- Linux-stable-mirror - lists.linaro.org

[PATCH 6.1.y] drm/amd/display: fixed integer types and null check locations

by jianqi.ren.cn＠windriver.com

From: Sohaib Nadeem <sohaib.nadeem(a)amd.com> [ Upstream commit 0484e05d048b66d01d1f3c1d2306010bb57d8738 ] [why]: issues fixed: - comparison with wider integer type in loop condition which can cause infinite loops - pointer dereference before null check Cc: Mario Limonciello <mario.limonciello(a)amd.com> Cc: Alex Deucher <alexander.deucher(a)amd.com> Cc: stable(a)vger.kernel.org Reviewed-by: Josip Pavic <josip.pavic(a)amd.com> Acked-by: Aurabindo Pillai <aurabindo.pillai(a)amd.com> Signed-off-by: Sohaib Nadeem <sohaib.nadeem(a)amd.com> Tested-by: Daniel Wheeler <daniel.wheeler(a)amd.com> Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com> Signed-off-by: Jianqi Ren <jianqi.ren.cn(a)windriver.com> --- .../gpu/drm/amd/display/dc/bios/bios_parser2.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c index 4d2590964a20..75e44d8a7b40 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c +++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c @@ -1862,19 +1862,21 @@ static enum bp_result get_firmware_info_v3_2( /* Vega12 */ smu_info_v3_2 = GET_IMAGE(struct atom_smu_info_v3_2, DATA_TABLES(smu_info)); - DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", smu_info_v3_2->gpuclk_ss_percentage); if (!smu_info_v3_2) return BP_RESULT_BADBIOSTABLE; + DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", smu_info_v3_2->gpuclk_ss_percentage); + info->default_engine_clk = smu_info_v3_2->bootup_dcefclk_10khz * 10; } else if (revision.minor == 3) { /* Vega20 */ smu_info_v3_3 = GET_IMAGE(struct atom_smu_info_v3_3, DATA_TABLES(smu_info)); - DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", smu_info_v3_3->gpuclk_ss_percentage); if (!smu_info_v3_3) return BP_RESULT_BADBIOSTABLE; + DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", smu_info_v3_3->gpuclk_ss_percentage); + info->default_engine_clk = smu_info_v3_3->bootup_dcefclk_10khz * 10; } @@ -2439,10 +2441,11 @@ static enum bp_result get_integrated_info_v11( info_v11 = GET_IMAGE(struct atom_integrated_system_info_v1_11, DATA_TABLES(integratedsysteminfo)); - DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", info_v11->gpuclk_ss_percentage); if (info_v11 == NULL) return BP_RESULT_BADBIOSTABLE; + DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", info_v11->gpuclk_ss_percentage); + info->gpu_cap_info = le32_to_cpu(info_v11->gpucapinfo); /* @@ -2654,11 +2657,12 @@ static enum bp_result get_integrated_info_v2_1( info_v2_1 = GET_IMAGE(struct atom_integrated_system_info_v2_1, DATA_TABLES(integratedsysteminfo)); - DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", info_v2_1->gpuclk_ss_percentage); if (info_v2_1 == NULL) return BP_RESULT_BADBIOSTABLE; + DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", info_v2_1->gpuclk_ss_percentage); + info->gpu_cap_info = le32_to_cpu(info_v2_1->gpucapinfo); /* @@ -2816,11 +2820,11 @@ static enum bp_result get_integrated_info_v2_2( info_v2_2 = GET_IMAGE(struct atom_integrated_system_info_v2_2, DATA_TABLES(integratedsysteminfo)); - DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", info_v2_2->gpuclk_ss_percentage); - if (info_v2_2 == NULL) return BP_RESULT_BADBIOSTABLE; + DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", info_v2_2->gpuclk_ss_percentage); + info->gpu_cap_info = le32_to_cpu(info_v2_2->gpucapinfo); /* -- 2.25.1

11 months, 2 weeks

2
1
0 0

[PATCH 6.1 v2] gve: Fixes for napi_poll when budget is 0

by Ziwei Xiao

Netpoll will explicitly pass the polling call with a budget of 0 to indicate it's clearing the Tx path only. For the gve_rx_poll and gve_xdp_poll, they were mistakenly taking the 0 budget as the indication to do all the work. Add check to avoid the rx path and xdp path being called when budget is 0. And also avoid napi_complete_done being called when budget is 0 for netpoll. The original fix was merged here: https://lore.kernel.org/r/20231114004144.2022268-1-ziweixiao@google.com Resend it since the original one was not cleanly applied to 6.1 kernel. commit 278a370c1766 ("gve: Fixes for napi_poll when budget is 0") Fixes: f5cedc84a30d ("gve: Add transmit and receive support") Signed-off-by: Ziwei Xiao <ziweixiao(a)google.com> Reviewed-by: Praveen Kaligineedi <pkaligineedi(a)google.com> Signed-off-by: Praveen Kaligineedi <pkaligineedi(a)google.com> --- Changes in v2: * Add the original git commit id --- drivers/net/ethernet/google/gve/gve_main.c | 7 +++++++ drivers/net/ethernet/google/gve/gve_rx.c | 4 ---- drivers/net/ethernet/google/gve/gve_tx.c | 4 ---- 3 files changed, 7 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index d3f6ad586ba1..8771ccfc69b4 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -202,6 +202,10 @@ static int gve_napi_poll(struct napi_struct *napi, int budget) if (block->tx) reschedule |= gve_tx_poll(block, budget); + + if (!budget) + return 0; + if (block->rx) { work_done = gve_rx_poll(block, budget); reschedule |= work_done == budget; @@ -242,6 +246,9 @@ static int gve_napi_poll_dqo(struct napi_struct *napi, int budget) if (block->tx) reschedule |= gve_tx_poll_dqo(block, /*do_clean=*/true); + if (!budget) + return 0; + if (block->rx) { work_done = gve_rx_poll_dqo(block, budget); reschedule |= work_done == budget; diff --git a/drivers/net/ethernet/google/gve/gve_rx.c b/drivers/net/ethernet/google/gve/gve_rx.c index 021bbf308d68..639eb6848c7d 100644 --- a/drivers/net/ethernet/google/gve/gve_rx.c +++ b/drivers/net/ethernet/google/gve/gve_rx.c @@ -778,10 +778,6 @@ int gve_rx_poll(struct gve_notify_block *block, int budget) feat = block->napi.dev->features; - /* If budget is 0, do all the work */ - if (budget == 0) - budget = INT_MAX; - if (budget > 0) work_done = gve_clean_rx_done(rx, budget, feat); diff --git a/drivers/net/ethernet/google/gve/gve_tx.c b/drivers/net/ethernet/google/gve/gve_tx.c index 5e11b8236754..bf1ac0d1dc6f 100644 --- a/drivers/net/ethernet/google/gve/gve_tx.c +++ b/drivers/net/ethernet/google/gve/gve_tx.c @@ -725,10 +725,6 @@ bool gve_tx_poll(struct gve_notify_block *block, int budget) u32 nic_done; u32 to_do; - /* If budget is 0, do all the work */ - if (budget == 0) - budget = INT_MAX; - /* In TX path, it may try to clean completed pkts in order to xmit, * to avoid cleaning conflict, use spin_lock(), it yields better * concurrency between xmit/clean than netif's lock. -- 2.47.0.338.g60cca15819-goog

11 months, 2 weeks

2
1
0 0

[PATCH 5.15] crypto: hisilicon/qm - inject error before stopping queue

by libo.chen.cn＠eng.windriver.com

From: Weili Qian <qianweili(a)huawei.com> [ Upstream commit b04f06fc0243600665b3b50253869533b7938468 ] The master ooo cannot be completely closed when the accelerator core reports memory error. Therefore, the driver needs to inject the qm error to close the master ooo. Currently, the qm error is injected after stopping queue, memory may be released immediately after stopping queue, causing the device to access the released memory. Therefore, error is injected to close master ooo before stopping queue to ensure that the device does not access the released memory. Fixes: 6c6dd5802c2d ("crypto: hisilicon/qm - add controller reset interface") Signed-off-by: Weili Qian <qianweili(a)huawei.com> Signed-off-by: Herbert Xu <herbert(a)gondor.apana.org.au> Signed-off-by: Libo Chen <libo.chen.cn(a)windriver.com> --- drivers/crypto/hisilicon/qm.c | 51 +++++++++++++++++------------------ 1 file changed, 24 insertions(+), 27 deletions(-) diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c index fd89918abd19..58e995db3783 100644 --- a/drivers/crypto/hisilicon/qm.c +++ b/drivers/crypto/hisilicon/qm.c @@ -4638,6 +4638,28 @@ static int qm_set_vf_mse(struct hisi_qm *qm, bool set) return -ETIMEDOUT; } +static void qm_dev_ecc_mbit_handle(struct hisi_qm *qm) +{ + u32 nfe_enb = 0; + + /* Kunpeng930 hardware automatically close master ooo when NFE occurs */ + if (qm->ver >= QM_HW_V3) + return; + + if (!qm->err_status.is_dev_ecc_mbit && + qm->err_status.is_qm_ecc_mbit && + qm->err_ini->close_axi_master_ooo) { + qm->err_ini->close_axi_master_ooo(qm); + } else if (qm->err_status.is_dev_ecc_mbit && + !qm->err_status.is_qm_ecc_mbit && + !qm->err_ini->close_axi_master_ooo) { + nfe_enb = readl(qm->io_base + QM_RAS_NFE_ENABLE); + writel(nfe_enb & QM_RAS_NFE_MBIT_DISABLE, + qm->io_base + QM_RAS_NFE_ENABLE); + writel(QM_ECC_MBIT, qm->io_base + QM_ABNORMAL_INT_SET); + } +} + static int qm_vf_reset_prepare(struct hisi_qm *qm, enum qm_stop_reason stop_reason) { @@ -4742,6 +4764,8 @@ static int qm_controller_reset_prepare(struct hisi_qm *qm) return ret; } + qm_dev_ecc_mbit_handle(qm); + /* PF obtains the information of VF by querying the register. */ qm_cmd_uninit(qm); @@ -4766,31 +4790,6 @@ static int qm_controller_reset_prepare(struct hisi_qm *qm) return 0; } -static void qm_dev_ecc_mbit_handle(struct hisi_qm *qm) -{ - u32 nfe_enb = 0; - - /* Kunpeng930 hardware automatically close master ooo when NFE occurs */ - if (qm->ver >= QM_HW_V3) - return; - - if (!qm->err_status.is_dev_ecc_mbit && - qm->err_status.is_qm_ecc_mbit && - qm->err_ini->close_axi_master_ooo) { - - qm->err_ini->close_axi_master_ooo(qm); - - } else if (qm->err_status.is_dev_ecc_mbit && - !qm->err_status.is_qm_ecc_mbit && - !qm->err_ini->close_axi_master_ooo) { - - nfe_enb = readl(qm->io_base + QM_RAS_NFE_ENABLE); - writel(nfe_enb & QM_RAS_NFE_MBIT_DISABLE, - qm->io_base + QM_RAS_NFE_ENABLE); - writel(QM_ECC_MBIT, qm->io_base + QM_ABNORMAL_INT_SET); - } -} - static int qm_soft_reset(struct hisi_qm *qm) { struct pci_dev *pdev = qm->pdev; @@ -4816,8 +4815,6 @@ static int qm_soft_reset(struct hisi_qm *qm) return ret; } - qm_dev_ecc_mbit_handle(qm); - /* OOO register set and check */ writel(ACC_MASTER_GLOBAL_CTRL_SHUTDOWN, qm->io_base + ACC_MASTER_GLOBAL_CTRL); -- 2.25.1

11 months, 2 weeks

2
1
0 0

[PATCH 5.15.y] ima: Fix use-after-free on a dentry's dname.name

by libo.chen.cn＠eng.windriver.com

From: Stefan Berger <stefanb(a)linux.ibm.com> [ Upstream commit be84f32bb2c981ca670922e047cdde1488b233de ] ->d_name.name can change on rename and the earlier value can be freed; there are conditions sufficient to stabilize it (->d_lock on dentry, ->d_lock on its parent, ->i_rwsem exclusive on the parent's inode, rename_lock), but none of those are met at any of the sites. Take a stable snapshot of the name instead. Link: https://lore.kernel.org/all/20240202182732.GE2087318@ZenIV/ Signed-off-by: Al Viro <viro(a)zeniv.linux.org.uk> Signed-off-by: Stefan Berger <stefanb(a)linux.ibm.com> Signed-off-by: Mimi Zohar <zohar(a)linux.ibm.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Libo Chen <libo.chen.cn(a)windriver.com> --- security/integrity/ima/ima_api.c | 16 ++++++++++++---- security/integrity/ima/ima_template_lib.c | 17 ++++++++++++++--- 2 files changed, 26 insertions(+), 7 deletions(-) diff --git a/security/integrity/ima/ima_api.c b/security/integrity/ima/ima_api.c index 04b9e465463b..fa7abe4bde61 100644 --- a/security/integrity/ima/ima_api.c +++ b/security/integrity/ima/ima_api.c @@ -217,7 +217,7 @@ int ima_collect_measurement(struct integrity_iint_cache *iint, const char *audit_cause = "failed"; struct inode *inode = file_inode(file); struct inode *real_inode = d_real_inode(file_dentry(file)); - const char *filename = file->f_path.dentry->d_name.name; + struct name_snapshot filename; int result = 0; int length; void *tmpbuf; @@ -280,9 +280,13 @@ int ima_collect_measurement(struct integrity_iint_cache *iint, if (file->f_flags & O_DIRECT) audit_cause = "failed(directio)"; + take_dentry_name_snapshot(&filename, file->f_path.dentry); + integrity_audit_msg(AUDIT_INTEGRITY_DATA, inode, - filename, "collect_data", audit_cause, - result, 0); + filename.name.name, "collect_data", + audit_cause, result, 0); + + release_dentry_name_snapshot(&filename); } return result; } @@ -395,6 +399,7 @@ void ima_audit_measurement(struct integrity_iint_cache *iint, */ const char *ima_d_path(const struct path *path, char **pathbuf, char *namebuf) { + struct name_snapshot filename; char *pathname = NULL; *pathbuf = __getname(); @@ -408,7 +413,10 @@ const char *ima_d_path(const struct path *path, char **pathbuf, char *namebuf) } if (!pathname) { - strlcpy(namebuf, path->dentry->d_name.name, NAME_MAX); + take_dentry_name_snapshot(&filename, path->dentry); + strscpy(namebuf, filename.name.name, NAME_MAX); + release_dentry_name_snapshot(&filename); + pathname = namebuf; } diff --git a/security/integrity/ima/ima_template_lib.c b/security/integrity/ima/ima_template_lib.c index ca017cae73eb..dd7beaa0e787 100644 --- a/security/integrity/ima/ima_template_lib.c +++ b/security/integrity/ima/ima_template_lib.c @@ -426,7 +426,10 @@ static int ima_eventname_init_common(struct ima_event_data *event_data, bool size_limit) { const char *cur_filename = NULL; + struct name_snapshot filename; u32 cur_filename_len = 0; + bool snapshot = false; + int ret; BUG_ON(event_data->filename == NULL && event_data->file == NULL); @@ -439,7 +442,10 @@ static int ima_eventname_init_common(struct ima_event_data *event_data, } if (event_data->file) { - cur_filename = event_data->file->f_path.dentry->d_name.name; + take_dentry_name_snapshot(&filename, + event_data->file->f_path.dentry); + snapshot = true; + cur_filename = filename.name.name; cur_filename_len = strlen(cur_filename); } else /* @@ -448,8 +454,13 @@ static int ima_eventname_init_common(struct ima_event_data *event_data, */ cur_filename_len = IMA_EVENT_NAME_LEN_MAX; out: - return ima_write_template_field_data(cur_filename, cur_filename_len, - DATA_FMT_STRING, field_data); + ret = ima_write_template_field_data(cur_filename, cur_filename_len, + DATA_FMT_STRING, field_data); + + if (snapshot) + release_dentry_name_snapshot(&filename); + + return ret; } /* -- 2.25.1

11 months, 2 weeks

3
2
0 0

[PATCH 6.1.y] drm/amd/display: fix NULL checks for adev->dm.dc in amdgpu_dm_fini()

by jianqi.ren.cn＠windriver.com

From: Nikita Zhandarovich <n.zhandarovich(a)fintech.ru> [ Upstream commit 2a3cfb9a24a28da9cc13d2c525a76548865e182c ] Since 'adev->dm.dc' in amdgpu_dm_fini() might turn out to be NULL before the call to dc_enable_dmub_notifications(), check beforehand to ensure there will not be a possible NULL-ptr-deref there. Also, since commit 1e88eb1b2c25 ("drm/amd/display: Drop CONFIG_DRM_AMD_DC_HDCP") there are two separate checks for NULL in 'adev->dm.dc' before dc_deinit_callbacks() and dc_dmub_srv_destroy(). Clean up by combining them all under one 'if'. Found by Linux Verification Center (linuxtesting.org) with static analysis tool SVACE. Fixes: 81927e2808be ("drm/amd/display: Support for DMUB AUX") Signed-off-by: Nikita Zhandarovich <n.zhandarovich(a)fintech.ru> Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com> Signed-off-by: Jianqi Ren <jianqi.ren.cn(a)windriver.com> --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) 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 8dc0f70df24f..7b4d44dcb343 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -1882,14 +1882,14 @@ static void amdgpu_dm_fini(struct amdgpu_device *adev) dc_deinit_callbacks(adev->dm.dc); #endif - if (adev->dm.dc) + if (adev->dm.dc) { dc_dmub_srv_destroy(&adev->dm.dc->ctx->dmub_srv); - - if (dc_enable_dmub_notifications(adev->dm.dc)) { - kfree(adev->dm.dmub_notify); - adev->dm.dmub_notify = NULL; - destroy_workqueue(adev->dm.delayed_hpd_wq); - adev->dm.delayed_hpd_wq = NULL; + if (dc_enable_dmub_notifications(adev->dm.dc)) { + kfree(adev->dm.dmub_notify); + adev->dm.dmub_notify = NULL; + destroy_workqueue(adev->dm.delayed_hpd_wq); + adev->dm.delayed_hpd_wq = NULL; + } } if (adev->dm.dmub_bo) -- 2.25.1

11 months, 2 weeks

2
1
0 0

[PATCH 6.1.y] drm/amd/display: fix NULL checks for adev->dm.dc in amdgpu_dm_fini()

by jianqi.ren.cn＠windriver.com

From: Nikita Zhandarovich <n.zhandarovich(a)fintech.ru> [ Upstream commit 2a3cfb9a24a28da9cc13d2c525a76548865e182c ] Since 'adev->dm.dc' in amdgpu_dm_fini() might turn out to be NULL before the call to dc_enable_dmub_notifications(), check beforehand to ensure there will not be a possible NULL-ptr-deref there. Also, since commit 1e88eb1b2c25 ("drm/amd/display: Drop CONFIG_DRM_AMD_DC_HDCP") there are two separate checks for NULL in 'adev->dm.dc' before dc_deinit_callbacks() and dc_dmub_srv_destroy(). Clean up by combining them all under one 'if'. Found by Linux Verification Center (linuxtesting.org) with static analysis tool SVACE. Fixes: 81927e2808be ("drm/amd/display: Support for DMUB AUX") Signed-off-by: Nikita Zhandarovich <n.zhandarovich(a)fintech.ru> Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com> Signed-off-by: Jianqi Ren <jianqi.ren.cn(a)windriver.com> --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) 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 8dc0f70df24f..7b4d44dcb343 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -1882,14 +1882,14 @@ static void amdgpu_dm_fini(struct amdgpu_device *adev) dc_deinit_callbacks(adev->dm.dc); #endif - if (adev->dm.dc) + if (adev->dm.dc) { dc_dmub_srv_destroy(&adev->dm.dc->ctx->dmub_srv); - - if (dc_enable_dmub_notifications(adev->dm.dc)) { - kfree(adev->dm.dmub_notify); - adev->dm.dmub_notify = NULL; - destroy_workqueue(adev->dm.delayed_hpd_wq); - adev->dm.delayed_hpd_wq = NULL; + if (dc_enable_dmub_notifications(adev->dm.dc)) { + kfree(adev->dm.dmub_notify); + adev->dm.dmub_notify = NULL; + destroy_workqueue(adev->dm.delayed_hpd_wq); + adev->dm.delayed_hpd_wq = NULL; + } } if (adev->dm.dmub_bo) -- 2.25.1

11 months, 2 weeks

2
1
0 0

[PATCH 6.1.y] net/mlx5e: Don't call cleanup on profile rollback failure

by jianqi.ren.cn＠windriver.com

From: Cosmin Ratiu <cratiu(a)nvidia.com> [ Upstream commit 4dbc1d1a9f39c3711ad2a40addca04d07d9ab5d0 ] When profile rollback fails in mlx5e_netdev_change_profile, the netdev profile var is left set to NULL. Avoid a crash when unloading the driver by not calling profile->cleanup in such a case. This was encountered while testing, with the original trigger that the wq rescuer thread creation got interrupted (presumably due to Ctrl+C-ing modprobe), which gets converted to ENOMEM (-12) by mlx5e_priv_init, the profile rollback also fails for the same reason (signal still active) so the profile is left as NULL, leading to a crash later in _mlx5e_remove. [ 732.473932] mlx5_core 0000:08:00.1: E-Switch: Unload vfs: mode(OFFLOADS), nvfs(2), necvfs(0), active vports(2) [ 734.525513] workqueue: Failed to create a rescuer kthread for wq "mlx5e": -EINTR [ 734.557372] mlx5_core 0000:08:00.1: mlx5e_netdev_init_profile:6235:(pid 6086): mlx5e_priv_init failed, err=-12 [ 734.559187] mlx5_core 0000:08:00.1 eth3: mlx5e_netdev_change_profile: new profile init failed, -12 [ 734.560153] workqueue: Failed to create a rescuer kthread for wq "mlx5e": -EINTR [ 734.589378] mlx5_core 0000:08:00.1: mlx5e_netdev_init_profile:6235:(pid 6086): mlx5e_priv_init failed, err=-12 [ 734.591136] mlx5_core 0000:08:00.1 eth3: mlx5e_netdev_change_profile: failed to rollback to orig profile, -12 [ 745.537492] BUG: kernel NULL pointer dereference, address: 0000000000000008 [ 745.538222] #PF: supervisor read access in kernel mode <snipped> [ 745.551290] Call Trace: [ 745.551590] <TASK> [ 745.551866] ? __die+0x20/0x60 [ 745.552218] ? page_fault_oops+0x150/0x400 [ 745.555307] ? exc_page_fault+0x79/0x240 [ 745.555729] ? asm_exc_page_fault+0x22/0x30 [ 745.556166] ? mlx5e_remove+0x6b/0xb0 [mlx5_core] [ 745.556698] auxiliary_bus_remove+0x18/0x30 [ 745.557134] device_release_driver_internal+0x1df/0x240 [ 745.557654] bus_remove_device+0xd7/0x140 [ 745.558075] device_del+0x15b/0x3c0 [ 745.558456] mlx5_rescan_drivers_locked.part.0+0xb1/0x2f0 [mlx5_core] [ 745.559112] mlx5_unregister_device+0x34/0x50 [mlx5_core] [ 745.559686] mlx5_uninit_one+0x46/0xf0 [mlx5_core] [ 745.560203] remove_one+0x4e/0xd0 [mlx5_core] [ 745.560694] pci_device_remove+0x39/0xa0 [ 745.561112] device_release_driver_internal+0x1df/0x240 [ 745.561631] driver_detach+0x47/0x90 [ 745.562022] bus_remove_driver+0x84/0x100 [ 745.562444] pci_unregister_driver+0x3b/0x90 [ 745.562890] mlx5_cleanup+0xc/0x1b [mlx5_core] [ 745.563415] __x64_sys_delete_module+0x14d/0x2f0 [ 745.563886] ? kmem_cache_free+0x1b0/0x460 [ 745.564313] ? lockdep_hardirqs_on_prepare+0xe2/0x190 [ 745.564825] do_syscall_64+0x6d/0x140 [ 745.565223] entry_SYSCALL_64_after_hwframe+0x4b/0x53 [ 745.565725] RIP: 0033:0x7f1579b1288b Fixes: 3ef14e463f6e ("net/mlx5e: Separate between netdev objects and mlx5e profiles initialization") Signed-off-by: Cosmin Ratiu <cratiu(a)nvidia.com> Reviewed-by: Dragos Tatulea <dtatulea(a)nvidia.com> Signed-off-by: Tariq Toukan <tariqt(a)nvidia.com> Signed-off-by: Paolo Abeni <pabeni(a)redhat.com> Signed-off-by: Jianqi Ren <jianqi.ren.cn(a)windriver.com> --- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 385904502a6b..8ee6a81b42b4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -5980,7 +5980,9 @@ static void mlx5e_remove(struct auxiliary_device *adev) mlx5e_dcbnl_delete_app(priv); unregister_netdev(priv->netdev); mlx5e_suspend(adev, state); - priv->profile->cleanup(priv); + /* Avoid cleanup if profile rollback failed. */ + if (priv->profile) + priv->profile->cleanup(priv); mlx5e_devlink_port_unregister(priv); mlx5e_destroy_netdev(priv); } -- 2.25.1

11 months, 2 weeks

3
2
0 0

[PATCH 5.15] crypto: hisilicon/qm - inject error before stopping queue

by libo.chen.cn＠eng.windriver.com

From: Weili Qian <qianweili(a)huawei.com> [ Upstream commit b04f06fc0243600665b3b50253869533b7938468 ] The master ooo cannot be completely closed when the accelerator core reports memory error. Therefore, the driver needs to inject the qm error to close the master ooo. Currently, the qm error is injected after stopping queue, memory may be released immediately after stopping queue, causing the device to access the released memory. Therefore, error is injected to close master ooo before stopping queue to ensure that the device does not access the released memory. Fixes: 6c6dd5802c2d ("crypto: hisilicon/qm - add controller reset interface") Signed-off-by: Weili Qian <qianweili(a)huawei.com> Signed-off-by: Herbert Xu <herbert(a)gondor.apana.org.au> Signed-off-by: Libo Chen <libo.chen.cn(a)windriver.com> --- drivers/crypto/hisilicon/qm.c | 51 +++++++++++++++++------------------ 1 file changed, 24 insertions(+), 27 deletions(-) diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c index fd89918abd19..58e995db3783 100644 --- a/drivers/crypto/hisilicon/qm.c +++ b/drivers/crypto/hisilicon/qm.c @@ -4638,6 +4638,28 @@ static int qm_set_vf_mse(struct hisi_qm *qm, bool set) return -ETIMEDOUT; } +static void qm_dev_ecc_mbit_handle(struct hisi_qm *qm) +{ + u32 nfe_enb = 0; + + /* Kunpeng930 hardware automatically close master ooo when NFE occurs */ + if (qm->ver >= QM_HW_V3) + return; + + if (!qm->err_status.is_dev_ecc_mbit && + qm->err_status.is_qm_ecc_mbit && + qm->err_ini->close_axi_master_ooo) { + qm->err_ini->close_axi_master_ooo(qm); + } else if (qm->err_status.is_dev_ecc_mbit && + !qm->err_status.is_qm_ecc_mbit && + !qm->err_ini->close_axi_master_ooo) { + nfe_enb = readl(qm->io_base + QM_RAS_NFE_ENABLE); + writel(nfe_enb & QM_RAS_NFE_MBIT_DISABLE, + qm->io_base + QM_RAS_NFE_ENABLE); + writel(QM_ECC_MBIT, qm->io_base + QM_ABNORMAL_INT_SET); + } +} + static int qm_vf_reset_prepare(struct hisi_qm *qm, enum qm_stop_reason stop_reason) { @@ -4742,6 +4764,8 @@ static int qm_controller_reset_prepare(struct hisi_qm *qm) return ret; } + qm_dev_ecc_mbit_handle(qm); + /* PF obtains the information of VF by querying the register. */ qm_cmd_uninit(qm); @@ -4766,31 +4790,6 @@ static int qm_controller_reset_prepare(struct hisi_qm *qm) return 0; } -static void qm_dev_ecc_mbit_handle(struct hisi_qm *qm) -{ - u32 nfe_enb = 0; - - /* Kunpeng930 hardware automatically close master ooo when NFE occurs */ - if (qm->ver >= QM_HW_V3) - return; - - if (!qm->err_status.is_dev_ecc_mbit && - qm->err_status.is_qm_ecc_mbit && - qm->err_ini->close_axi_master_ooo) { - - qm->err_ini->close_axi_master_ooo(qm); - - } else if (qm->err_status.is_dev_ecc_mbit && - !qm->err_status.is_qm_ecc_mbit && - !qm->err_ini->close_axi_master_ooo) { - - nfe_enb = readl(qm->io_base + QM_RAS_NFE_ENABLE); - writel(nfe_enb & QM_RAS_NFE_MBIT_DISABLE, - qm->io_base + QM_RAS_NFE_ENABLE); - writel(QM_ECC_MBIT, qm->io_base + QM_ABNORMAL_INT_SET); - } -} - static int qm_soft_reset(struct hisi_qm *qm) { struct pci_dev *pdev = qm->pdev; @@ -4816,8 +4815,6 @@ static int qm_soft_reset(struct hisi_qm *qm) return ret; } - qm_dev_ecc_mbit_handle(qm); - /* OOO register set and check */ writel(ACC_MASTER_GLOBAL_CTRL_SHUTDOWN, qm->io_base + ACC_MASTER_GLOBAL_CTRL); -- 2.25.1

11 months, 2 weeks

4
3
0 0

[PATCH 6.1.y] ext4: fix access to uninitialised lock in fc replay path

by jianqi.ren.cn＠windriver.com

From: "Luis Henriques (SUSE)" <luis.henriques(a)linux.dev> [ commit 23dfdb56581ad92a9967bcd720c8c23356af74c1 upstream ] The following kernel trace can be triggered with fstest generic/629 when executed against a filesystem with fast-commit feature enabled: INFO: trying to register non-static key. The code is fine but needs lockdep annotation, or maybe you didn't initialize this object before use? turning off the locking correctness validator. CPU: 0 PID: 866 Comm: mount Not tainted 6.10.0+ #11 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.2-3-gd478f380-prebuilt.qemu.org 04/01/2014 Call Trace: <TASK> dump_stack_lvl+0x66/0x90 register_lock_class+0x759/0x7d0 __lock_acquire+0x85/0x2630 ? __find_get_block+0xb4/0x380 lock_acquire+0xd1/0x2d0 ? __ext4_journal_get_write_access+0xd5/0x160 _raw_spin_lock+0x33/0x40 ? __ext4_journal_get_write_access+0xd5/0x160 __ext4_journal_get_write_access+0xd5/0x160 ext4_reserve_inode_write+0x61/0xb0 __ext4_mark_inode_dirty+0x79/0x270 ? ext4_ext_replay_set_iblocks+0x2f8/0x450 ext4_ext_replay_set_iblocks+0x330/0x450 ext4_fc_replay+0x14c8/0x1540 ? jread+0x88/0x2e0 ? rcu_is_watching+0x11/0x40 do_one_pass+0x447/0xd00 jbd2_journal_recover+0x139/0x1b0 jbd2_journal_load+0x96/0x390 ext4_load_and_init_journal+0x253/0xd40 ext4_fill_super+0x2cc6/0x3180 ... In the replay path there's an attempt to lock sbi->s_bdev_wb_lock in function ext4_check_bdev_write_error(). Unfortunately, at this point this spinlock has not been initialized yet. Moving it's initialization to an earlier point in __ext4_fill_super() fixes this splat. Signed-off-by: Luis Henriques (SUSE) <luis.henriques(a)linux.dev> Link: https://patch.msgid.link/20240718094356.7863-1-luis.henriques@linux.dev Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> Cc: stable(a)kernel.org Signed-off-by: Jianqi Ren <jianqi.ren.cn(a)windriver.com> --- fs/ext4/super.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 987d49e18dbe..65e6e532cfb9 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -5276,6 +5276,8 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */ mutex_init(&sbi->s_orphan_lock); + spin_lock_init(&sbi->s_bdev_wb_lock); + ext4_fast_commit_init(sb); sb->s_root = NULL; @@ -5526,7 +5528,6 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) * Save the original bdev mapping's wb_err value which could be * used to detect the metadata async write error. */ - spin_lock_init(&sbi->s_bdev_wb_lock); errseq_check_and_advance(&sb->s_bdev->bd_inode->i_mapping->wb_err, &sbi->s_bdev_wb_err); sb->s_bdev->bd_super = sb; -- 2.25.1

11 months, 2 weeks

2
1
0 0

[PATCH 6.1.y] driver core: bus: Fix double free in driver API bus_register()

by jianqi.ren.cn＠windriver.com

From: Zijun Hu <quic_zijuhu(a)quicinc.com> [ Upstream commit bfa54a793ba77ef696755b66f3ac4ed00c7d1248 ] For bus_register(), any error which happens after kset_register() will cause that @priv are freed twice, fixed by setting @priv with NULL after the first free. Signed-off-by: Zijun Hu <quic_zijuhu(a)quicinc.com> Link: https://lore.kernel.org/r/20240727-bus_register_fix-v1-1-fed8dd0dba7a@quici… Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> [ Using bus->p instead of priv which will be consistent with the context ] Signed-off-by: Jianqi Ren <jianqi.ren.cn(a)windriver.com> --- drivers/base/bus.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/base/bus.c b/drivers/base/bus.c index 339a9edcde5f..028e45d2f7fe 100644 --- a/drivers/base/bus.c +++ b/drivers/base/bus.c @@ -853,6 +853,8 @@ int bus_register(struct bus_type *bus) bus_remove_file(bus, &bus_attr_uevent); bus_uevent_fail: kset_unregister(&bus->p->subsys); + /* Above kset_unregister() will kfree @priv */ + bus->p = NULL; out: kfree(bus->p); bus->p = NULL; -- 2.25.1

11 months, 2 weeks

2
1
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror