November 2023 - Linux-stable-mirror

FAILED: patch "[PATCH] drm/amd/display: fix the white screen issue when >= 64GB DRAM" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x a4246c63516600ce6feb4e2ee2124b8796f7a664 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112428-cramp-nicotine-d724@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: a4246c635166 ("drm/amd/display: fix the white screen issue when >= 64GB DRAM") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From a4246c63516600ce6feb4e2ee2124b8796f7a664 Mon Sep 17 00:00:00 2001 From: Yifan Zhang <yifan1.zhang(a)amd.com> Date: Fri, 8 Sep 2023 16:46:39 +0800 Subject: [PATCH] drm/amd/display: fix the white screen issue when >= 64GB DRAM Dropping bit 31:4 of page table base is wrong, it makes page table base points to wrong address if phys addr is beyond 64GB; dropping page_table_start/end bit 31:4 is unnecessary since dcn20_vmid_setup will do that. Also, while we are at it, cleanup the assignments using upper_32_bits()/lower_32_bits() and AMDGPU_GPU_PAGE_SHIFT. Cc: stable(a)vger.kernel.org Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2354 Fixes: 81d0bcf99009 ("drm/amdgpu: make display pinning more flexible (v2)") Acked-by: Harry Wentland <harry.wentland(a)amd.com> Reviewed-by: Alex Deucher <alexander.deucher(a)amd.com> Signed-off-by: Yifan Zhang <yifan1.zhang(a)amd.com> Co-developed-by: Hamza Mahfooz <hamza.mahfooz(a)amd.com> Signed-off-by: Hamza Mahfooz <hamza.mahfooz(a)amd.com> Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com> diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 2408ec33d35b..bde6b7037ba6 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -1283,11 +1283,15 @@ static void mmhub_read_system_context(struct amdgpu_device *adev, struct dc_phy_ pt_base = amdgpu_gmc_pd_addr(adev->gart.bo); - page_table_start.high_part = (u32)(adev->gmc.gart_start >> 44) & 0xF; - page_table_start.low_part = (u32)(adev->gmc.gart_start >> 12); - page_table_end.high_part = (u32)(adev->gmc.gart_end >> 44) & 0xF; - page_table_end.low_part = (u32)(adev->gmc.gart_end >> 12); - page_table_base.high_part = upper_32_bits(pt_base) & 0xF; + page_table_start.high_part = upper_32_bits(adev->gmc.gart_start >> + AMDGPU_GPU_PAGE_SHIFT); + page_table_start.low_part = lower_32_bits(adev->gmc.gart_start >> + AMDGPU_GPU_PAGE_SHIFT); + page_table_end.high_part = upper_32_bits(adev->gmc.gart_end >> + AMDGPU_GPU_PAGE_SHIFT); + page_table_end.low_part = lower_32_bits(adev->gmc.gart_end >> + AMDGPU_GPU_PAGE_SHIFT); + page_table_base.high_part = upper_32_bits(pt_base); page_table_base.low_part = lower_32_bits(pt_base); pa_config->system_aperture.start_addr = (uint64_t)logical_addr_low << 18;

1 year, 3 months

1
0
0 0

FAILED: patch "[PATCH] drm/amd/display: fix the white screen issue when >= 64GB DRAM" failed to apply to 6.5-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.5-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.5.y git checkout FETCH_HEAD git cherry-pick -x a4246c63516600ce6feb4e2ee2124b8796f7a664 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112427-happening-doorknob-4288@gregkh' --subject-prefix 'PATCH 6.5.y' HEAD^.. Possible dependencies: a4246c635166 ("drm/amd/display: fix the white screen issue when >= 64GB DRAM") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From a4246c63516600ce6feb4e2ee2124b8796f7a664 Mon Sep 17 00:00:00 2001 From: Yifan Zhang <yifan1.zhang(a)amd.com> Date: Fri, 8 Sep 2023 16:46:39 +0800 Subject: [PATCH] drm/amd/display: fix the white screen issue when >= 64GB DRAM Dropping bit 31:4 of page table base is wrong, it makes page table base points to wrong address if phys addr is beyond 64GB; dropping page_table_start/end bit 31:4 is unnecessary since dcn20_vmid_setup will do that. Also, while we are at it, cleanup the assignments using upper_32_bits()/lower_32_bits() and AMDGPU_GPU_PAGE_SHIFT. Cc: stable(a)vger.kernel.org Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2354 Fixes: 81d0bcf99009 ("drm/amdgpu: make display pinning more flexible (v2)") Acked-by: Harry Wentland <harry.wentland(a)amd.com> Reviewed-by: Alex Deucher <alexander.deucher(a)amd.com> Signed-off-by: Yifan Zhang <yifan1.zhang(a)amd.com> Co-developed-by: Hamza Mahfooz <hamza.mahfooz(a)amd.com> Signed-off-by: Hamza Mahfooz <hamza.mahfooz(a)amd.com> Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com> diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 2408ec33d35b..bde6b7037ba6 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -1283,11 +1283,15 @@ static void mmhub_read_system_context(struct amdgpu_device *adev, struct dc_phy_ pt_base = amdgpu_gmc_pd_addr(adev->gart.bo); - page_table_start.high_part = (u32)(adev->gmc.gart_start >> 44) & 0xF; - page_table_start.low_part = (u32)(adev->gmc.gart_start >> 12); - page_table_end.high_part = (u32)(adev->gmc.gart_end >> 44) & 0xF; - page_table_end.low_part = (u32)(adev->gmc.gart_end >> 12); - page_table_base.high_part = upper_32_bits(pt_base) & 0xF; + page_table_start.high_part = upper_32_bits(adev->gmc.gart_start >> + AMDGPU_GPU_PAGE_SHIFT); + page_table_start.low_part = lower_32_bits(adev->gmc.gart_start >> + AMDGPU_GPU_PAGE_SHIFT); + page_table_end.high_part = upper_32_bits(adev->gmc.gart_end >> + AMDGPU_GPU_PAGE_SHIFT); + page_table_end.low_part = lower_32_bits(adev->gmc.gart_end >> + AMDGPU_GPU_PAGE_SHIFT); + page_table_base.high_part = upper_32_bits(pt_base); page_table_base.low_part = lower_32_bits(pt_base); pa_config->system_aperture.start_addr = (uint64_t)logical_addr_low << 18;

1 year, 3 months

1
0
0 0

FAILED: patch "[PATCH] drm/amd/display: fix the white screen issue when >= 64GB DRAM" failed to apply to 6.6-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.6-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y git checkout FETCH_HEAD git cherry-pick -x a4246c63516600ce6feb4e2ee2124b8796f7a664 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112426-culture-junction-5d8a@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: a4246c635166 ("drm/amd/display: fix the white screen issue when >= 64GB DRAM") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From a4246c63516600ce6feb4e2ee2124b8796f7a664 Mon Sep 17 00:00:00 2001 From: Yifan Zhang <yifan1.zhang(a)amd.com> Date: Fri, 8 Sep 2023 16:46:39 +0800 Subject: [PATCH] drm/amd/display: fix the white screen issue when >= 64GB DRAM Dropping bit 31:4 of page table base is wrong, it makes page table base points to wrong address if phys addr is beyond 64GB; dropping page_table_start/end bit 31:4 is unnecessary since dcn20_vmid_setup will do that. Also, while we are at it, cleanup the assignments using upper_32_bits()/lower_32_bits() and AMDGPU_GPU_PAGE_SHIFT. Cc: stable(a)vger.kernel.org Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2354 Fixes: 81d0bcf99009 ("drm/amdgpu: make display pinning more flexible (v2)") Acked-by: Harry Wentland <harry.wentland(a)amd.com> Reviewed-by: Alex Deucher <alexander.deucher(a)amd.com> Signed-off-by: Yifan Zhang <yifan1.zhang(a)amd.com> Co-developed-by: Hamza Mahfooz <hamza.mahfooz(a)amd.com> Signed-off-by: Hamza Mahfooz <hamza.mahfooz(a)amd.com> Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com> diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 2408ec33d35b..bde6b7037ba6 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -1283,11 +1283,15 @@ static void mmhub_read_system_context(struct amdgpu_device *adev, struct dc_phy_ pt_base = amdgpu_gmc_pd_addr(adev->gart.bo); - page_table_start.high_part = (u32)(adev->gmc.gart_start >> 44) & 0xF; - page_table_start.low_part = (u32)(adev->gmc.gart_start >> 12); - page_table_end.high_part = (u32)(adev->gmc.gart_end >> 44) & 0xF; - page_table_end.low_part = (u32)(adev->gmc.gart_end >> 12); - page_table_base.high_part = upper_32_bits(pt_base) & 0xF; + page_table_start.high_part = upper_32_bits(adev->gmc.gart_start >> + AMDGPU_GPU_PAGE_SHIFT); + page_table_start.low_part = lower_32_bits(adev->gmc.gart_start >> + AMDGPU_GPU_PAGE_SHIFT); + page_table_end.high_part = upper_32_bits(adev->gmc.gart_end >> + AMDGPU_GPU_PAGE_SHIFT); + page_table_end.low_part = lower_32_bits(adev->gmc.gart_end >> + AMDGPU_GPU_PAGE_SHIFT); + page_table_base.high_part = upper_32_bits(pt_base); page_table_base.low_part = lower_32_bits(pt_base); pa_config->system_aperture.start_addr = (uint64_t)logical_addr_low << 18;

1 year, 3 months

1
0
0 0

FAILED: patch "[PATCH] drm/amd/display: Adjust the MST resume flow" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y git checkout FETCH_HEAD git cherry-pick -x 73c57a0aa7f672110d3f28c0ac03ec778a21d9d4 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112418-elevation-snooper-e9a2@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: 73c57a0aa7f6 ("drm/amd/display: Adjust the MST resume flow") 1e5d4d8eb8c0 ("drm/amd/display: Ext displays with dock can't recognized after resume") 028c4ccfb812 ("drm/amd/display: force connector state when bpc changes during compliance") d5a43956b73b ("drm/amd/display: move dp capability related logic to link_dp_capability") 94dfeaa46925 ("drm/amd/display: move dp phy related logic to link_dp_phy") 630168a97314 ("drm/amd/display: move dp link training logic to link_dp_training") d144b40a4833 ("drm/amd/display: move dc_link_dpia logic to link_dp_dpia") a28d0bac0956 ("drm/amd/display: move dpcd logic from dc_link_dpcd to link_dpcd") a98cdd8c4856 ("drm/amd/display: refactor ddc logic from dc_link_ddc to link_ddc") 4370f72e3845 ("drm/amd/display: refactor hpd logic from dc_link to link_hpd") 0e8cf83a2b47 ("drm/amd/display: allow hpo and dio encoder switching during dp retrain test") 7462475e3a06 ("drm/amd/display: move dccg programming from link hwss hpo dp to hwss") e85d59885409 ("drm/amd/display: use encoder type independent hwss instead of accessing enc directly") ebf13b72020a ("drm/amd/display: Revert Scaler HCBlank issue workaround") 639f6ad6df7f ("drm/amd/display: Revert Reduce delay when sink device not able to ACK 00340h write") e3aa827e2ab3 ("drm/amd/display: Avoid setting pixel rate divider to N/A") 180f33d27a55 ("drm/amd/display: Adjust DP 8b10b LT exit behavior") b7ada7ee61d3 ("drm/amd/display: Populate DP2.0 output type for DML pipe") ea192af507d9 ("drm/amd/display: Only update link settings after successful MST link train") be9f6b222c52 ("drm/amd/display: Fix fallback issues for DP LL 1.4a tests") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 73c57a0aa7f672110d3f28c0ac03ec778a21d9d4 Mon Sep 17 00:00:00 2001 From: Wayne Lin <wayne.lin(a)amd.com> Date: Tue, 22 Aug 2023 16:03:17 +0800 Subject: [PATCH] drm/amd/display: Adjust the MST resume flow [Why] In drm_dp_mst_topology_mgr_resume() today, it will resume the mst branch to be ready handling mst mode and also consecutively do the mst topology probing. Which will cause the dirver have chance to fire hotplug event before restoring the old state. Then Userspace will react to the hotplug event based on a wrong state. [How] Adjust the mst resume flow as: 1. set dpcd to resume mst branch status 2. restore source old state 3. Do mst resume topology probing For drm_dp_mst_topology_mgr_resume(), it's better to adjust it to pull out topology probing work into a 2nd part procedure of the mst resume. Will have a follow up patch in drm. Reviewed-by: Chao-kai Wang <stylon.wang(a)amd.com> Cc: Mario Limonciello <mario.limonciello(a)amd.com> Cc: Alex Deucher <alexander.deucher(a)amd.com> Cc: stable(a)vger.kernel.org Acked-by: Stylon Wang <stylon.wang(a)amd.com> Signed-off-by: Wayne Lin <wayne.lin(a)amd.com> Tested-by: Daniel Wheeler <daniel.wheeler(a)amd.com> Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com> diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 0e1ce71350d7..8e98dda1e084 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -2355,14 +2355,62 @@ static int dm_late_init(void *handle) return detect_mst_link_for_all_connectors(adev_to_drm(adev)); } +static void resume_mst_branch_status(struct drm_dp_mst_topology_mgr *mgr) +{ + int ret; + u8 guid[16]; + u64 tmp64; + + mutex_lock(&mgr->lock); + if (!mgr->mst_primary) + goto out_fail; + + if (drm_dp_read_dpcd_caps(mgr->aux, mgr->dpcd) < 0) { + drm_dbg_kms(mgr->dev, "dpcd read failed - undocked during suspend?\n"); + goto out_fail; + } + + ret = drm_dp_dpcd_writeb(mgr->aux, DP_MSTM_CTRL, + DP_MST_EN | + DP_UP_REQ_EN | + DP_UPSTREAM_IS_SRC); + if (ret < 0) { + drm_dbg_kms(mgr->dev, "mst write failed - undocked during suspend?\n"); + goto out_fail; + } + + /* Some hubs forget their guids after they resume */ + ret = drm_dp_dpcd_read(mgr->aux, DP_GUID, guid, 16); + if (ret != 16) { + drm_dbg_kms(mgr->dev, "dpcd read failed - undocked during suspend?\n"); + goto out_fail; + } + + if (memchr_inv(guid, 0, 16) == NULL) { + tmp64 = get_jiffies_64(); + memcpy(&guid[0], &tmp64, sizeof(u64)); + memcpy(&guid[8], &tmp64, sizeof(u64)); + + ret = drm_dp_dpcd_write(mgr->aux, DP_GUID, guid, 16); + + if (ret != 16) { + drm_dbg_kms(mgr->dev, "check mstb guid failed - undocked during suspend?\n"); + goto out_fail; + } + } + + memcpy(mgr->mst_primary->guid, guid, 16); + +out_fail: + mutex_unlock(&mgr->lock); +} + static void s3_handle_mst(struct drm_device *dev, bool suspend) { struct amdgpu_dm_connector *aconnector; struct drm_connector *connector; struct drm_connector_list_iter iter; struct drm_dp_mst_topology_mgr *mgr; - int ret; - bool need_hotplug = false; drm_connector_list_iter_begin(dev, &iter); drm_for_each_connector_iter(connector, &iter) { @@ -2384,18 +2432,15 @@ static void s3_handle_mst(struct drm_device *dev, bool suspend) if (!dp_is_lttpr_present(aconnector->dc_link)) try_to_configure_aux_timeout(aconnector->dc_link->ddc, LINK_AUX_DEFAULT_TIMEOUT_PERIOD); - ret = drm_dp_mst_topology_mgr_resume(mgr, true); - if (ret < 0) { - dm_helpers_dp_mst_stop_top_mgr(aconnector->dc_link->ctx, - aconnector->dc_link); - need_hotplug = true; - } + /* TODO: move resume_mst_branch_status() into drm mst resume again + * once topology probing work is pulled out from mst resume into mst + * resume 2nd step. mst resume 2nd step should be called after old + * state getting restored (i.e. drm_atomic_helper_resume()). + */ + resume_mst_branch_status(mgr); } } drm_connector_list_iter_end(&iter); - - if (need_hotplug) - drm_kms_helper_hotplug_event(dev); } static int amdgpu_dm_smu_write_watermarks_table(struct amdgpu_device *adev) @@ -2789,7 +2834,8 @@ static int dm_resume(void *handle) struct dm_atomic_state *dm_state = to_dm_atomic_state(dm->atomic_obj.state); enum dc_connection_type new_connection_type = dc_connection_none; struct dc_state *dc_state; - int i, r, j; + int i, r, j, ret; + bool need_hotplug = false; if (dm->dc->caps.ips_support) { dc_dmub_srv_exit_low_power_state(dm->dc); @@ -2891,7 +2937,7 @@ static int dm_resume(void *handle) continue; /* - * this is the case when traversing through already created + * this is the case when traversing through already created end sink * MST connectors, should be skipped */ if (aconnector && aconnector->mst_root) @@ -2951,6 +2997,27 @@ static int dm_resume(void *handle) dm->cached_state = NULL; + /* Do mst topology probing after resuming cached state*/ + drm_connector_list_iter_begin(ddev, &iter); + drm_for_each_connector_iter(connector, &iter) { + aconnector = to_amdgpu_dm_connector(connector); + if (aconnector->dc_link->type != dc_connection_mst_branch || + aconnector->mst_root) + continue; + + ret = drm_dp_mst_topology_mgr_resume(&aconnector->mst_mgr, true); + + if (ret < 0) { + dm_helpers_dp_mst_stop_top_mgr(aconnector->dc_link->ctx, + aconnector->dc_link); + need_hotplug = true; + } + } + drm_connector_list_iter_end(&iter); + + if (need_hotplug) + drm_kms_helper_hotplug_event(ddev); + amdgpu_dm_irq_resume_late(adev); amdgpu_dm_smu_write_watermarks_table(adev);

1 year, 3 months

1
0
0 0

FAILED: patch "[PATCH] drm/amd/display: Adjust the MST resume flow" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x 73c57a0aa7f672110d3f28c0ac03ec778a21d9d4 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112417-palace-parkway-a8a2@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: 73c57a0aa7f6 ("drm/amd/display: Adjust the MST resume flow") 1e5d4d8eb8c0 ("drm/amd/display: Ext displays with dock can't recognized after resume") 028c4ccfb812 ("drm/amd/display: force connector state when bpc changes during compliance") d5a43956b73b ("drm/amd/display: move dp capability related logic to link_dp_capability") 94dfeaa46925 ("drm/amd/display: move dp phy related logic to link_dp_phy") 630168a97314 ("drm/amd/display: move dp link training logic to link_dp_training") d144b40a4833 ("drm/amd/display: move dc_link_dpia logic to link_dp_dpia") a28d0bac0956 ("drm/amd/display: move dpcd logic from dc_link_dpcd to link_dpcd") a98cdd8c4856 ("drm/amd/display: refactor ddc logic from dc_link_ddc to link_ddc") 4370f72e3845 ("drm/amd/display: refactor hpd logic from dc_link to link_hpd") 0e8cf83a2b47 ("drm/amd/display: allow hpo and dio encoder switching during dp retrain test") 7462475e3a06 ("drm/amd/display: move dccg programming from link hwss hpo dp to hwss") e85d59885409 ("drm/amd/display: use encoder type independent hwss instead of accessing enc directly") ebf13b72020a ("drm/amd/display: Revert Scaler HCBlank issue workaround") 639f6ad6df7f ("drm/amd/display: Revert Reduce delay when sink device not able to ACK 00340h write") e3aa827e2ab3 ("drm/amd/display: Avoid setting pixel rate divider to N/A") 180f33d27a55 ("drm/amd/display: Adjust DP 8b10b LT exit behavior") b7ada7ee61d3 ("drm/amd/display: Populate DP2.0 output type for DML pipe") ea192af507d9 ("drm/amd/display: Only update link settings after successful MST link train") be9f6b222c52 ("drm/amd/display: Fix fallback issues for DP LL 1.4a tests") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 73c57a0aa7f672110d3f28c0ac03ec778a21d9d4 Mon Sep 17 00:00:00 2001 From: Wayne Lin <wayne.lin(a)amd.com> Date: Tue, 22 Aug 2023 16:03:17 +0800 Subject: [PATCH] drm/amd/display: Adjust the MST resume flow [Why] In drm_dp_mst_topology_mgr_resume() today, it will resume the mst branch to be ready handling mst mode and also consecutively do the mst topology probing. Which will cause the dirver have chance to fire hotplug event before restoring the old state. Then Userspace will react to the hotplug event based on a wrong state. [How] Adjust the mst resume flow as: 1. set dpcd to resume mst branch status 2. restore source old state 3. Do mst resume topology probing For drm_dp_mst_topology_mgr_resume(), it's better to adjust it to pull out topology probing work into a 2nd part procedure of the mst resume. Will have a follow up patch in drm. Reviewed-by: Chao-kai Wang <stylon.wang(a)amd.com> Cc: Mario Limonciello <mario.limonciello(a)amd.com> Cc: Alex Deucher <alexander.deucher(a)amd.com> Cc: stable(a)vger.kernel.org Acked-by: Stylon Wang <stylon.wang(a)amd.com> Signed-off-by: Wayne Lin <wayne.lin(a)amd.com> Tested-by: Daniel Wheeler <daniel.wheeler(a)amd.com> Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com> diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 0e1ce71350d7..8e98dda1e084 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -2355,14 +2355,62 @@ static int dm_late_init(void *handle) return detect_mst_link_for_all_connectors(adev_to_drm(adev)); } +static void resume_mst_branch_status(struct drm_dp_mst_topology_mgr *mgr) +{ + int ret; + u8 guid[16]; + u64 tmp64; + + mutex_lock(&mgr->lock); + if (!mgr->mst_primary) + goto out_fail; + + if (drm_dp_read_dpcd_caps(mgr->aux, mgr->dpcd) < 0) { + drm_dbg_kms(mgr->dev, "dpcd read failed - undocked during suspend?\n"); + goto out_fail; + } + + ret = drm_dp_dpcd_writeb(mgr->aux, DP_MSTM_CTRL, + DP_MST_EN | + DP_UP_REQ_EN | + DP_UPSTREAM_IS_SRC); + if (ret < 0) { + drm_dbg_kms(mgr->dev, "mst write failed - undocked during suspend?\n"); + goto out_fail; + } + + /* Some hubs forget their guids after they resume */ + ret = drm_dp_dpcd_read(mgr->aux, DP_GUID, guid, 16); + if (ret != 16) { + drm_dbg_kms(mgr->dev, "dpcd read failed - undocked during suspend?\n"); + goto out_fail; + } + + if (memchr_inv(guid, 0, 16) == NULL) { + tmp64 = get_jiffies_64(); + memcpy(&guid[0], &tmp64, sizeof(u64)); + memcpy(&guid[8], &tmp64, sizeof(u64)); + + ret = drm_dp_dpcd_write(mgr->aux, DP_GUID, guid, 16); + + if (ret != 16) { + drm_dbg_kms(mgr->dev, "check mstb guid failed - undocked during suspend?\n"); + goto out_fail; + } + } + + memcpy(mgr->mst_primary->guid, guid, 16); + +out_fail: + mutex_unlock(&mgr->lock); +} + static void s3_handle_mst(struct drm_device *dev, bool suspend) { struct amdgpu_dm_connector *aconnector; struct drm_connector *connector; struct drm_connector_list_iter iter; struct drm_dp_mst_topology_mgr *mgr; - int ret; - bool need_hotplug = false; drm_connector_list_iter_begin(dev, &iter); drm_for_each_connector_iter(connector, &iter) { @@ -2384,18 +2432,15 @@ static void s3_handle_mst(struct drm_device *dev, bool suspend) if (!dp_is_lttpr_present(aconnector->dc_link)) try_to_configure_aux_timeout(aconnector->dc_link->ddc, LINK_AUX_DEFAULT_TIMEOUT_PERIOD); - ret = drm_dp_mst_topology_mgr_resume(mgr, true); - if (ret < 0) { - dm_helpers_dp_mst_stop_top_mgr(aconnector->dc_link->ctx, - aconnector->dc_link); - need_hotplug = true; - } + /* TODO: move resume_mst_branch_status() into drm mst resume again + * once topology probing work is pulled out from mst resume into mst + * resume 2nd step. mst resume 2nd step should be called after old + * state getting restored (i.e. drm_atomic_helper_resume()). + */ + resume_mst_branch_status(mgr); } } drm_connector_list_iter_end(&iter); - - if (need_hotplug) - drm_kms_helper_hotplug_event(dev); } static int amdgpu_dm_smu_write_watermarks_table(struct amdgpu_device *adev) @@ -2789,7 +2834,8 @@ static int dm_resume(void *handle) struct dm_atomic_state *dm_state = to_dm_atomic_state(dm->atomic_obj.state); enum dc_connection_type new_connection_type = dc_connection_none; struct dc_state *dc_state; - int i, r, j; + int i, r, j, ret; + bool need_hotplug = false; if (dm->dc->caps.ips_support) { dc_dmub_srv_exit_low_power_state(dm->dc); @@ -2891,7 +2937,7 @@ static int dm_resume(void *handle) continue; /* - * this is the case when traversing through already created + * this is the case when traversing through already created end sink * MST connectors, should be skipped */ if (aconnector && aconnector->mst_root) @@ -2951,6 +2997,27 @@ static int dm_resume(void *handle) dm->cached_state = NULL; + /* Do mst topology probing after resuming cached state*/ + drm_connector_list_iter_begin(ddev, &iter); + drm_for_each_connector_iter(connector, &iter) { + aconnector = to_amdgpu_dm_connector(connector); + if (aconnector->dc_link->type != dc_connection_mst_branch || + aconnector->mst_root) + continue; + + ret = drm_dp_mst_topology_mgr_resume(&aconnector->mst_mgr, true); + + if (ret < 0) { + dm_helpers_dp_mst_stop_top_mgr(aconnector->dc_link->ctx, + aconnector->dc_link); + need_hotplug = true; + } + } + drm_connector_list_iter_end(&iter); + + if (need_hotplug) + drm_kms_helper_hotplug_event(ddev); + amdgpu_dm_irq_resume_late(adev); amdgpu_dm_smu_write_watermarks_table(adev);

1 year, 3 months

1
0
0 0

FAILED: patch "[PATCH] drm/amd/display: Adjust the MST resume flow" failed to apply to 6.5-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.5-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.5.y git checkout FETCH_HEAD git cherry-pick -x 73c57a0aa7f672110d3f28c0ac03ec778a21d9d4 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112416-gliding-depose-7862@gregkh' --subject-prefix 'PATCH 6.5.y' HEAD^.. Possible dependencies: 73c57a0aa7f6 ("drm/amd/display: Adjust the MST resume flow") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 73c57a0aa7f672110d3f28c0ac03ec778a21d9d4 Mon Sep 17 00:00:00 2001 From: Wayne Lin <wayne.lin(a)amd.com> Date: Tue, 22 Aug 2023 16:03:17 +0800 Subject: [PATCH] drm/amd/display: Adjust the MST resume flow [Why] In drm_dp_mst_topology_mgr_resume() today, it will resume the mst branch to be ready handling mst mode and also consecutively do the mst topology probing. Which will cause the dirver have chance to fire hotplug event before restoring the old state. Then Userspace will react to the hotplug event based on a wrong state. [How] Adjust the mst resume flow as: 1. set dpcd to resume mst branch status 2. restore source old state 3. Do mst resume topology probing For drm_dp_mst_topology_mgr_resume(), it's better to adjust it to pull out topology probing work into a 2nd part procedure of the mst resume. Will have a follow up patch in drm. Reviewed-by: Chao-kai Wang <stylon.wang(a)amd.com> Cc: Mario Limonciello <mario.limonciello(a)amd.com> Cc: Alex Deucher <alexander.deucher(a)amd.com> Cc: stable(a)vger.kernel.org Acked-by: Stylon Wang <stylon.wang(a)amd.com> Signed-off-by: Wayne Lin <wayne.lin(a)amd.com> Tested-by: Daniel Wheeler <daniel.wheeler(a)amd.com> Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com> diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 0e1ce71350d7..8e98dda1e084 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -2355,14 +2355,62 @@ static int dm_late_init(void *handle) return detect_mst_link_for_all_connectors(adev_to_drm(adev)); } +static void resume_mst_branch_status(struct drm_dp_mst_topology_mgr *mgr) +{ + int ret; + u8 guid[16]; + u64 tmp64; + + mutex_lock(&mgr->lock); + if (!mgr->mst_primary) + goto out_fail; + + if (drm_dp_read_dpcd_caps(mgr->aux, mgr->dpcd) < 0) { + drm_dbg_kms(mgr->dev, "dpcd read failed - undocked during suspend?\n"); + goto out_fail; + } + + ret = drm_dp_dpcd_writeb(mgr->aux, DP_MSTM_CTRL, + DP_MST_EN | + DP_UP_REQ_EN | + DP_UPSTREAM_IS_SRC); + if (ret < 0) { + drm_dbg_kms(mgr->dev, "mst write failed - undocked during suspend?\n"); + goto out_fail; + } + + /* Some hubs forget their guids after they resume */ + ret = drm_dp_dpcd_read(mgr->aux, DP_GUID, guid, 16); + if (ret != 16) { + drm_dbg_kms(mgr->dev, "dpcd read failed - undocked during suspend?\n"); + goto out_fail; + } + + if (memchr_inv(guid, 0, 16) == NULL) { + tmp64 = get_jiffies_64(); + memcpy(&guid[0], &tmp64, sizeof(u64)); + memcpy(&guid[8], &tmp64, sizeof(u64)); + + ret = drm_dp_dpcd_write(mgr->aux, DP_GUID, guid, 16); + + if (ret != 16) { + drm_dbg_kms(mgr->dev, "check mstb guid failed - undocked during suspend?\n"); + goto out_fail; + } + } + + memcpy(mgr->mst_primary->guid, guid, 16); + +out_fail: + mutex_unlock(&mgr->lock); +} + static void s3_handle_mst(struct drm_device *dev, bool suspend) { struct amdgpu_dm_connector *aconnector; struct drm_connector *connector; struct drm_connector_list_iter iter; struct drm_dp_mst_topology_mgr *mgr; - int ret; - bool need_hotplug = false; drm_connector_list_iter_begin(dev, &iter); drm_for_each_connector_iter(connector, &iter) { @@ -2384,18 +2432,15 @@ static void s3_handle_mst(struct drm_device *dev, bool suspend) if (!dp_is_lttpr_present(aconnector->dc_link)) try_to_configure_aux_timeout(aconnector->dc_link->ddc, LINK_AUX_DEFAULT_TIMEOUT_PERIOD); - ret = drm_dp_mst_topology_mgr_resume(mgr, true); - if (ret < 0) { - dm_helpers_dp_mst_stop_top_mgr(aconnector->dc_link->ctx, - aconnector->dc_link); - need_hotplug = true; - } + /* TODO: move resume_mst_branch_status() into drm mst resume again + * once topology probing work is pulled out from mst resume into mst + * resume 2nd step. mst resume 2nd step should be called after old + * state getting restored (i.e. drm_atomic_helper_resume()). + */ + resume_mst_branch_status(mgr); } } drm_connector_list_iter_end(&iter); - - if (need_hotplug) - drm_kms_helper_hotplug_event(dev); } static int amdgpu_dm_smu_write_watermarks_table(struct amdgpu_device *adev) @@ -2789,7 +2834,8 @@ static int dm_resume(void *handle) struct dm_atomic_state *dm_state = to_dm_atomic_state(dm->atomic_obj.state); enum dc_connection_type new_connection_type = dc_connection_none; struct dc_state *dc_state; - int i, r, j; + int i, r, j, ret; + bool need_hotplug = false; if (dm->dc->caps.ips_support) { dc_dmub_srv_exit_low_power_state(dm->dc); @@ -2891,7 +2937,7 @@ static int dm_resume(void *handle) continue; /* - * this is the case when traversing through already created + * this is the case when traversing through already created end sink * MST connectors, should be skipped */ if (aconnector && aconnector->mst_root) @@ -2951,6 +2997,27 @@ static int dm_resume(void *handle) dm->cached_state = NULL; + /* Do mst topology probing after resuming cached state*/ + drm_connector_list_iter_begin(ddev, &iter); + drm_for_each_connector_iter(connector, &iter) { + aconnector = to_amdgpu_dm_connector(connector); + if (aconnector->dc_link->type != dc_connection_mst_branch || + aconnector->mst_root) + continue; + + ret = drm_dp_mst_topology_mgr_resume(&aconnector->mst_mgr, true); + + if (ret < 0) { + dm_helpers_dp_mst_stop_top_mgr(aconnector->dc_link->ctx, + aconnector->dc_link); + need_hotplug = true; + } + } + drm_connector_list_iter_end(&iter); + + if (need_hotplug) + drm_kms_helper_hotplug_event(ddev); + amdgpu_dm_irq_resume_late(adev); amdgpu_dm_smu_write_watermarks_table(adev);

1 year, 3 months

1
0
0 0

FAILED: patch "[PATCH] drm/amd/display: Adjust the MST resume flow" failed to apply to 6.6-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.6-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y git checkout FETCH_HEAD git cherry-pick -x 73c57a0aa7f672110d3f28c0ac03ec778a21d9d4 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112415-commute-pacific-3c87@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: 73c57a0aa7f6 ("drm/amd/display: Adjust the MST resume flow") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 73c57a0aa7f672110d3f28c0ac03ec778a21d9d4 Mon Sep 17 00:00:00 2001 From: Wayne Lin <wayne.lin(a)amd.com> Date: Tue, 22 Aug 2023 16:03:17 +0800 Subject: [PATCH] drm/amd/display: Adjust the MST resume flow [Why] In drm_dp_mst_topology_mgr_resume() today, it will resume the mst branch to be ready handling mst mode and also consecutively do the mst topology probing. Which will cause the dirver have chance to fire hotplug event before restoring the old state. Then Userspace will react to the hotplug event based on a wrong state. [How] Adjust the mst resume flow as: 1. set dpcd to resume mst branch status 2. restore source old state 3. Do mst resume topology probing For drm_dp_mst_topology_mgr_resume(), it's better to adjust it to pull out topology probing work into a 2nd part procedure of the mst resume. Will have a follow up patch in drm. Reviewed-by: Chao-kai Wang <stylon.wang(a)amd.com> Cc: Mario Limonciello <mario.limonciello(a)amd.com> Cc: Alex Deucher <alexander.deucher(a)amd.com> Cc: stable(a)vger.kernel.org Acked-by: Stylon Wang <stylon.wang(a)amd.com> Signed-off-by: Wayne Lin <wayne.lin(a)amd.com> Tested-by: Daniel Wheeler <daniel.wheeler(a)amd.com> Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com> diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 0e1ce71350d7..8e98dda1e084 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -2355,14 +2355,62 @@ static int dm_late_init(void *handle) return detect_mst_link_for_all_connectors(adev_to_drm(adev)); } +static void resume_mst_branch_status(struct drm_dp_mst_topology_mgr *mgr) +{ + int ret; + u8 guid[16]; + u64 tmp64; + + mutex_lock(&mgr->lock); + if (!mgr->mst_primary) + goto out_fail; + + if (drm_dp_read_dpcd_caps(mgr->aux, mgr->dpcd) < 0) { + drm_dbg_kms(mgr->dev, "dpcd read failed - undocked during suspend?\n"); + goto out_fail; + } + + ret = drm_dp_dpcd_writeb(mgr->aux, DP_MSTM_CTRL, + DP_MST_EN | + DP_UP_REQ_EN | + DP_UPSTREAM_IS_SRC); + if (ret < 0) { + drm_dbg_kms(mgr->dev, "mst write failed - undocked during suspend?\n"); + goto out_fail; + } + + /* Some hubs forget their guids after they resume */ + ret = drm_dp_dpcd_read(mgr->aux, DP_GUID, guid, 16); + if (ret != 16) { + drm_dbg_kms(mgr->dev, "dpcd read failed - undocked during suspend?\n"); + goto out_fail; + } + + if (memchr_inv(guid, 0, 16) == NULL) { + tmp64 = get_jiffies_64(); + memcpy(&guid[0], &tmp64, sizeof(u64)); + memcpy(&guid[8], &tmp64, sizeof(u64)); + + ret = drm_dp_dpcd_write(mgr->aux, DP_GUID, guid, 16); + + if (ret != 16) { + drm_dbg_kms(mgr->dev, "check mstb guid failed - undocked during suspend?\n"); + goto out_fail; + } + } + + memcpy(mgr->mst_primary->guid, guid, 16); + +out_fail: + mutex_unlock(&mgr->lock); +} + static void s3_handle_mst(struct drm_device *dev, bool suspend) { struct amdgpu_dm_connector *aconnector; struct drm_connector *connector; struct drm_connector_list_iter iter; struct drm_dp_mst_topology_mgr *mgr; - int ret; - bool need_hotplug = false; drm_connector_list_iter_begin(dev, &iter); drm_for_each_connector_iter(connector, &iter) { @@ -2384,18 +2432,15 @@ static void s3_handle_mst(struct drm_device *dev, bool suspend) if (!dp_is_lttpr_present(aconnector->dc_link)) try_to_configure_aux_timeout(aconnector->dc_link->ddc, LINK_AUX_DEFAULT_TIMEOUT_PERIOD); - ret = drm_dp_mst_topology_mgr_resume(mgr, true); - if (ret < 0) { - dm_helpers_dp_mst_stop_top_mgr(aconnector->dc_link->ctx, - aconnector->dc_link); - need_hotplug = true; - } + /* TODO: move resume_mst_branch_status() into drm mst resume again + * once topology probing work is pulled out from mst resume into mst + * resume 2nd step. mst resume 2nd step should be called after old + * state getting restored (i.e. drm_atomic_helper_resume()). + */ + resume_mst_branch_status(mgr); } } drm_connector_list_iter_end(&iter); - - if (need_hotplug) - drm_kms_helper_hotplug_event(dev); } static int amdgpu_dm_smu_write_watermarks_table(struct amdgpu_device *adev) @@ -2789,7 +2834,8 @@ static int dm_resume(void *handle) struct dm_atomic_state *dm_state = to_dm_atomic_state(dm->atomic_obj.state); enum dc_connection_type new_connection_type = dc_connection_none; struct dc_state *dc_state; - int i, r, j; + int i, r, j, ret; + bool need_hotplug = false; if (dm->dc->caps.ips_support) { dc_dmub_srv_exit_low_power_state(dm->dc); @@ -2891,7 +2937,7 @@ static int dm_resume(void *handle) continue; /* - * this is the case when traversing through already created + * this is the case when traversing through already created end sink * MST connectors, should be skipped */ if (aconnector && aconnector->mst_root) @@ -2951,6 +2997,27 @@ static int dm_resume(void *handle) dm->cached_state = NULL; + /* Do mst topology probing after resuming cached state*/ + drm_connector_list_iter_begin(ddev, &iter); + drm_for_each_connector_iter(connector, &iter) { + aconnector = to_amdgpu_dm_connector(connector); + if (aconnector->dc_link->type != dc_connection_mst_branch || + aconnector->mst_root) + continue; + + ret = drm_dp_mst_topology_mgr_resume(&aconnector->mst_mgr, true); + + if (ret < 0) { + dm_helpers_dp_mst_stop_top_mgr(aconnector->dc_link->ctx, + aconnector->dc_link); + need_hotplug = true; + } + } + drm_connector_list_iter_end(&iter); + + if (need_hotplug) + drm_kms_helper_hotplug_event(ddev); + amdgpu_dm_irq_resume_late(adev); amdgpu_dm_smu_write_watermarks_table(adev);

1 year, 3 months

1
0
0 0

FAILED: patch "[PATCH] ext4: fix racy may inline data check in dio write" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y git checkout FETCH_HEAD git cherry-pick -x ce56d21355cd6f6937aca32f1f44ca749d1e4808 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112448-opposing-boxy-53a0@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: ce56d21355cd ("ext4: fix racy may inline data check in dio write") 310ee0902b8d ("ext4: allow concurrent unaligned dio overwrites") 240930fb7e6b ("ext4: dio take shared inode lock when overwriting preallocated blocks") 4bb26f2885ac ("ext4: avoid crash when inline data creation follows DIO write") 786f847f43a5 ("iomap: add per-iomap_iter private data") 36e8c62273aa ("btrfs: add a btrfs_dio_rw wrapper") 42e4c3bdcae7 ("gfs2: Variable rename") 3d198e42ce25 ("Merge tag 'gfs2-v5.17-rc4-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/gfs2/linux-gfs2") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From ce56d21355cd6f6937aca32f1f44ca749d1e4808 Mon Sep 17 00:00:00 2001 From: Brian Foster <bfoster(a)redhat.com> Date: Mon, 2 Oct 2023 14:50:20 -0400 Subject: [PATCH] ext4: fix racy may inline data check in dio write syzbot reports that the following warning from ext4_iomap_begin() triggers as of the commit referenced below: if (WARN_ON_ONCE(ext4_has_inline_data(inode))) return -ERANGE; This occurs during a dio write, which is never expected to encounter an inode with inline data. To enforce this behavior, ext4_dio_write_iter() checks the current inline state of the inode and clears the MAY_INLINE_DATA state flag to either fall back to buffered writes, or enforce that any other writers in progress on the inode are not allowed to create inline data. The problem is that the check for existing inline data and the state flag can span a lock cycle. For example, if the ilock is originally locked shared and subsequently upgraded to exclusive, another writer may have reacquired the lock and created inline data before the dio write task acquires the lock and proceeds. The commit referenced below loosens the lock requirements to allow some forms of unaligned dio writes to occur under shared lock, but AFAICT the inline data check was technically already racy for any dio write that would have involved a lock cycle. Regardless, lift clearing of the state bit to the same lock critical section that checks for preexisting inline data on the inode to close the race. Cc: stable(a)kernel.org Reported-by: syzbot+307da6ca5cb0d01d581a(a)syzkaller.appspotmail.com Fixes: 310ee0902b8d ("ext4: allow concurrent unaligned dio overwrites") Signed-off-by: Brian Foster <bfoster(a)redhat.com> Link: https://lore.kernel.org/r/20231002185020.531537-1-bfoster@redhat.com Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 6830ea3a6c59..747c0378122d 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -569,18 +569,20 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from) return ext4_buffered_write_iter(iocb, from); } + /* + * Prevent inline data from being created since we are going to allocate + * blocks for DIO. We know the inode does not currently have inline data + * because ext4_should_use_dio() checked for it, but we have to clear + * the state flag before the write checks because a lock cycle could + * introduce races with other writers. + */ + ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); + ret = ext4_dio_write_checks(iocb, from, &ilock_shared, &extend, &unwritten, &dio_flags); if (ret <= 0) return ret; - /* - * Make sure inline data cannot be created anymore since we are going - * to allocate blocks for DIO. We know the inode does not have any - * inline data now because ext4_dio_supported() checked for that. - */ - ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); - offset = iocb->ki_pos; count = ret;

1 year, 3 months

1
0
0 0

FAILED: patch "[PATCH] ext4: fix racy may inline data check in dio write" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x ce56d21355cd6f6937aca32f1f44ca749d1e4808 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112447-veto-frail-2fa8@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: ce56d21355cd ("ext4: fix racy may inline data check in dio write") 310ee0902b8d ("ext4: allow concurrent unaligned dio overwrites") 240930fb7e6b ("ext4: dio take shared inode lock when overwriting preallocated blocks") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From ce56d21355cd6f6937aca32f1f44ca749d1e4808 Mon Sep 17 00:00:00 2001 From: Brian Foster <bfoster(a)redhat.com> Date: Mon, 2 Oct 2023 14:50:20 -0400 Subject: [PATCH] ext4: fix racy may inline data check in dio write syzbot reports that the following warning from ext4_iomap_begin() triggers as of the commit referenced below: if (WARN_ON_ONCE(ext4_has_inline_data(inode))) return -ERANGE; This occurs during a dio write, which is never expected to encounter an inode with inline data. To enforce this behavior, ext4_dio_write_iter() checks the current inline state of the inode and clears the MAY_INLINE_DATA state flag to either fall back to buffered writes, or enforce that any other writers in progress on the inode are not allowed to create inline data. The problem is that the check for existing inline data and the state flag can span a lock cycle. For example, if the ilock is originally locked shared and subsequently upgraded to exclusive, another writer may have reacquired the lock and created inline data before the dio write task acquires the lock and proceeds. The commit referenced below loosens the lock requirements to allow some forms of unaligned dio writes to occur under shared lock, but AFAICT the inline data check was technically already racy for any dio write that would have involved a lock cycle. Regardless, lift clearing of the state bit to the same lock critical section that checks for preexisting inline data on the inode to close the race. Cc: stable(a)kernel.org Reported-by: syzbot+307da6ca5cb0d01d581a(a)syzkaller.appspotmail.com Fixes: 310ee0902b8d ("ext4: allow concurrent unaligned dio overwrites") Signed-off-by: Brian Foster <bfoster(a)redhat.com> Link: https://lore.kernel.org/r/20231002185020.531537-1-bfoster@redhat.com Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 6830ea3a6c59..747c0378122d 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -569,18 +569,20 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from) return ext4_buffered_write_iter(iocb, from); } + /* + * Prevent inline data from being created since we are going to allocate + * blocks for DIO. We know the inode does not currently have inline data + * because ext4_should_use_dio() checked for it, but we have to clear + * the state flag before the write checks because a lock cycle could + * introduce races with other writers. + */ + ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); + ret = ext4_dio_write_checks(iocb, from, &ilock_shared, &extend, &unwritten, &dio_flags); if (ret <= 0) return ret; - /* - * Make sure inline data cannot be created anymore since we are going - * to allocate blocks for DIO. We know the inode does not have any - * inline data now because ext4_dio_supported() checked for that. - */ - ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); - offset = iocb->ki_pos; count = ret;

1 year, 3 months

1
0
0 0

FAILED: patch "[PATCH] ext4: make sure allocate pending entry not fail" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x 8e387c89e96b9543a339f84043cf9df15fed2632 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112431-sniff-afford-8ceb@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: 8e387c89e96b ("ext4: make sure allocate pending entry not fail") 768d612f7982 ("ext4: fix slab-use-after-free in ext4_es_insert_extent()") 2a69c450083d ("ext4: using nofail preallocation in ext4_es_insert_extent()") 4a2d98447b37 ("ext4: using nofail preallocation in ext4_es_insert_delayed_block()") e9fe2b882bd5 ("ext4: using nofail preallocation in ext4_es_remove_extent()") bda3efaf774f ("ext4: use pre-allocated es in __es_remove_extent()") 95f0b320339a ("ext4: use pre-allocated es in __es_insert_extent()") 73a2f033656b ("ext4: factor out __es_alloc_extent() and __es_free_extent()") 9649eb18c628 ("ext4: add a new helper to check if es must be kept") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 8e387c89e96b9543a339f84043cf9df15fed2632 Mon Sep 17 00:00:00 2001 From: Zhang Yi <yi.zhang(a)huawei.com> Date: Thu, 24 Aug 2023 17:26:05 +0800 Subject: [PATCH] ext4: make sure allocate pending entry not fail __insert_pending() allocate memory in atomic context, so the allocation could fail, but we are not handling that failure now. It could lead ext4_es_remove_extent() to get wrong reserved clusters, and the global data blocks reservation count will be incorrect. The same to extents_status entry preallocation, preallocate pending entry out of the i_es_lock with __GFP_NOFAIL, make sure __insert_pending() and __revise_pending() always succeeds. Signed-off-by: Zhang Yi <yi.zhang(a)huawei.com> Cc: stable(a)kernel.org Link: https://lore.kernel.org/r/20230824092619.1327976-3-yi.zhang@huaweicloud.com Reviewed-by: Jan Kara <jack(a)suse.cz> Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c index 5e625ea4545d..f4b50652f0cc 100644 --- a/fs/ext4/extents_status.c +++ b/fs/ext4/extents_status.c @@ -152,8 +152,9 @@ static int __es_remove_extent(struct inode *inode, ext4_lblk_t lblk, static int es_reclaim_extents(struct ext4_inode_info *ei, int *nr_to_scan); static int __es_shrink(struct ext4_sb_info *sbi, int nr_to_scan, struct ext4_inode_info *locked_ei); -static void __revise_pending(struct inode *inode, ext4_lblk_t lblk, - ext4_lblk_t len); +static int __revise_pending(struct inode *inode, ext4_lblk_t lblk, + ext4_lblk_t len, + struct pending_reservation **prealloc); int __init ext4_init_es(void) { @@ -448,6 +449,19 @@ static void ext4_es_list_del(struct inode *inode) spin_unlock(&sbi->s_es_lock); } +static inline struct pending_reservation *__alloc_pending(bool nofail) +{ + if (!nofail) + return kmem_cache_alloc(ext4_pending_cachep, GFP_ATOMIC); + + return kmem_cache_zalloc(ext4_pending_cachep, GFP_KERNEL | __GFP_NOFAIL); +} + +static inline void __free_pending(struct pending_reservation *pr) +{ + kmem_cache_free(ext4_pending_cachep, pr); +} + /* * Returns true if we cannot fail to allocate memory for this extent_status * entry and cannot reclaim it until its status changes. @@ -836,11 +850,12 @@ void ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk, { struct extent_status newes; ext4_lblk_t end = lblk + len - 1; - int err1 = 0; - int err2 = 0; + int err1 = 0, err2 = 0, err3 = 0; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct extent_status *es1 = NULL; struct extent_status *es2 = NULL; + struct pending_reservation *pr = NULL; + bool revise_pending = false; if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) return; @@ -868,11 +883,17 @@ void ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk, ext4_es_insert_extent_check(inode, &newes); + revise_pending = sbi->s_cluster_ratio > 1 && + test_opt(inode->i_sb, DELALLOC) && + (status & (EXTENT_STATUS_WRITTEN | + EXTENT_STATUS_UNWRITTEN)); retry: if (err1 && !es1) es1 = __es_alloc_extent(true); if ((err1 || err2) && !es2) es2 = __es_alloc_extent(true); + if ((err1 || err2 || err3) && revise_pending && !pr) + pr = __alloc_pending(true); write_lock(&EXT4_I(inode)->i_es_lock); err1 = __es_remove_extent(inode, lblk, end, NULL, es1); @@ -897,13 +918,18 @@ void ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk, es2 = NULL; } - if (sbi->s_cluster_ratio > 1 && test_opt(inode->i_sb, DELALLOC) && - (status & EXTENT_STATUS_WRITTEN || - status & EXTENT_STATUS_UNWRITTEN)) - __revise_pending(inode, lblk, len); + if (revise_pending) { + err3 = __revise_pending(inode, lblk, len, &pr); + if (err3 != 0) + goto error; + if (pr) { + __free_pending(pr); + pr = NULL; + } + } error: write_unlock(&EXT4_I(inode)->i_es_lock); - if (err1 || err2) + if (err1 || err2 || err3) goto retry; ext4_es_print_tree(inode); @@ -1311,7 +1337,7 @@ static unsigned int get_rsvd(struct inode *inode, ext4_lblk_t end, rc->ndelonly--; node = rb_next(&pr->rb_node); rb_erase(&pr->rb_node, &tree->root); - kmem_cache_free(ext4_pending_cachep, pr); + __free_pending(pr); if (!node) break; pr = rb_entry(node, struct pending_reservation, @@ -1907,11 +1933,13 @@ static struct pending_reservation *__get_pending(struct inode *inode, * * @inode - file containing the cluster * @lblk - logical block in the cluster to be added + * @prealloc - preallocated pending entry * * Returns 0 on successful insertion and -ENOMEM on failure. If the * pending reservation is already in the set, returns successfully. */ -static int __insert_pending(struct inode *inode, ext4_lblk_t lblk) +static int __insert_pending(struct inode *inode, ext4_lblk_t lblk, + struct pending_reservation **prealloc) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct ext4_pending_tree *tree = &EXT4_I(inode)->i_pending_tree; @@ -1937,10 +1965,15 @@ static int __insert_pending(struct inode *inode, ext4_lblk_t lblk) } } - pr = kmem_cache_alloc(ext4_pending_cachep, GFP_ATOMIC); - if (pr == NULL) { - ret = -ENOMEM; - goto out; + if (likely(*prealloc == NULL)) { + pr = __alloc_pending(false); + if (!pr) { + ret = -ENOMEM; + goto out; + } + } else { + pr = *prealloc; + *prealloc = NULL; } pr->lclu = lclu; @@ -1970,7 +2003,7 @@ static void __remove_pending(struct inode *inode, ext4_lblk_t lblk) if (pr != NULL) { tree = &EXT4_I(inode)->i_pending_tree; rb_erase(&pr->rb_node, &tree->root); - kmem_cache_free(ext4_pending_cachep, pr); + __free_pending(pr); } } @@ -2029,10 +2062,10 @@ void ext4_es_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk, bool allocated) { struct extent_status newes; - int err1 = 0; - int err2 = 0; + int err1 = 0, err2 = 0, err3 = 0; struct extent_status *es1 = NULL; struct extent_status *es2 = NULL; + struct pending_reservation *pr = NULL; if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) return; @@ -2052,6 +2085,8 @@ void ext4_es_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk, es1 = __es_alloc_extent(true); if ((err1 || err2) && !es2) es2 = __es_alloc_extent(true); + if ((err1 || err2 || err3) && allocated && !pr) + pr = __alloc_pending(true); write_lock(&EXT4_I(inode)->i_es_lock); err1 = __es_remove_extent(inode, lblk, lblk, NULL, es1); @@ -2074,11 +2109,18 @@ void ext4_es_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk, es2 = NULL; } - if (allocated) - __insert_pending(inode, lblk); + if (allocated) { + err3 = __insert_pending(inode, lblk, &pr); + if (err3 != 0) + goto error; + if (pr) { + __free_pending(pr); + pr = NULL; + } + } error: write_unlock(&EXT4_I(inode)->i_es_lock); - if (err1 || err2) + if (err1 || err2 || err3) goto retry; ext4_es_print_tree(inode); @@ -2184,21 +2226,24 @@ unsigned int ext4_es_delayed_clu(struct inode *inode, ext4_lblk_t lblk, * @inode - file containing the range * @lblk - logical block defining the start of range * @len - length of range in blocks + * @prealloc - preallocated pending entry * * Used after a newly allocated extent is added to the extents status tree. * Requires that the extents in the range have either written or unwritten * status. Must be called while holding i_es_lock. */ -static void __revise_pending(struct inode *inode, ext4_lblk_t lblk, - ext4_lblk_t len) +static int __revise_pending(struct inode *inode, ext4_lblk_t lblk, + ext4_lblk_t len, + struct pending_reservation **prealloc) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); ext4_lblk_t end = lblk + len - 1; ext4_lblk_t first, last; bool f_del = false, l_del = false; + int ret = 0; if (len == 0) - return; + return 0; /* * Two cases - block range within single cluster and block range @@ -2219,7 +2264,9 @@ static void __revise_pending(struct inode *inode, ext4_lblk_t lblk, f_del = __es_scan_range(inode, &ext4_es_is_delonly, first, lblk - 1); if (f_del) { - __insert_pending(inode, first); + ret = __insert_pending(inode, first, prealloc); + if (ret < 0) + goto out; } else { last = EXT4_LBLK_CMASK(sbi, end) + sbi->s_cluster_ratio - 1; @@ -2227,9 +2274,11 @@ static void __revise_pending(struct inode *inode, ext4_lblk_t lblk, l_del = __es_scan_range(inode, &ext4_es_is_delonly, end + 1, last); - if (l_del) - __insert_pending(inode, last); - else + if (l_del) { + ret = __insert_pending(inode, last, prealloc); + if (ret < 0) + goto out; + } else __remove_pending(inode, last); } } else { @@ -2237,18 +2286,24 @@ static void __revise_pending(struct inode *inode, ext4_lblk_t lblk, if (first != lblk) f_del = __es_scan_range(inode, &ext4_es_is_delonly, first, lblk - 1); - if (f_del) - __insert_pending(inode, first); - else + if (f_del) { + ret = __insert_pending(inode, first, prealloc); + if (ret < 0) + goto out; + } else __remove_pending(inode, first); last = EXT4_LBLK_CMASK(sbi, end) + sbi->s_cluster_ratio - 1; if (last != end) l_del = __es_scan_range(inode, &ext4_es_is_delonly, end + 1, last); - if (l_del) - __insert_pending(inode, last); - else + if (l_del) { + ret = __insert_pending(inode, last, prealloc); + if (ret < 0) + goto out; + } else __remove_pending(inode, last); } +out: + return ret; }

1 year, 3 months

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror November 2023