - .debugfs_name = "mmhub_err_inject", }; if (!adev->mmhub.ras_if) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.c index 7d5c3a9de9ea..6201a5f4b4fa 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.c @@ -30,7 +30,6 @@ int amdgpu_nbio_ras_late_init(struct amdgpu_device *adev) }; struct ras_fs_if fs_info = { .sysfs_name = "pcie_bif_err_count", - .debugfs_name = "pcie_bif_err_inject", }; if (!adev->nbio.ras_if) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index 7f29e704936e..ce8548d5fbf3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -1174,7 +1174,6 @@ static void amdgpu_ras_debugfs_remove_all(struct amdgpu_device *adev) static int amdgpu_ras_fs_init(struct amdgpu_device *adev) { amdgpu_ras_sysfs_create_feature_node(adev); - amdgpu_ras_debugfs_create_ctrl_node(adev); return 0; } @@ -1878,8 +1877,6 @@ int amdgpu_ras_late_init(struct amdgpu_device *adev, goto interrupt; } - amdgpu_ras_debugfs_create(adev, fs_info); - r = amdgpu_ras_sysfs_create(adev, fs_info); if (r) goto sysfs; @@ -1888,7 +1885,6 @@ int amdgpu_ras_late_init(struct amdgpu_device *adev, cleanup: amdgpu_ras_sysfs_remove(adev, ras_block); sysfs: - amdgpu_ras_debugfs_remove(adev, ras_block); if (ih_info->cb) amdgpu_ras_interrupt_remove_handler(adev, ih_info); interrupt: @@ -1905,7 +1901,6 @@ void amdgpu_ras_late_fini(struct amdgpu_device *adev, return; amdgpu_ras_sysfs_remove(adev, ras_block); - amdgpu_ras_debugfs_remove(adev, ras_block); if (ih_info->cb) amdgpu_ras_interrupt_remove_handler(adev, ih_info); amdgpu_ras_feature_enable(adev, ras_block, 0); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c index 7854c053e85d..250a309e4dee 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c @@ -93,7 +93,6 @@ int amdgpu_sdma_ras_late_init(struct amdgpu_device *adev, struct ras_ih_if *ih_info = (struct ras_ih_if *)ras_ih_info; struct ras_fs_if fs_info = { .sysfs_name = "sdma_err_count", - .debugfs_name = "sdma_err_inject", }; if (!ih_info) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c index f4d40855147b..9dd51f0d2c11 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c @@ -28,7 +28,6 @@ int amdgpu_umc_ras_late_init(struct amdgpu_device *adev) int r; struct ras_fs_if fs_info = { .sysfs_name = "umc_err_count", - .debugfs_name = "umc_err_inject", }; struct ras_ih_if ih_info = { .cb = amdgpu_umc_process_ras_data_cb, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c index 59d171510ddc..95b3327168ac 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c @@ -598,7 +598,6 @@ int amdgpu_xgmi_ras_late_init(struct amdgpu_device *adev) }; struct ras_fs_if fs_info = { .sysfs_name = "xgmi_wafl_err_count", - .debugfs_name = "xgmi_wafl_err_inject", }; if (!adev->gmc.xgmi.supported || -- cgit v1.2.3