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

[PATCH] drm/amdgpu/discovery: fix fw based ip discovery

by Alex Deucher

We only need the fw based discovery table for sysfs. No need to parse it. Additionally parsing some of the board specific tables may result in incorrect data on some boards. just load the binary and don't parse it on those boards. Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/4441 Fixes: 80a0e8282933 ("drm/amdgpu/discovery: optionally use fw based ip discovery") Cc: stable(a)vger.kernel.org Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com> --- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 5 +- drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c | 72 ++++++++++--------- 2 files changed, 41 insertions(+), 36 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index efe98ffb679a4..b2538cff222ce 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -2570,9 +2570,6 @@ static int amdgpu_device_parse_gpu_info_fw(struct amdgpu_device *adev) adev->firmware.gpu_info_fw = NULL; - if (adev->mman.discovery_bin) - return 0; - switch (adev->asic_type) { default: return 0; @@ -2594,6 +2591,8 @@ static int amdgpu_device_parse_gpu_info_fw(struct amdgpu_device *adev) chip_name = "arcturus"; break; case CHIP_NAVI12: + if (adev->mman.discovery_bin) + return 0; chip_name = "navi12"; break; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c index 81b3443c8d7f4..27bd7659961e8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c @@ -2555,40 +2555,11 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev) switch (adev->asic_type) { case CHIP_VEGA10: - case CHIP_VEGA12: - case CHIP_RAVEN: - case CHIP_VEGA20: - case CHIP_ARCTURUS: - case CHIP_ALDEBARAN: - /* this is not fatal. We have a fallback below - * if the new firmwares are not present. some of - * this will be overridden below to keep things - * consistent with the current behavior. + /* This is not fatal. We only need the discovery + * binary for sysfs. We don't need it for a + * functional system. */ - r = amdgpu_discovery_reg_base_init(adev); - if (!r) { - amdgpu_discovery_harvest_ip(adev); - amdgpu_discovery_get_gfx_info(adev); - amdgpu_discovery_get_mall_info(adev); - amdgpu_discovery_get_vcn_info(adev); - } - break; - default: - r = amdgpu_discovery_reg_base_init(adev); - if (r) { - drm_err(&adev->ddev, "discovery failed: %d\n", r); - return r; - } - - amdgpu_discovery_harvest_ip(adev); - amdgpu_discovery_get_gfx_info(adev); - amdgpu_discovery_get_mall_info(adev); - amdgpu_discovery_get_vcn_info(adev); - break; - } - - switch (adev->asic_type) { - case CHIP_VEGA10: + amdgpu_discovery_init(adev); vega10_reg_base_init(adev); adev->sdma.num_instances = 2; adev->gmc.num_umc = 4; @@ -2611,6 +2582,11 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev) adev->ip_versions[DCI_HWIP][0] = IP_VERSION(12, 0, 0); break; case CHIP_VEGA12: + /* This is not fatal. We only need the discovery + * binary for sysfs. We don't need it for a + * functional system. + */ + amdgpu_discovery_init(adev); vega10_reg_base_init(adev); adev->sdma.num_instances = 2; adev->gmc.num_umc = 4; @@ -2633,6 +2609,11 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev) adev->ip_versions[DCI_HWIP][0] = IP_VERSION(12, 0, 1); break; case CHIP_RAVEN: + /* This is not fatal. We only need the discovery + * binary for sysfs. We don't need it for a + * functional system. + */ + amdgpu_discovery_init(adev); vega10_reg_base_init(adev); adev->sdma.num_instances = 1; adev->vcn.num_vcn_inst = 1; @@ -2674,6 +2655,11 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev) } break; case CHIP_VEGA20: + /* This is not fatal. We only need the discovery + * binary for sysfs. We don't need it for a + * functional system. + */ + amdgpu_discovery_init(adev); vega20_reg_base_init(adev); adev->sdma.num_instances = 2; adev->gmc.num_umc = 8; @@ -2697,6 +2683,11 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev) adev->ip_versions[DCI_HWIP][0] = IP_VERSION(12, 1, 0); break; case CHIP_ARCTURUS: + /* This is not fatal. We only need the discovery + * binary for sysfs. We don't need it for a + * functional system. + */ + amdgpu_discovery_init(adev); arct_reg_base_init(adev); adev->sdma.num_instances = 8; adev->vcn.num_vcn_inst = 2; @@ -2725,6 +2716,11 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev) adev->ip_versions[UVD_HWIP][1] = IP_VERSION(2, 5, 0); break; case CHIP_ALDEBARAN: + /* This is not fatal. We only need the discovery + * binary for sysfs. We don't need it for a + * functional system. + */ + amdgpu_discovery_init(adev); aldebaran_reg_base_init(adev); adev->sdma.num_instances = 5; adev->vcn.num_vcn_inst = 2; @@ -2751,6 +2747,16 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev) adev->ip_versions[XGMI_HWIP][0] = IP_VERSION(6, 1, 0); break; default: + r = amdgpu_discovery_reg_base_init(adev); + if (r) { + drm_err(&adev->ddev, "discovery failed: %d\n", r); + return r; + } + + amdgpu_discovery_harvest_ip(adev); + amdgpu_discovery_get_gfx_info(adev); + amdgpu_discovery_get_mall_info(adev); + amdgpu_discovery_get_vcn_info(adev); break; } -- 2.50.1

3 weeks, 1 day

4
4
0 0

[PATCH 1/3] phy: tegra: xusb: fix device and OF node leak at probe

by Johan Hovold

Make sure to drop the references taken to the PMC OF node and device by of_parse_phandle() and of_find_device_by_node() during probe. Note the holding a reference to the PMC device does not prevent the PMC regmap from going away (e.g. if the PMC driver is unbound) so there is no need to keep the reference. Fixes: 2d1021487273 ("phy: tegra: xusb: Add wake/sleepwalk for Tegra210") Cc: stable(a)vger.kernel.org # 5.14 Cc: JC Kuo <jckuo(a)nvidia.com> Signed-off-by: Johan Hovold <johan(a)kernel.org> --- drivers/phy/tegra/xusb-tegra210.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/phy/tegra/xusb-tegra210.c b/drivers/phy/tegra/xusb-tegra210.c index ebc8a7e21a31..3409924498e9 100644 --- a/drivers/phy/tegra/xusb-tegra210.c +++ b/drivers/phy/tegra/xusb-tegra210.c @@ -3164,18 +3164,22 @@ tegra210_xusb_padctl_probe(struct device *dev, } pdev = of_find_device_by_node(np); + of_node_put(np); if (!pdev) { dev_warn(dev, "PMC device is not available\n"); goto out; } - if (!platform_get_drvdata(pdev)) + if (!platform_get_drvdata(pdev)) { + put_device(&pdev->dev); return ERR_PTR(-EPROBE_DEFER); + } padctl->regmap = dev_get_regmap(&pdev->dev, "usb_sleepwalk"); if (!padctl->regmap) dev_info(dev, "failed to find PMC regmap\n"); + put_device(&pdev->dev); out: return &padctl->base; } -- 2.49.1

3 weeks, 1 day

2
1
0 0

[PATCH] drm/probe-helper: fix output polling not resuming after HPD IRQ storm

by Nicusor Huhulea

A regression in output polling was introduced by commit 4ad8d57d902fbc7c82507cfc1b031f3a07c3de6e ("drm: Check output polling initialized before disabling") in the 6.1.y stable tree. As a result, when the i915 driver detects an HPD IRQ storm and attempts to switch from IRQ-based hotplug detection to polling, output polling fails to resume. The root cause is the use of dev->mode_config.poll_running. Once poll_running is set (during the first connector detection) the calls to drm_kms_helper_poll_enable(), such as intel_hpd_irq_storm_switch_to_polling() fails to schedule output_poll_work as expected. Therefore, after an IRQ storm disables HPD IRQs, polling does not start, breaking hotplug detection. The fix is to remove the dev->mode_config.poll_running in the check condition, ensuring polling is always scheduled as requested. Notes: Initial analysis, assumptions, device testing details, the correct fix and detailed rationale were discussed here https://lore.kernel.org/stable/aI32HUzrT95nS_H9@ideak-desk/ Cc: stable(a)vger.kernel.org # 6.1.y Cc: Imre Deak <imre.deak(a)intel.com> Cc: Shradha Gupta <shradhagupta(a)linux.microsoft.com> Suggested-by: Imre Deak <imre.deak(a)intel.com> Signed-off-by: Nicusor Huhulea <nicusor.huhulea(a)siemens.com> --- drivers/gpu/drm/drm_probe_helper.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/drm_probe_helper.c b/drivers/gpu/drm/drm_probe_helper.c index 0e5eadc6d44d..a515b78f839e 100644 --- a/drivers/gpu/drm/drm_probe_helper.c +++ b/drivers/gpu/drm/drm_probe_helper.c @@ -250,7 +250,7 @@ void drm_kms_helper_poll_enable(struct drm_device *dev) unsigned long delay = DRM_OUTPUT_POLL_PERIOD; if (drm_WARN_ON_ONCE(dev, !dev->mode_config.poll_enabled) || - !drm_kms_helper_poll || dev->mode_config.poll_running) + !drm_kms_helper_poll) return; drm_connector_list_iter_begin(dev, &conn_iter); -- 2.39.2

3 weeks, 1 day

4
6
0 0

[PATCH] cdx: Fix off-by-one error in cdx_rpmsg_probe()

by Thorsten Blum

In cdx_rpmsg_probe(), strscpy() is incorrectly called with the length of the source string (excluding the NUL terminator) rather than the size of the destination buffer. This results in one character less being copied from 'cdx_rpmsg_id_table[0].name' to 'chinfo.name'. Use the destination buffer size instead to ensure the name is copied correctly. Cc: stable(a)vger.kernel.org Fixes: 2a226927d9b8 ("cdx: add rpmsg communication channel for CDX") Signed-off-by: Thorsten Blum <thorsten.blum(a)linux.dev> --- drivers/cdx/controller/cdx_rpmsg.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/cdx/controller/cdx_rpmsg.c b/drivers/cdx/controller/cdx_rpmsg.c index 04b578a0be17..61f1a290ff08 100644 --- a/drivers/cdx/controller/cdx_rpmsg.c +++ b/drivers/cdx/controller/cdx_rpmsg.c @@ -129,8 +129,7 @@ static int cdx_rpmsg_probe(struct rpmsg_device *rpdev) chinfo.src = RPMSG_ADDR_ANY; chinfo.dst = rpdev->dst; - strscpy(chinfo.name, cdx_rpmsg_id_table[0].name, - strlen(cdx_rpmsg_id_table[0].name)); + strscpy(chinfo.name, cdx_rpmsg_id_table[0].name, sizeof(chinfo.name)); cdx_mcdi->ept = rpmsg_create_ept(rpdev, cdx_rpmsg_cb, NULL, chinfo); if (!cdx_mcdi->ept) { -- 2.50.1

3 weeks, 1 day

1
0
0 0

[PATCH] blk-wbt: Fix io starvation in wbt_rqw_done()

by Julian Sun

Recently, we encountered the following hungtask: INFO: task kworker/11:2:2981147 blocked for more than 6266 seconds "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. kworker/11:2 D 0 2981147 2 0x80004000 Workqueue: cgroup_destroy css_free_rwork_fn Call Trace: __schedule+0x934/0xe10 schedule+0x40/0xb0 wb_wait_for_completion+0x52/0x80 ? finish_wait+0x80/0x80 mem_cgroup_css_free+0x3a/0x1b0 css_free_rwork_fn+0x42/0x380 process_one_work+0x1a2/0x360 worker_thread+0x30/0x390 ? create_worker+0x1a0/0x1a0 kthread+0x110/0x130 ? __kthread_cancel_work+0x40/0x40 ret_from_fork+0x1f/0x30 This is because the writeback thread has been continuously and repeatedly throttled by wbt, but at the same time, the writes of another thread proceed quite smoothly. After debugging, I believe it is caused by the following reasons. When thread A is blocked by wbt, the I/O issued by thread B will use a deeper queue depth(rwb->rq_depth.max_depth) because it meets the conditions of wb_recent_wait(), thus allowing thread B's I/O to be issued smoothly and resulting in the inflight I/O of wbt remaining relatively high. However, when I/O completes, due to the high inflight I/O of wbt, the condition "limit - inflight >= rwb->wb_background / 2" in wbt_rqw_done() cannot be satisfied, causing thread A's I/O to remain unable to be woken up. Some on-site information: >>> rwb.rq_depth.max_depth (unsigned int)48 >>> rqw.inflight.counter.value_() 44 >>> rqw.inflight.counter.value_() 35 >>> prog['jiffies'] - rwb.rqos.q.backing_dev_info.last_bdp_sleep (unsigned long)3 >>> prog['jiffies'] - rwb.rqos.q.backing_dev_info.last_bdp_sleep (unsigned long)2 >>> prog['jiffies'] - rwb.rqos.q.backing_dev_info.last_bdp_sleep (unsigned long)20 >>> prog['jiffies'] - rwb.rqos.q.backing_dev_info.last_bdp_sleep (unsigned long)12 cat wb_normal 24 cat wb_background 12 To fix this issue, we can use max_depth in wbt_rqw_done(), so that the handling of wb_recent_wait by wbt_rqw_done() and get_limit() will also be consistent, which is more reasonable. Signed-off-by: Julian Sun <sunjunchao(a)bytedance.com> Fixes: e34cbd307477 ("blk-wbt: add general throttling mechanism") --- block/blk-wbt.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/block/blk-wbt.c b/block/blk-wbt.c index a50d4cd55f41..d6a2782d442f 100644 --- a/block/blk-wbt.c +++ b/block/blk-wbt.c @@ -210,6 +210,8 @@ static void wbt_rqw_done(struct rq_wb *rwb, struct rq_wait *rqw, else if (blk_queue_write_cache(rwb->rqos.disk->queue) && !wb_recent_wait(rwb)) limit = 0; + else if (wb_recent_wait(rwb)) + limit = rwb->rq_depth.max_depth; else limit = rwb->wb_normal; -- 2.20.1

3 weeks, 1 day

4
4
0 0

[PATCH] drm/mediatek: Fix device/node reference count leaks in mtk_drm_get_all_drm_priv

by Ma Ke

Using device_find_child() and of_find_device_by_node() to locate devices could cause an imbalance in the device's reference count. device_find_child() and of_find_device_by_node() both call get_device() to increment the reference count of the found device before returning the pointer. In mtk_drm_get_all_drm_priv(), these references are never released through put_device(), resulting in permanent reference count increments. Additionally, the for_each_child_of_node() iterator fails to release node references in all code paths. This leaks device node references when loop termination occurs before reaching MAX_CRTC. These reference count leaks may prevent device/node resources from being properly released during driver unbind operations. As comment of device_find_child() says, 'NOTE: you will need to drop the reference with put_device() after use'. Found by code review. Cc: stable(a)vger.kernel.org Fixes: 1ef7ed48356c ("drm/mediatek: Modify mediatek-drm for mt8195 multi mmsys support") Signed-off-by: Ma Ke <make24(a)iscas.ac.cn> --- drivers/gpu/drm/mediatek/mtk_drm_drv.c | 27 +++++++++++++++++--------- 1 file changed, 18 insertions(+), 9 deletions(-) diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c index 7c0c12dde488..c78186debd3e 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c @@ -388,19 +388,24 @@ static bool mtk_drm_get_all_drm_priv(struct device *dev) of_id = of_match_node(mtk_drm_of_ids, node); if (!of_id) - continue; + goto next; pdev = of_find_device_by_node(node); if (!pdev) - continue; + goto next; drm_dev = device_find_child(&pdev->dev, NULL, mtk_drm_match); - if (!drm_dev) - continue; + if (!drm_dev) { + put_device(&pdev->dev); + goto next; + } temp_drm_priv = dev_get_drvdata(drm_dev); - if (!temp_drm_priv) - continue; + if (!temp_drm_priv) { + put_device(drm_dev); + put_device(&pdev->dev); + goto next; + } if (temp_drm_priv->data->main_len) all_drm_priv[CRTC_MAIN] = temp_drm_priv; @@ -412,10 +417,14 @@ static bool mtk_drm_get_all_drm_priv(struct device *dev) if (temp_drm_priv->mtk_drm_bound) cnt++; - if (cnt == MAX_CRTC) { - of_node_put(node); + put_device(drm_dev); + put_device(&pdev->dev); + +next: + of_node_put(node); + + if (cnt == MAX_CRTC) break; - } } if (drm_priv->data->mmsys_dev_num == cnt) { -- 2.25.1

3 weeks, 1 day

2
1
0 0

accel/ivpu backport request for 6.12

by Jacek Lawrynowicz

Hi, Please cherry-pick following patch to 6.12: 541a137254c71 accel/ivpu: Fix reset_engine debugfs file logic It fixes a small regression introduced in: 0c3fa6e8441b1 accel/ivpu: Remove copy engine support Thanks, Jacek

3 weeks, 1 day

1
0
0 0

[PATCH v2 0/2] fscontext: do not consume log entries when returning -EMSGSIZE

by Aleksa Sarai

Userspace generally expects APIs that return -EMSGSIZE to allow for them to adjust their buffer size and retry the operation. However, the fscontext log would previously clear the message even in the -EMSGSIZE case. Given that it is very cheap for us to check whether the buffer is too small before we remove the message from the ring buffer, let's just do that instead. While we're at it, refactor some fscontext_read() into a separate helper to make the ring buffer logic a bit easier to read. Fixes: 007ec26cdc9f ("vfs: Implement logging through fs_context") Signed-off-by: Aleksa Sarai <cyphar(a)cyphar.com> --- Changes in v2: - Refactor message fetching to fetch_message_locked() which returns ERR_PTR() in error cases. [Al Viro] - v1: <https://lore.kernel.org/r/20250806-fscontext-log-cleanups-v1-0-880597d42a5a…> --- Aleksa Sarai (2): fscontext: do not consume log entries when returning -EMSGSIZE selftests/filesystems: add basic fscontext log tests fs/fsopen.c | 54 +++++----- tools/testing/selftests/filesystems/.gitignore | 1 + tools/testing/selftests/filesystems/Makefile | 2 +- tools/testing/selftests/filesystems/fclog.c | 135 +++++++++++++++++++++++++ 4 files changed, 167 insertions(+), 25 deletions(-) --- base-commit: 66639db858112bf6b0f76677f7517643d586e575 change-id: 20250806-fscontext-log-cleanups-50f0143674ae Best regards, -- Aleksa Sarai <cyphar(a)cyphar.com>

3 weeks, 1 day

1
1
0 0

[PATCH v2] ALSA: intel_hdmi: Fix off-by-one error in __hdmi_lpe_audio_probe()

by Thorsten Blum

In __hdmi_lpe_audio_probe(), strscpy() is incorrectly called with the length of the source string (excluding the NUL terminator) rather than the size of the destination buffer. This results in one character less being copied from 'card->shortname' to 'pcm->name'. Use the destination buffer size instead to ensure the card name is copied correctly. Cc: stable(a)vger.kernel.org Fixes: 75b1a8f9d62e ("ALSA: Convert strlcpy to strscpy when return value is unused") Signed-off-by: Thorsten Blum <thorsten.blum(a)linux.dev> --- Changes in v2: - Use three parameter variant of strscpy() for backporting as suggested by Sakari Ailus <sakari.ailus(a)linux.intel.com> - Link to v1: https://lore.kernel.org/lkml/20250805190809.31150-1-thorsten.blum@linux.dev/ --- sound/x86/intel_hdmi_audio.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/x86/intel_hdmi_audio.c b/sound/x86/intel_hdmi_audio.c index cc54539c6030..01f49555c5f6 100644 --- a/sound/x86/intel_hdmi_audio.c +++ b/sound/x86/intel_hdmi_audio.c @@ -1765,7 +1765,7 @@ static int __hdmi_lpe_audio_probe(struct platform_device *pdev) /* setup private data which can be retrieved when required */ pcm->private_data = ctx; pcm->info_flags = 0; - strscpy(pcm->name, card->shortname, strlen(card->shortname)); + strscpy(pcm->name, card->shortname, sizeof(pcm->name)); /* setup the ops for playback */ snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_PLAYBACK, &had_pcm_ops); -- 2.50.1

3 weeks, 1 day

2
1
0 0

[PATCH 0/2] fscontext: do not consume log entries for -EMSGSIZE case

by Aleksa Sarai

Userspace generally expects APIs that return EMSGSIZE to allow for them to adjust their buffer size and retry the operation. However, the fscontext log would previously clear the message even in the EMSGSIZE case. Given that it is very cheap for us to check whether the buffer is too small before we remove the message from the ring buffer, let's just do that instead. Fixes: 007ec26cdc9f ("vfs: Implement logging through fs_context") Signed-off-by: Aleksa Sarai <cyphar(a)cyphar.com> --- Aleksa Sarai (2): fscontext: do not consume log entries for -EMSGSIZE case selftests/filesystems: add basic fscontext log tests fs/fsopen.c | 22 ++-- tools/testing/selftests/filesystems/.gitignore | 1 + tools/testing/selftests/filesystems/Makefile | 2 +- tools/testing/selftests/filesystems/fclog.c | 137 +++++++++++++++++++++++++ 4 files changed, 153 insertions(+), 9 deletions(-) --- base-commit: 66639db858112bf6b0f76677f7517643d586e575 change-id: 20250806-fscontext-log-cleanups-50f0143674ae Best regards, -- Aleksa Sarai <cyphar(a)cyphar.com>

3 weeks, 1 day

2
2
0 0

[PATCH v2] smb: server: Fix extension string in ksmbd_extract_shortname()

by Thorsten Blum

In ksmbd_extract_shortname(), strscpy() is incorrectly called with the length of the source string (excluding the NUL terminator) rather than the size of the destination buffer. This results in "__" being copied to 'extension' rather than "___" (two underscores instead of three). Use the destination buffer size instead to ensure that the string "___" (three underscores) is copied correctly. Cc: stable(a)vger.kernel.org Fixes: e2f34481b24d ("cifsd: add server-side procedures for SMB3") Signed-off-by: Thorsten Blum <thorsten.blum(a)linux.dev> --- Changes in v2: - Use three parameter variant of strscpy() for easier backporting - Link to v1: https://lore.kernel.org/lkml/20250805221424.57890-1-thorsten.blum@linux.dev/ --- fs/smb/server/smb_common.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/smb/server/smb_common.c b/fs/smb/server/smb_common.c index 425c756bcfb8..b23203a1c286 100644 --- a/fs/smb/server/smb_common.c +++ b/fs/smb/server/smb_common.c @@ -515,7 +515,7 @@ int ksmbd_extract_shortname(struct ksmbd_conn *conn, const char *longname, p = strrchr(longname, '.'); if (p == longname) { /*name starts with a dot*/ - strscpy(extension, "___", strlen("___")); + strscpy(extension, "___", sizeof(extension)); } else { if (p) { p++; -- 2.50.1

3 weeks, 2 days

2
1
0 0

[PATCH v2] fs: always return zero on success from replace_fd()

by Thomas Weißschuh

replace_fd() returns the number of the new file descriptor through the return value of do_dup2(). However its callers never care about the specific number. In fact the caller in receive_fd_replace() treats any non-zero return value as an error and therefore never calls __receive_sock() for most file descriptors, which is a bug. To fix the bug in receive_fd_replace() and to avoid the same issue happening in future callers, signal success through a plain zero. Suggested-by: Al Viro <viro(a)zeniv.linux.org.uk> Link: https://lore.kernel.org/lkml/20250801220215.GS222315@ZenIV/ Fixes: 173817151b15 ("fs: Expand __receive_fd() to accept existing fd") Fixes: 42eb0d54c08a ("fs: split receive_fd_replace from __receive_fd") Cc: stable(a)vger.kernel.org Signed-off-by: Thomas Weißschuh <thomas.weissschuh(a)linutronix.de> --- Changes in v2: - Move the fix to replace_fd() (Al) - Link to v1: https://lore.kernel.org/r/20250801-fix-receive_fd_replace-v1-1-d46d600c74d6… --- Untested, it stuck out while reading the code. --- fs/file.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/fs/file.c b/fs/file.c index 6d2275c3be9c6967d16c75d1b6521f9b58980926..f8a271265913951d755a5db559938d589219c4f2 100644 --- a/fs/file.c +++ b/fs/file.c @@ -1330,7 +1330,10 @@ int replace_fd(unsigned fd, struct file *file, unsigned flags) err = expand_files(files, fd); if (unlikely(err < 0)) goto out_unlock; - return do_dup2(files, file, fd, flags); + err = do_dup2(files, file, fd, flags); + if (err < 0) + goto out_unlock; + err = 0; out_unlock: spin_unlock(&files->file_lock); --- base-commit: d2eedaa3909be9102d648a4a0a50ccf64f96c54f change-id: 20250801-fix-receive_fd_replace-7fdd5ce6532d Best regards, -- Thomas Weißschuh <thomas.weissschuh(a)linutronix.de>

3 weeks, 2 days

3
9
0 0

[PATCH v1 0/6] Backport "x86: fix off-by-one in access_ok()" to 6.6.y

by Jimmy Tran

This patch series backports a critical security fix, identified as CVE-2020-12965 ("Transient Execution of Non-Canonical Accesses"), to the 6.6.y stable kernel tree. commit 573f45a9f9a47fed4c7957609689b772121b33d7 upstream. David Laight (1): x86: fix off-by-one in access_ok() Linus Torvalds (5): vfs: dcache: move hashlen_hash() from callers into d_hash() runtime constants: add default dummy infrastructure runtime constants: add x86 architecture support arm64: add 'runtime constant' support x86: fix user address masking non-canonical speculation issue arch/arm64/include/asm/runtime-const.h | 92 ++++++++++++++++++++++++++ arch/arm64/kernel/vmlinux.lds.S | 3 + arch/x86/include/asm/runtime-const.h | 61 +++++++++++++++++ arch/x86/include/asm/uaccess_64.h | 45 ++++++++----- arch/x86/kernel/cpu/common.c | 10 +++ arch/x86/kernel/vmlinux.lds.S | 4 ++ arch/x86/lib/getuser.S | 9 ++- fs/dcache.c | 17 +++-- include/asm-generic/Kbuild | 1 + include/asm-generic/runtime-const.h | 15 +++++ include/asm-generic/vmlinux.lds.h | 8 +++ 11 files changed, 243 insertions(+), 22 deletions(-) create mode 100644 arch/arm64/include/asm/runtime-const.h create mode 100644 arch/x86/include/asm/runtime-const.h create mode 100644 include/asm-generic/runtime-const.h -- 2.50.0.727.gbf7dc18ff4-goog

3 weeks, 2 days

4
17
0 0

[PATCH] smb: server: Fix extension string in ksmbd_extract_shortname()

by Thorsten Blum

In ksmbd_extract_shortname(), strscpy() is incorrectly called with the length of the source string (excluding the NUL terminator) rather than the size of the destination buffer. This results in "__" being copied to 'extension' rather than "___" (two underscores instead of three). Since 'extension' is a fixed-size buffer, we can safely omit the size argument and let strscpy() infer it using sizeof(). This ensures that the string "___" (three underscores) is copied correctly. Cc: stable(a)vger.kernel.org Fixes: e2f34481b24d ("cifsd: add server-side procedures for SMB3") Signed-off-by: Thorsten Blum <thorsten.blum(a)linux.dev> --- fs/smb/server/smb_common.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/smb/server/smb_common.c b/fs/smb/server/smb_common.c index 425c756bcfb8..92c0562283da 100644 --- a/fs/smb/server/smb_common.c +++ b/fs/smb/server/smb_common.c @@ -515,7 +515,7 @@ int ksmbd_extract_shortname(struct ksmbd_conn *conn, const char *longname, p = strrchr(longname, '.'); if (p == longname) { /*name starts with a dot*/ - strscpy(extension, "___", strlen("___")); + strscpy(extension, "___"); } else { if (p) { p++; -- 2.50.1

3 weeks, 2 days

1
0
0 0

[merged mm-hotfixes-stable] mm-kmemleak-avoid-soft-lockup-in-__kmemleak_do_cleanup.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: mm/kmemleak: avoid soft lockup in __kmemleak_do_cleanup() has been removed from the -mm tree. Its filename was mm-kmemleak-avoid-soft-lockup-in-__kmemleak_do_cleanup.patch This patch was dropped because it was merged into the mm-hotfixes-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: Waiman Long <longman(a)redhat.com> Subject: mm/kmemleak: avoid soft lockup in __kmemleak_do_cleanup() Date: Mon, 28 Jul 2025 15:02:48 -0400 A soft lockup warning was observed on a relative small system x86-64 system with 16 GB of memory when running a debug kernel with kmemleak enabled. watchdog: BUG: soft lockup - CPU#8 stuck for 33s! [kworker/8:1:134] The test system was running a workload with hot unplug happening in parallel. Then kemleak decided to disable itself due to its inability to allocate more kmemleak objects. The debug kernel has its CONFIG_DEBUG_KMEMLEAK_MEM_POOL_SIZE set to 40,000. The soft lockup happened in kmemleak_do_cleanup() when the existing kmemleak objects were being removed and deleted one-by-one in a loop via a workqueue. In this particular case, there are at least 40,000 objects that need to be processed and given the slowness of a debug kernel and the fact that a raw_spinlock has to be acquired and released in __delete_object(), it could take a while to properly handle all these objects. As kmemleak has been disabled in this case, the object removal and deletion process can be further optimized as locking isn't really needed. However, it is probably not worth the effort to optimize for such an edge case that should rarely happen. So the simple solution is to call cond_resched() at periodic interval in the iteration loop to avoid soft lockup. Link: https://lkml.kernel.org/r/20250728190248.605750-1-longman@redhat.com Signed-off-by: Waiman Long <longman(a)redhat.com> Acked-by: Catalin Marinas <catalin.marinas(a)arm.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/kmemleak.c | 5 +++++ 1 file changed, 5 insertions(+) --- a/mm/kmemleak.c~mm-kmemleak-avoid-soft-lockup-in-__kmemleak_do_cleanup +++ a/mm/kmemleak.c @@ -2184,6 +2184,7 @@ static const struct file_operations kmem static void __kmemleak_do_cleanup(void) { struct kmemleak_object *object, *tmp; + unsigned int cnt = 0; /* * Kmemleak has already been disabled, no need for RCU list traversal @@ -2192,6 +2193,10 @@ static void __kmemleak_do_cleanup(void) list_for_each_entry_safe(object, tmp, &object_list, object_list) { __remove_object(object); __delete_object(object); + + /* Call cond_resched() once per 64 iterations to avoid soft lockup */ + if (!(++cnt & 0x3f)) + cond_resched(); } } _ Patches currently in -mm which might be from longman(a)redhat.com are

3 weeks, 2 days

1
0
0 0

[merged mm-hotfixes-stable] mm-kmemleak-avoid-deadlock-by-moving-pr_warn-outside-kmemleak_lock.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: mm/kmemleak: avoid deadlock by moving pr_warn() outside kmemleak_lock has been removed from the -mm tree. Its filename was mm-kmemleak-avoid-deadlock-by-moving-pr_warn-outside-kmemleak_lock.patch This patch was dropped because it was merged into the mm-hotfixes-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: Breno Leitao <leitao(a)debian.org> Subject: mm/kmemleak: avoid deadlock by moving pr_warn() outside kmemleak_lock Date: Thu, 31 Jul 2025 02:57:18 -0700 When netpoll is enabled, calling pr_warn_once() while holding kmemleak_lock in mem_pool_alloc() can cause a deadlock due to lock inversion with the netconsole subsystem. This occurs because pr_warn_once() may trigger netpoll, which eventually leads to __alloc_skb() and back into kmemleak code, attempting to reacquire kmemleak_lock. This is the path for the deadlock. mem_pool_alloc() -> raw_spin_lock_irqsave(&kmemleak_lock, flags); -> pr_warn_once() -> netconsole subsystem -> netpoll -> __alloc_skb -> __create_object -> raw_spin_lock_irqsave(&kmemleak_lock, flags); Fix this by setting a flag and issuing the pr_warn_once() after kmemleak_lock is released. Link: https://lkml.kernel.org/r/20250731-kmemleak_lock-v1-1-728fd470198f@debian.o… Fixes: c5665868183f ("mm: kmemleak: use the memory pool for early allocations") Signed-off-by: Breno Leitao <leitao(a)debian.org> Reported-by: Jakub Kicinski <kuba(a)kernel.org> Acked-by: Catalin Marinas <catalin.marinas(a)arm.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/kmemleak.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) --- a/mm/kmemleak.c~mm-kmemleak-avoid-deadlock-by-moving-pr_warn-outside-kmemleak_lock +++ a/mm/kmemleak.c @@ -470,6 +470,7 @@ static struct kmemleak_object *mem_pool_ { unsigned long flags; struct kmemleak_object *object; + bool warn = false; /* try the slab allocator first */ if (object_cache) { @@ -488,8 +489,10 @@ static struct kmemleak_object *mem_pool_ else if (mem_pool_free_count) object = &mem_pool[--mem_pool_free_count]; else - pr_warn_once("Memory pool empty, consider increasing CONFIG_DEBUG_KMEMLEAK_MEM_POOL_SIZE\n"); + warn = true; raw_spin_unlock_irqrestore(&kmemleak_lock, flags); + if (warn) + pr_warn_once("Memory pool empty, consider increasing CONFIG_DEBUG_KMEMLEAK_MEM_POOL_SIZE\n"); return object; } _ Patches currently in -mm which might be from leitao(a)debian.org are

3 weeks, 2 days

1
0
0 0

[merged mm-hotfixes-stable] kasan-test-fix-protection-against-compiler-elision.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: kasan/test: fix protection against compiler elision has been removed from the -mm tree. Its filename was kasan-test-fix-protection-against-compiler-elision.patch This patch was dropped because it was merged into the mm-hotfixes-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: Jann Horn <jannh(a)google.com> Subject: kasan/test: fix protection against compiler elision Date: Mon, 28 Jul 2025 22:11:54 +0200 The kunit test is using assignments to "static volatile void *kasan_ptr_result" to prevent elision of memory loads, but that's not working: In this variable definition, the "volatile" applies to the "void", not to the pointer. To make "volatile" apply to the pointer as intended, it must follow after the "*". This makes the kasan_memchr test pass again on my system. The kasan_strings test is still failing because all the definitions of load_unaligned_zeropad() are lacking explicit instrumentation hooks and ASAN does not instrument asm() memory operands. Link: https://lkml.kernel.org/r/20250728-kasan-kunit-fix-volatile-v1-1-e7157c9af8… Fixes: 5f1c8108e7ad ("mm:kasan: fix sparse warnings: Should it be static?") Signed-off-by: Jann Horn <jannh(a)google.com> Cc: Alexander Potapenko <glider(a)google.com> Cc: Andrey Konovalov <andreyknvl(a)gmail.com> Cc: Andrey Ryabinin <ryabinin.a.a(a)gmail.com> Cc: Dmitriy Vyukov <dvyukov(a)google.com> Cc: Jann Horn <jannh(a)google.com> Cc: Nihar Chaithanya <niharchaithanya(a)gmail.com> Cc: Vincenzo Frascino <vincenzo.frascino(a)arm.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/kasan/kasan_test_c.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) --- a/mm/kasan/kasan_test_c.c~kasan-test-fix-protection-against-compiler-elision +++ a/mm/kasan/kasan_test_c.c @@ -47,7 +47,7 @@ static struct { * Some tests use these global variables to store return values from function * calls that could otherwise be eliminated by the compiler as dead code. */ -static volatile void *kasan_ptr_result; +static void *volatile kasan_ptr_result; static volatile int kasan_int_result; /* Probe for console output: obtains test_status lines of interest. */ _ Patches currently in -mm which might be from jannh(a)google.com are kasan-add-test-for-slab_typesafe_by_rcu-quarantine-skipping.patch kasan-add-test-for-slab_typesafe_by_rcu-quarantine-skipping-v2.patch

3 weeks, 2 days

1
0
0 0

[PATCH] NFSD: Fix destination buffer size in nfsd4_ssc_setup_dul()

by Thorsten Blum

Commit 5304877936c0 ("NFSD: Fix strncpy() fortify warning") replaced strncpy(,, sizeof(..)) with strlcpy(,, sizeof(..) - 1), but strlcpy() already guaranteed NUL-termination of the destination buffer and subtracting one byte potentially truncated the source string. The incorrect size was then carried over in commit 72f78ae00a8e ("NFSD: move from strlcpy with unused retval to strscpy") when switching from strlcpy() to strscpy(). Fix this off-by-one error by using the full size of the destination buffer again. Cc: stable(a)vger.kernel.org Fixes: 5304877936c0 ("NFSD: Fix strncpy() fortify warning") Signed-off-by: Thorsten Blum <thorsten.blum(a)linux.dev> --- fs/nfsd/nfs4proc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 71b428efcbb5..32be002a248f 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1469,7 +1469,7 @@ static __be32 nfsd4_ssc_setup_dul(struct nfsd_net *nn, char *ipaddr, return 0; } if (work) { - strscpy(work->nsui_ipaddr, ipaddr, sizeof(work->nsui_ipaddr) - 1); + strscpy(work->nsui_ipaddr, ipaddr); refcount_set(&work->nsui_refcnt, 2); work->nsui_busy = true; list_add_tail(&work->nsui_list, &nn->nfsd_ssc_mount_list); -- 2.50.1

3 weeks, 2 days

2
1
0 0

[PATCH AUTOSEL 6.16-6.6] mfd: axp20x: Set explicit ID for AXP313 regulator

by Sasha Levin

From: Chen-Yu Tsai <wens(a)csie.org> [ Upstream commit 88828c7e940dd45d139ad4a39d702b23840a37c5 ] On newer boards featuring the A523 SoC, the AXP323 (related to the AXP313) is paired with the AXP717 and serves as a secondary PMIC providing additional regulator outputs. However the MFD cells are all registered with PLATFORM_DEVID_NONE, which causes the regulator cells to conflict with each other. Commit e37ec3218870 ("mfd: axp20x: Allow multiple regulators") attempted to fix this by switching to PLATFORM_DEVID_AUTO so that the device names would all be different, however that broke IIO channel mapping, which is also tied to the device names. As a result the change was later reverted. Instead, here we attempt to make sure the AXP313/AXP323 regulator cell does not conflict by explicitly giving it an ID number. This was previously done for the AXP809+AXP806 pair used with the A80 SoC. Signed-off-by: Chen-Yu Tsai <wens(a)csie.org> Link: https://lore.kernel.org/r/20250619173207.3367126-1-wens@kernel.org Signed-off-by: Lee Jones <lee(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- LLM Generated explanations, may be completely bogus: Based on my analysis, here's my assessment: **Backport Status: YES** This commit is suitable for backporting to stable kernel trees for the following reasons: 1. **Fixes a real bug**: The commit addresses a device naming conflict issue when using AXP313/AXP323 PMICs alongside AXP717 as a secondary PMIC. Without this fix, the kernel produces a sysfs duplicate filename error and fails to properly register the secondary regulator device. 2. **Small and contained change**: The fix is minimal - it only changes one line of code from `MFD_CELL_NAME("axp20x-regulator")` to `MFD_CELL_BASIC("axp20x-regulator", NULL, NULL, 0, 1)`, which explicitly sets an ID of 1 for the AXP313 regulator cell. 3. **Follows established pattern**: The commit follows an existing pattern already used in the same driver for the AXP806 PMIC (lines 1173-1174 in axp806_cells), which also sets an explicit ID (2) to avoid conflicts when paired with AXP809. 4. **Minimal risk of regression**: The change only affects AXP313/AXP323 devices and doesn't touch other PMIC configurations. The explicit ID assignment is a safe approach that doesn't break existing IIO channel mappings (which was the problem with the previous PLATFORM_DEVID_AUTO approach mentioned in the commit message). 5. **Clear problem and solution**: The commit message clearly explains the issue (sysfs duplicate filename error) and references the history of previous attempts to fix similar issues (commit e37ec3218870 and its revert). The solution is targeted and doesn't introduce architectural changes. 6. **Hardware enablement fix**: This fix enables proper functioning of boards with the A523 SoC that use dual PMIC configurations (AXP323 + AXP717), which would otherwise fail to initialize properly. The commit meets the stable tree criteria of being an important bugfix with minimal risk and contained scope. It fixes a specific hardware configuration issue without introducing new features or making broad architectural changes. drivers/mfd/axp20x.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/mfd/axp20x.c b/drivers/mfd/axp20x.c index e9914e8a29a3..25c639b348cd 100644 --- a/drivers/mfd/axp20x.c +++ b/drivers/mfd/axp20x.c @@ -1053,7 +1053,8 @@ static const struct mfd_cell axp152_cells[] = { }; static struct mfd_cell axp313a_cells[] = { - MFD_CELL_NAME("axp20x-regulator"), + /* AXP323 is sometimes paired with AXP717 as sub-PMIC */ + MFD_CELL_BASIC("axp20x-regulator", NULL, NULL, 0, 1), MFD_CELL_RES("axp313a-pek", axp313a_pek_resources), }; -- 2.39.5

3 weeks, 2 days

2
72
0 0

[PATCH v3 0/4] kcov, usb: Fix invalid context sleep in softirq path on PREEMPT_RT

by Yunseong Kim

This patch series resolves a sleeping function called from invalid context bug that occurs when fuzzing USB with syzkaller on a PREEMPT_RT kernel. The regression was introduced by the interaction of two separate patches: one that made kcov's internal locks sleep on PREEMPT_RT for better latency (d5d2c51f1e5f), and another that wrapped a kcov call in the USB softirq path with local_irq_save() to prevent re-entrancy (f85d39dd7ed8). This combination resulted in an attempt to acquire a sleeping lock from within an atomic context, causing a kernel BUG. To resolve this, this series makes the kcov remote path fully compatible with atomic contexts by converting all its internal locking primitives to non-sleeping variants. This approach is more robust than conditional compilation as it creates a single, unified codebase that works correctly on both RT and non-RT kernels. The series is structured as follows: Patch 1 converts the global kcov locks (kcov->lock and kcov_remote_lock) to use the non-sleeping raw_spinlock_t. Patch 2 replace the PREEMPT_RT-specific per-CPU local_lock_t back to the original local_irq_save/restore primitives, making the per-CPU protection non-sleeping as well. Patches 3 and 4 are preparatory refactoring. They move the memory allocation for remote handles out of the locked sections in the KCOV_REMOTE_ENABLE ioctl path, which is a prerequisite for safely using raw_spinlock_t as it forbids sleeping functions like kmalloc within its critical section. With these changes, I have been able to run syzkaller fuzzing on a PREEMPT_RT kernel for a full day with no issues reported. Reproduction details in here. Link: https://lore.kernel.org/all/20250725201400.1078395-2-ysk@kzalloc.com/t/#u Signed-off-by: Yunseong Kim <ysk(a)kzalloc.com> --- Changes from v2: 1. Updated kcov_remote_reset() to use raw_spin_lock_irqsave() / raw_spin_unlock_irqrestore() instead of raw_spin_lock() / raw_spin_unlock(), following the interrupt disabling pattern used in the original function that guard kcov_remote_lock. Changes from v1: 1. Dropped the #ifdef-based PREEMPT_RT branching. 2. Convert kcov->lock and kcov_remote_lock from spinlock_t to raw_spinlock_t. This ensures they remain true, non-sleeping spinlocks even on PREEMPT_RT kernels. 3. Remove the local_lock_t protection for kcov_percpu_data in kcov_remote_start/stop(). Since local_lock_t can also sleep under RT, and the required protection is against local interrupts when accessing per-CPU data, it is replaced with explicit local_irq_save/restore(). 4. Refactor the KCOV_REMOTE_ENABLE path to move memory allocations out of the critical section. 5. Modify the ioctl handling logic to utilize these pre-allocated structures within the critical section. kcov_remote_add() is modified to accept a pre-allocated structure instead of allocating one internally. All necessary struct kcov_remote structures are now pre-allocated individually in kcov_ioctl() using GFP_KERNEL (allowing sleep) before acquiring the raw spinlocks. Changes from v0: 1. On PREEMPT_RT, separated the handling of kcov_remote_start_usb_softirq() and kcov_remote_stop_usb_softirq() to allow sleeping when entering kcov_remote_start_usb() / kcov_remote_stop(). Yunseong Kim (4): kcov: Use raw_spinlock_t for kcov->lock and kcov_remote_lock kcov: Replace per-CPU local_lock with local_irq_save/restore kcov: Separate KCOV_REMOTE_ENABLE ioctl helper function kcov: move remote handle allocation outside raw spinlock kernel/kcov.c | 248 +++++++++++++++++++++++++++----------------------- 1 file changed, 134 insertions(+), 114 deletions(-) base-commit: 186f3edfdd41f2ae87fc40a9ccba52a3bf930994 -- 2.50.0

3 weeks, 2 days

3
11
0 0

[PATCH v2] drm/xe: Defer buffer object shrinker write-backs and GPU waits

by Thomas Hellström

When the xe buffer-object shrinker allows GPU waits and write-back, (typically from kswapd), perform multiple passes, skipping subsequent passes if the shrinker number of scanned objects target is reached. 1) Without GPU waits and write-back 2) Without write-back 3) With both GPU-waits and write-back This is to avoid stalls and costly write- and readbacks unless they are really necessary. v2: - Don't test for scan completion twice. (Stuart Summers) - Update tags. Reported-by: melvyn <melvyn2(a)dnsense.pub> Closes: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/5557 Cc: Summers Stuart <stuart.summers(a)intel.com> Fixes: 00c8efc3180f ("drm/xe: Add a shrinker for xe bos") Cc: <stable(a)vger.kernel.org> # v6.15+ Signed-off-by: Thomas Hellström <thomas.hellstrom(a)linux.intel.com> --- drivers/gpu/drm/xe/xe_shrinker.c | 51 +++++++++++++++++++++++++++++--- 1 file changed, 47 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_shrinker.c b/drivers/gpu/drm/xe/xe_shrinker.c index 1c3c04d52f55..90244fe59b59 100644 --- a/drivers/gpu/drm/xe/xe_shrinker.c +++ b/drivers/gpu/drm/xe/xe_shrinker.c @@ -54,10 +54,10 @@ xe_shrinker_mod_pages(struct xe_shrinker *shrinker, long shrinkable, long purgea write_unlock(&shrinker->lock); } -static s64 xe_shrinker_walk(struct xe_device *xe, - struct ttm_operation_ctx *ctx, - const struct xe_bo_shrink_flags flags, - unsigned long to_scan, unsigned long *scanned) +static s64 __xe_shrinker_walk(struct xe_device *xe, + struct ttm_operation_ctx *ctx, + const struct xe_bo_shrink_flags flags, + unsigned long to_scan, unsigned long *scanned) { unsigned int mem_type; s64 freed = 0, lret; @@ -93,6 +93,48 @@ static s64 xe_shrinker_walk(struct xe_device *xe, return freed; } +/* + * Try shrinking idle objects without writeback first, then if not sufficient, + * try also non-idle objects and finally if that's not sufficient either, + * add writeback. This avoids stalls and explicit writebacks with light or + * moderate memory pressure. + */ +static s64 xe_shrinker_walk(struct xe_device *xe, + struct ttm_operation_ctx *ctx, + const struct xe_bo_shrink_flags flags, + unsigned long to_scan, unsigned long *scanned) +{ + bool no_wait_gpu = true; + struct xe_bo_shrink_flags save_flags = flags; + s64 lret, freed; + + swap(no_wait_gpu, ctx->no_wait_gpu); + save_flags.writeback = false; + lret = __xe_shrinker_walk(xe, ctx, save_flags, to_scan, scanned); + swap(no_wait_gpu, ctx->no_wait_gpu); + if (lret < 0 || *scanned >= to_scan) + return lret; + + freed = lret; + if (!ctx->no_wait_gpu) { + lret = __xe_shrinker_walk(xe, ctx, save_flags, to_scan, scanned); + if (lret < 0) + return lret; + freed += lret; + if (*scanned >= to_scan) + return freed; + } + + if (flags.writeback) { + lret = __xe_shrinker_walk(xe, ctx, flags, to_scan, scanned); + if (lret < 0) + return lret; + freed += lret; + } + + return freed; +} + static unsigned long xe_shrinker_count(struct shrinker *shrink, struct shrink_control *sc) { @@ -199,6 +241,7 @@ static unsigned long xe_shrinker_scan(struct shrinker *shrink, struct shrink_con runtime_pm = xe_shrinker_runtime_pm_get(shrinker, true, 0, can_backup); shrink_flags.purge = false; + lret = xe_shrinker_walk(shrinker->xe, &ctx, shrink_flags, nr_to_scan, &nr_scanned); if (lret >= 0) -- 2.50.1

3 weeks, 2 days

3
2
0 0

[PATCH v2] RDMA/siw: Fix the sendmsg byte count in siw_tcp_sendpages

by Pedro Falcato

Ever since commit c2ff29e99a76 ("siw: Inline do_tcp_sendpages()"), we have been doing this: static int siw_tcp_sendpages(struct socket *s, struct page **page, int offset, size_t size) [...] /* Calculate the number of bytes we need to push, for this page * specifically */ size_t bytes = min_t(size_t, PAGE_SIZE - offset, size); /* If we can't splice it, then copy it in, as normal */ if (!sendpage_ok(page[i])) msg.msg_flags &= ~MSG_SPLICE_PAGES; /* Set the bvec pointing to the page, with len $bytes */ bvec_set_page(&bvec, page[i], bytes, offset); /* Set the iter to $size, aka the size of the whole sendpages (!!!) */ iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, size); try_page_again: lock_sock(sk); /* Sendmsg with $size size (!!!) */ rv = tcp_sendmsg_locked(sk, &msg, size); This means we've been sending oversized iov_iters and tcp_sendmsg calls for a while. This has a been a benign bug because sendpage_ok() always returned true. With the recent slab allocator changes being slowly introduced into next (that disallow sendpage on large kmalloc allocations), we have recently hit out-of-bounds crashes, due to slight differences in iov_iter behavior between the MSG_SPLICE_PAGES and "regular" copy paths: (MSG_SPLICE_PAGES) skb_splice_from_iter iov_iter_extract_pages iov_iter_extract_bvec_pages uses i->nr_segs to correctly stop in its tracks before OoB'ing everywhere skb_splice_from_iter gets a "short" read (!MSG_SPLICE_PAGES) skb_copy_to_page_nocache copy=iov_iter_count [...] copy_from_iter /* this doesn't help */ if (unlikely(iter->count < len)) len = iter->count; iterate_bvec ... and we run off the bvecs Fix this by properly setting the iov_iter's byte count, plus sending the correct byte count to tcp_sendmsg_locked. Cc: stable(a)vger.kernel.org Fixes: c2ff29e99a76 ("siw: Inline do_tcp_sendpages()") Reported-by: kernel test robot <oliver.sang(a)intel.com> Closes: https://lore.kernel.org/oe-lkp/202507220801.50a7210-lkp@intel.com Reviewed-by: David Howells <dhowells(a)redhat.com> Signed-off-by: Pedro Falcato <pfalcato(a)suse.de> --- v2: - Add David Howells's Rb on the original patch - Remove the offset increment, since it's dead code drivers/infiniband/sw/siw/siw_qp_tx.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/infiniband/sw/siw/siw_qp_tx.c b/drivers/infiniband/sw/siw/siw_qp_tx.c index 3a08f57d2211..f7dd32c6e5ba 100644 --- a/drivers/infiniband/sw/siw/siw_qp_tx.c +++ b/drivers/infiniband/sw/siw/siw_qp_tx.c @@ -340,18 +340,17 @@ static int siw_tcp_sendpages(struct socket *s, struct page **page, int offset, if (!sendpage_ok(page[i])) msg.msg_flags &= ~MSG_SPLICE_PAGES; bvec_set_page(&bvec, page[i], bytes, offset); - iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, size); + iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, bytes); try_page_again: lock_sock(sk); - rv = tcp_sendmsg_locked(sk, &msg, size); + rv = tcp_sendmsg_locked(sk, &msg, bytes); release_sock(sk); if (rv > 0) { size -= rv; sent += rv; if (rv != bytes) { - offset += rv; bytes -= rv; goto try_page_again; } -- 2.50.1

3 weeks, 2 days

4
5
0 0

[PATCH v3] vhost/net: Protect ubufs with rcu read lock in vhost_net_ubuf_put()

by Nikolay Kuratov

When operating on struct vhost_net_ubuf_ref, the following execution sequence is theoretically possible: CPU0 is finalizing DMA operation CPU1 is doing VHOST_NET_SET_BACKEND // ubufs->refcount == 2 vhost_net_ubuf_put() vhost_net_ubuf_put_wait_and_free(oldubufs) vhost_net_ubuf_put_and_wait() vhost_net_ubuf_put() int r = atomic_sub_return(1, &ubufs->refcount); // r = 1 int r = atomic_sub_return(1, &ubufs->refcount); // r = 0 wait_event(ubufs->wait, !atomic_read(&ubufs->refcount)); // no wait occurs here because condition is already true kfree(ubufs); if (unlikely(!r)) wake_up(&ubufs->wait); // use-after-free This leads to use-after-free on ubufs access. This happens because CPU1 skips waiting for wake_up() when refcount is already zero. To prevent that use a read-side RCU critical section in vhost_net_ubuf_put(), as suggested by Hillf Danton. For this lock to take effect, free ubufs with kfree_rcu(). Cc: stable(a)vger.kernel.org Fixes: 0ad8b480d6ee9 ("vhost: fix ref cnt checking deadlock") Reported-by: Andrey Ryabinin <arbn(a)yandex-team.com> Suggested-by: Hillf Danton <hdanton(a)sina.com> Signed-off-by: Nikolay Kuratov <kniv(a)yandex-team.ru> --- v2: * move reinit_completion() into vhost_net_flush(), thanks to Hillf Danton * add Tested-by: Lei Yang * check that usages of put_and_wait() are consistent across LTS kernels v3: * use rcu_read_lock() with kfree_rcu() instead of completion, as suggested by Hillf Danton drivers/vhost/net.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 6edac0c1ba9b..c6508fe0d5c8 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -99,6 +99,7 @@ struct vhost_net_ubuf_ref { atomic_t refcount; wait_queue_head_t wait; struct vhost_virtqueue *vq; + struct rcu_head rcu; }; #define VHOST_NET_BATCH 64 @@ -250,9 +251,13 @@ vhost_net_ubuf_alloc(struct vhost_virtqueue *vq, bool zcopy) static int vhost_net_ubuf_put(struct vhost_net_ubuf_ref *ubufs) { - int r = atomic_sub_return(1, &ubufs->refcount); + int r; + + rcu_read_lock(); + r = atomic_sub_return(1, &ubufs->refcount); if (unlikely(!r)) wake_up(&ubufs->wait); + rcu_read_unlock(); return r; } @@ -265,7 +270,7 @@ static void vhost_net_ubuf_put_and_wait(struct vhost_net_ubuf_ref *ubufs) static void vhost_net_ubuf_put_wait_and_free(struct vhost_net_ubuf_ref *ubufs) { vhost_net_ubuf_put_and_wait(ubufs); - kfree(ubufs); + kfree_rcu(ubufs, rcu); } static void vhost_net_clear_ubuf_info(struct vhost_net *n) -- 2.34.1

3 weeks, 2 days

1
0
0 0

[PATCH v3 1/3] sched_ext: Mark scx_bpf_cpu_rq as NULL returnable

by Christian Loehle

scx_bpf_cpu_rq() obviously returns NULL on invalid cpu. Mark it as such. While kf_cpu_valid() will trigger scx_ops_error() that leads to the BPF scheduler exiting, this isn't guaranteed to be immediate, allowing for a dereference of a NULL scx_bpf_cpu_rq() return value. Cc: stable(a)vger.kernel.org Fixes: 6203ef73fa5c ("sched/ext: Add BPF function to fetch rq") Signed-off-by: Christian Loehle <christian.loehle(a)arm.com> Acked-by: Andrea Righi <arighi(a)nvidia.com> --- kernel/sched/ext.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 7dedc9a16281..3ea3f0f18030 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -7589,7 +7589,7 @@ BTF_ID_FLAGS(func, scx_bpf_get_online_cpumask, KF_ACQUIRE) BTF_ID_FLAGS(func, scx_bpf_put_cpumask, KF_RELEASE) BTF_ID_FLAGS(func, scx_bpf_task_running, KF_RCU) BTF_ID_FLAGS(func, scx_bpf_task_cpu, KF_RCU) -BTF_ID_FLAGS(func, scx_bpf_cpu_rq) +BTF_ID_FLAGS(func, scx_bpf_cpu_rq, KF_RET_NULL) #ifdef CONFIG_CGROUP_SCHED BTF_ID_FLAGS(func, scx_bpf_task_cgroup, KF_RCU | KF_ACQUIRE) #endif -- 2.34.1

3 weeks, 2 days

1
0
0 0

[PATCH] drm/amdgpu: Raven: don't allow mixing GTT and VRAM

by Brian Geffon

Commit 81d0bcf99009 ("drm/amdgpu: make display pinning more flexible (v2)") allowed for newer ASICs to mix GTT and VRAM, this change also noted that some older boards, such as Stoney and Carrizo do not support this. It appears that at least one additional ASIC does not support this which is Raven. We observed this issue when migrating a device from a 5.4 to 6.6 kernel and have confirmed that Raven also needs to be excluded from mixing GTT and VRAM. Fixes: 81d0bcf99009 ("drm/amdgpu: make display pinning more flexible (v2)") Cc: Luben Tuikov <luben.tuikov(a)amd.com> Cc: Christian König <christian.koenig(a)amd.com> Cc: Alex Deucher <alexander.deucher(a)amd.com> Cc: stable(a)vger.kernel.org # 6.1+ Tested-by: Thadeu Lima de Souza Cascardo <cascardo(a)igalia.com> Signed-off-by: Brian Geffon <bgeffon(a)google.com> --- drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 73403744331a..5d7f13e25b7c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -1545,7 +1545,8 @@ uint32_t amdgpu_bo_get_preferred_domain(struct amdgpu_device *adev, uint32_t domain) { if ((domain == (AMDGPU_GEM_DOMAIN_VRAM | AMDGPU_GEM_DOMAIN_GTT)) && - ((adev->asic_type == CHIP_CARRIZO) || (adev->asic_type == CHIP_STONEY))) { + ((adev->asic_type == CHIP_CARRIZO) || (adev->asic_type == CHIP_STONEY) || + (adev->asic_type == CHIP_RAVEN))) { domain = AMDGPU_GEM_DOMAIN_VRAM; if (adev->gmc.real_vram_size <= AMDGPU_SG_THRESHOLD) domain = AMDGPU_GEM_DOMAIN_GTT; -- 2.50.0.727.gbf7dc18ff4-goog

3 weeks, 2 days

5
16
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror