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

[PATCH] drm/tegra: fix device leak on probe()

by Johan Hovold

Make sure to drop the reference taken when looking up the companion device during probe(). Note that holding a reference to a device does not prevent its driver data from going away so there is no point in keeping the reference. Fixes: f68ba6912bd2 ("drm/tegra: dc: Link DC1 to DC0 on Tegra20") Cc: stable(a)vger.kernel.org # 4.16 Cc: Dmitry Osipenko <digetx(a)gmail.com> Signed-off-by: Johan Hovold <johan(a)kernel.org> --- drivers/gpu/drm/tegra/dc.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/tegra/dc.c b/drivers/gpu/drm/tegra/dc.c index 59d5c1ba145a..7a6b30df6a89 100644 --- a/drivers/gpu/drm/tegra/dc.c +++ b/drivers/gpu/drm/tegra/dc.c @@ -3148,6 +3148,8 @@ static int tegra_dc_couple(struct tegra_dc *dc) dc->client.parent = &parent->client; dev_dbg(dc->dev, "coupled to %s\n", dev_name(companion)); + + put_device(companion); } return 0; -- 2.51.2

7 hours, 30 minutes

1
0
0 0

[PATCH] crypto: hisilicon/qm - fix device leak on QoS updates

by Johan Hovold

Make sure to drop the reference taken when looking up the PCI device on QoS updates. Fixes: 22d7a6c39cab ("crypto: hisilicon/qm - add pci bdf number check") Cc: stable(a)vger.kernel.org # 6.2 Cc: Kai Ye <yekai13(a)huawei.com> Signed-off-by: Johan Hovold <johan(a)kernel.org> --- drivers/crypto/hisilicon/qm.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c index a5b96adf2d1e..ef6fdcc3dbcb 100644 --- a/drivers/crypto/hisilicon/qm.c +++ b/drivers/crypto/hisilicon/qm.c @@ -3871,11 +3871,14 @@ static ssize_t qm_get_qos_value(struct hisi_qm *qm, const char *buf, pdev = container_of(dev, struct pci_dev, dev); if (pci_physfn(pdev) != qm->pdev) { pci_err(qm->pdev, "the pdev input does not match the pf!\n"); + put_device(dev); return -EINVAL; } *fun_index = pdev->devfn; + put_device(dev); + return 0; } -- 2.51.2

7 hours, 43 minutes

1
0
0 0

[PATCH v2] intel_th: fix device leak on output open()

by Johan Hovold

Make sure to drop the reference taken when looking up the th device during output device open() on errors and on close(). Fixes: 39f4034693b7 ("intel_th: Add driver infrastructure for Intel(R) Trace Hub devices") Cc: stable(a)vger.kernel.org # 4.4 Cc: Alexander Shishkin <alexander.shishkin(a)linux.intel.com> Signed-off-by: Johan Hovold <johan(a)kernel.org> --- Hit send too soon... Changes in v2: - drop reference also on the last error path drivers/hwtracing/intel_th/core.c | 30 ++++++++++++++++++++++++++---- 1 file changed, 26 insertions(+), 4 deletions(-) diff --git a/drivers/hwtracing/intel_th/core.c b/drivers/hwtracing/intel_th/core.c index 47d9e6c3bac0..bc38814e6802 100644 --- a/drivers/hwtracing/intel_th/core.c +++ b/drivers/hwtracing/intel_th/core.c @@ -810,13 +810,20 @@ static int intel_th_output_open(struct inode *inode, struct file *file) int err; dev = bus_find_device_by_devt(&intel_th_bus, inode->i_rdev); - if (!dev || !dev->driver) + if (!dev) return -ENODEV; + if (!dev->driver) { + err = -ENODEV; + goto err_put_dev; + } + thdrv = to_intel_th_driver(dev->driver); fops = fops_get(thdrv->fops); - if (!fops) - return -ENODEV; + if (!fops) { + err = -ENODEV; + goto err_put_dev; + } replace_fops(file, fops); @@ -824,14 +831,29 @@ static int intel_th_output_open(struct inode *inode, struct file *file) if (file->f_op->open) { err = file->f_op->open(inode, file); - return err; + goto err_put_dev; } + return 0; + +err_put_dev: + put_device(dev); + + return err; +} + +static int intel_th_output_release(struct inode *inode, struct file *file) +{ + struct intel_th_device *thdev = file->private_data; + + put_device(&thdev->dev); + return 0; } static const struct file_operations intel_th_output_fops = { .open = intel_th_output_open, + .release = intel_th_output_release, .llseek = noop_llseek, }; -- 2.51.2

7 hours, 59 minutes

1
0
0 0

[PATCH] intel_th: fix device leak on output open()

by Johan Hovold

Make sure to drop the reference taken when looking up the th device during output device open() on errors and on close(). Fixes: 39f4034693b7 ("intel_th: Add driver infrastructure for Intel(R) Trace Hub devices") Cc: stable(a)vger.kernel.org # 4.4 Cc: Alexander Shishkin <alexander.shishkin(a)linux.intel.com> Signed-off-by: Johan Hovold <johan(a)kernel.org> --- drivers/hwtracing/intel_th/core.c | 28 +++++++++++++++++++++++++--- 1 file changed, 25 insertions(+), 3 deletions(-) diff --git a/drivers/hwtracing/intel_th/core.c b/drivers/hwtracing/intel_th/core.c index 47d9e6c3bac0..ddc51de2d775 100644 --- a/drivers/hwtracing/intel_th/core.c +++ b/drivers/hwtracing/intel_th/core.c @@ -810,13 +810,20 @@ static int intel_th_output_open(struct inode *inode, struct file *file) int err; dev = bus_find_device_by_devt(&intel_th_bus, inode->i_rdev); - if (!dev || !dev->driver) + if (!dev) return -ENODEV; + if (!dev->driver) { + err = -ENODEV; + goto err_put_dev; + } + thdrv = to_intel_th_driver(dev->driver); fops = fops_get(thdrv->fops); - if (!fops) - return -ENODEV; + if (!fops) { + err = -ENODEV; + goto err_put_dev; + } replace_fops(file, fops); @@ -827,11 +834,26 @@ static int intel_th_output_open(struct inode *inode, struct file *file) return err; } + return 0; + +err_put_dev: + put_device(dev); + + return err; +} + +static int intel_th_output_release(struct inode *inode, struct file *file) +{ + struct intel_th_device *thdev = file->private_data; + + put_device(&thdev->dev); + return 0; } static const struct file_operations intel_th_output_fops = { .open = intel_th_output_open, + .release = intel_th_output_release, .llseek = noop_llseek, }; -- 2.51.2

8 hours, 4 minutes

1
0
0 0

[PATCH 6.6.y] smb: client: support kvec iterators in async read path

by Henrique Carvalho

commit 3ee1a1fc39819906f04d6c62c180e760cd3a689d upstream. Add cifs_limit_kvec_subset() and select the appropriate limiter in cifs_send_async_read() to handle kvec iterators in async read path, fixing the EIO bug when running executables in cifs shares mounted with nolease. This patch -- or equivalent patch, does not exist upstream, as the upstream code has suffered considerable API changes. The affected path is currently handled by netfs lib and located under netfs/direct_read.c. Reproducer: $ mount.cifs //server/share /mnt -o nolease $ cat - > /mnt/test.sh <<EOL echo hallo EOL $ chmod +x /mnt/test.sh $ /mnt/test.sh bash: /mnt/test.sh: /bin/bash: Defekter Interpreter: Eingabe-/Ausgabefehler $ rm -f /mnt/test.sh Fixes: d08089f649a0 ("cifs: Change the I/O paths to use an iterator rather than a page list") Reported-by: Laura Kerner <laura.kerner(a)ichaus.de> Closes: https://bugzilla.suse.com/show_bug.cgi?id=1245449 Signed-off-by: Henrique Carvalho <henrique.carvalho(a)suse.com> --- fs/smb/client/file.c | 46 ++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 44 insertions(+), 2 deletions(-) diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index d883ed75022c..4878c74bae6f 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -3527,6 +3527,42 @@ static size_t cifs_limit_bvec_subset(const struct iov_iter *iter, size_t max_siz return span; } +static size_t cifs_limit_kvec_subset(const struct iov_iter *iter, size_t max_size, + size_t max_segs, unsigned int *_nsegs) +{ + const struct kvec *kvecs = iter->kvec; + unsigned int nkv = iter->nr_segs, ix = 0, nsegs = 0; + size_t len, span = 0, n = iter->count; + size_t skip = iter->iov_offset; + + if (WARN_ON(!iov_iter_is_kvec(iter)) || n == 0) + return 0; + + while (n && ix < nkv && skip) { + len = kvecs[ix].iov_len; + if (skip < len) + break; + skip -= len; + n -= len; + ix++; + } + + while (n && ix < nkv) { + len = min3(n, kvecs[ix].iov_len - skip, max_size); + span += len; + max_size -= len; + nsegs++; + ix++; + if (max_size == 0 || nsegs >= max_segs) + break; + skip = 0; + n -= len; + } + + *_nsegs = nsegs; + return span; +} + static int cifs_write_from_iter(loff_t fpos, size_t len, struct iov_iter *from, struct cifsFileInfo *open_file, @@ -4079,6 +4115,13 @@ cifs_send_async_read(loff_t fpos, size_t len, struct cifsFileInfo *open_file, int rc; pid_t pid; struct TCP_Server_Info *server; + size_t (*limit_iov_subset)(const struct iov_iter *iter, size_t max_size, + size_t max_segs, unsigned int *_nsegs); + + if (iov_iter_is_kvec(&ctx->iter)) + limit_iov_subset = cifs_limit_kvec_subset; + else + limit_iov_subset = cifs_limit_bvec_subset; server = cifs_pick_channel(tlink_tcon(open_file->tlink)->ses); @@ -4113,8 +4156,7 @@ cifs_send_async_read(loff_t fpos, size_t len, struct cifsFileInfo *open_file, max_len = min_t(size_t, len, rsize); - cur_len = cifs_limit_bvec_subset(&ctx->iter, max_len, - max_segs, &nsegs); + cur_len = limit_iov_subset(&ctx->iter, max_len, max_segs, &nsegs); cifs_dbg(FYI, "read-to-iter len=%zx/%zx nsegs=%u/%lu/%u\n", cur_len, max_len, nsegs, ctx->iter.nr_segs, max_segs); if (cur_len == 0) { -- 2.47.0

8 hours, 23 minutes

5
6
0 0

[PATCH v3] drm/tilcdc: Fix removal actions in case of failed probe

by Kory Maincent

From: "Kory Maincent (TI.com)" <kory.maincent(a)bootlin.com> The drm_kms_helper_poll_fini() and drm_atomic_helper_shutdown() helpers should only be called when the device has been successfully registered. Currently, these functions are called unconditionally in tilcdc_fini(), which causes warnings during probe deferral scenarios. [ 7.972317] WARNING: CPU: 0 PID: 23 at drivers/gpu/drm/drm_atomic_state_helper.c:175 drm_atomic_helper_crtc_duplicate_state+0x60/0x68 ... [ 8.005820] drm_atomic_helper_crtc_duplicate_state from drm_atomic_get_crtc_state+0x68/0x108 [ 8.005858] drm_atomic_get_crtc_state from drm_atomic_helper_disable_all+0x90/0x1c8 [ 8.005885] drm_atomic_helper_disable_all from drm_atomic_helper_shutdown+0x90/0x144 [ 8.005911] drm_atomic_helper_shutdown from tilcdc_fini+0x68/0xf8 [tilcdc] [ 8.005957] tilcdc_fini [tilcdc] from tilcdc_pdev_probe+0xb0/0x6d4 [tilcdc] Fix this by rewriting the failed probe cleanup path using the standard goto error handling pattern, which ensures that cleanup functions are only called on successfully initialized resources. Additionally, remove the now-unnecessary is_registered flag. Cc: stable(a)vger.kernel.org Fixes: 3c4babae3c4a ("drm: Call drm_atomic_helper_shutdown() at shutdown/remove time for misc drivers") Signed-off-by: Kory Maincent (TI.com) <kory.maincent(a)bootlin.com> --- I'm working on removing the usage of deprecated functions as well as general improvements to this driver, but it will take some time so for now this is a simple fix to a functional bug. Change in v3: - Rewrite the failed probe clean up path using goto - Remove the is_registered flag Change in v2: - Add missing cc: stable tag - Add Swamil reviewed-by --- drivers/gpu/drm/tilcdc/tilcdc_crtc.c | 2 +- drivers/gpu/drm/tilcdc/tilcdc_drv.c | 53 ++++++++++++++++++---------- drivers/gpu/drm/tilcdc/tilcdc_drv.h | 2 +- 3 files changed, 37 insertions(+), 20 deletions(-) diff --git a/drivers/gpu/drm/tilcdc/tilcdc_crtc.c b/drivers/gpu/drm/tilcdc/tilcdc_crtc.c index 5718d9d83a49f..52c95131af5af 100644 --- a/drivers/gpu/drm/tilcdc/tilcdc_crtc.c +++ b/drivers/gpu/drm/tilcdc/tilcdc_crtc.c @@ -586,7 +586,7 @@ static void tilcdc_crtc_recover_work(struct work_struct *work) drm_modeset_unlock(&crtc->mutex); } -static void tilcdc_crtc_destroy(struct drm_crtc *crtc) +void tilcdc_crtc_destroy(struct drm_crtc *crtc) { struct tilcdc_drm_private *priv = crtc->dev->dev_private; diff --git a/drivers/gpu/drm/tilcdc/tilcdc_drv.c b/drivers/gpu/drm/tilcdc/tilcdc_drv.c index 7caec4d38ddf0..2a88cce445b8f 100644 --- a/drivers/gpu/drm/tilcdc/tilcdc_drv.c +++ b/drivers/gpu/drm/tilcdc/tilcdc_drv.c @@ -172,8 +172,7 @@ static void tilcdc_fini(struct drm_device *dev) if (priv->crtc) tilcdc_crtc_shutdown(priv->crtc); - if (priv->is_registered) - drm_dev_unregister(dev); + drm_dev_unregister(dev); drm_kms_helper_poll_fini(dev); drm_atomic_helper_shutdown(dev); @@ -220,21 +219,21 @@ static int tilcdc_init(const struct drm_driver *ddrv, struct device *dev) priv->wq = alloc_ordered_workqueue("tilcdc", 0); if (!priv->wq) { ret = -ENOMEM; - goto init_failed; + goto put_drm; } priv->mmio = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(priv->mmio)) { dev_err(dev, "failed to request / ioremap\n"); ret = PTR_ERR(priv->mmio); - goto init_failed; + goto free_wq; } priv->clk = clk_get(dev, "fck"); if (IS_ERR(priv->clk)) { dev_err(dev, "failed to get functional clock\n"); ret = -ENODEV; - goto init_failed; + goto free_wq; } pm_runtime_enable(dev); @@ -313,7 +312,7 @@ static int tilcdc_init(const struct drm_driver *ddrv, struct device *dev) ret = tilcdc_crtc_create(ddev); if (ret < 0) { dev_err(dev, "failed to create crtc\n"); - goto init_failed; + goto disable_pm; } modeset_init(ddev); @@ -324,46 +323,46 @@ static int tilcdc_init(const struct drm_driver *ddrv, struct device *dev) if (ret) { dev_err(dev, "failed to register cpufreq notifier\n"); priv->freq_transition.notifier_call = NULL; - goto init_failed; + goto destroy_crtc; } #endif if (priv->is_componentized) { ret = component_bind_all(dev, ddev); if (ret < 0) - goto init_failed; + goto unregister_cpufreq_notif; ret = tilcdc_add_component_encoder(ddev); if (ret < 0) - goto init_failed; + goto unbind_component; } else { ret = tilcdc_attach_external_device(ddev); if (ret) - goto init_failed; + goto unregister_cpufreq_notif; } if (!priv->external_connector && ((priv->num_encoders == 0) || (priv->num_connectors == 0))) { dev_err(dev, "no encoders/connectors found\n"); ret = -EPROBE_DEFER; - goto init_failed; + goto unbind_component; } ret = drm_vblank_init(ddev, 1); if (ret < 0) { dev_err(dev, "failed to initialize vblank\n"); - goto init_failed; + goto unbind_component; } ret = platform_get_irq(pdev, 0); if (ret < 0) - goto init_failed; + goto unbind_component; priv->irq = ret; ret = tilcdc_irq_install(ddev, priv->irq); if (ret < 0) { dev_err(dev, "failed to install IRQ handler\n"); - goto init_failed; + goto unbind_component; } drm_mode_config_reset(ddev); @@ -372,16 +371,34 @@ static int tilcdc_init(const struct drm_driver *ddrv, struct device *dev) ret = drm_dev_register(ddev, 0); if (ret) - goto init_failed; - priv->is_registered = true; + goto stop_poll; drm_client_setup_with_color_mode(ddev, bpp); return 0; -init_failed: - tilcdc_fini(ddev); +stop_poll: + drm_kms_helper_poll_fini(ddev); + tilcdc_irq_uninstall(ddev); +unbind_component: + if (priv->is_componentized) + component_unbind_all(dev, ddev); +unregister_cpufreq_notif: +#ifdef CONFIG_CPU_FREQ + cpufreq_unregister_notifier(&priv->freq_transition, + CPUFREQ_TRANSITION_NOTIFIER); +#endif +destroy_crtc: + tilcdc_crtc_destroy(priv->crtc); +disable_pm: + pm_runtime_disable(dev); + clk_put(priv->clk); +free_wq: + destroy_workqueue(priv->wq); +put_drm: platform_set_drvdata(pdev, NULL); + ddev->dev_private = NULL; + drm_dev_put(ddev); return ret; } diff --git a/drivers/gpu/drm/tilcdc/tilcdc_drv.h b/drivers/gpu/drm/tilcdc/tilcdc_drv.h index b818448c83f61..58b276f82a669 100644 --- a/drivers/gpu/drm/tilcdc/tilcdc_drv.h +++ b/drivers/gpu/drm/tilcdc/tilcdc_drv.h @@ -82,7 +82,6 @@ struct tilcdc_drm_private { struct drm_encoder *external_encoder; struct drm_connector *external_connector; - bool is_registered; bool is_componentized; bool irq_enabled; }; @@ -164,6 +163,7 @@ void tilcdc_crtc_set_panel_info(struct drm_crtc *crtc, void tilcdc_crtc_set_simulate_vesa_sync(struct drm_crtc *crtc, bool simulate_vesa_sync); void tilcdc_crtc_shutdown(struct drm_crtc *crtc); +void tilcdc_crtc_destroy(struct drm_crtc *crtc); int tilcdc_crtc_update_fb(struct drm_crtc *crtc, struct drm_framebuffer *fb, struct drm_pending_vblank_event *event); -- 2.43.0

8 hours, 30 minutes

3
4
0 0

Great Original Shirts

by Spencer

8 hours, 32 minutes

1
0
0 0

[REGRESSION 6.12.y] hyper-v: BUG: kernel NULL pointer dereference, address: 00000000000000a0: RIP: 0010:hv_uio_channel_cb+0xd/0x20 [uio_hv_generic]

by Salvatore Bonaccorso

Peter Morrow reported in Debian a regression, reported in https://bugs.debian.org/1120602 . The regression was seen after updating, to 6.12.57-1 in Debian, but details on the offending commit follows. His report was as follows: > Dear Maintainer, > > I'm seeing a kernel crash quite soon after boot on a debian trixie based > system running 6.12.57+deb13-amd64, unfortunately the kernel panics before > I can access the system to gather more information. Thus I'll provide details > of the system using a previously known good version. The panic is happening > 100% of the time unfortunately. I have access to the serial console however > so can enable any required verbose logging during boot if necessary. > > Crucially the crash is not seen with kernel version 6.12.41+deb13-amd64 with the > same userspace. We had pinned to that version until very recently to in order > to work around https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=1109676 > > I'm running a dpdk application here (VPP) on Azure, VM form factor is a > "Standard DS3 v2 (4 vcpus, 14 GiB memory)". > > The only relevant upstream commit in this area (as far as I can see) is: > > https://lore.kernel.org/linux-hyperv/1bb599ee-fe28-409d-b430-2fc086268936@l… > > The comment regarding avoiding races at start adds a bit more weight behind this > hunch, though it's only a hunch as I am most definitely nowhere near an expert > in this area. > > -- Package-specific info: > > [ 19.625535] BUG: kernel NULL pointer dereference, address: 00000000000000a0 > [ 19.628874] #PF: supervisor read access in kernel mode > [ 19.630841] #PF: error_code(0x0000) - not-present page > [ 19.632788] PGD 0 P4D 0 > [ 19.633905] Oops: Oops: 0000 [#1] PREEMPT SMP PTI > [ 19.635586] CPU: 3 UID: 0 PID: 0 Comm: swapper/3 Not tainted 6.12.57+deb13-amd64 #1 Debian 6.12.57-1 > [ 19.640216] Hardware name: Microsoft Corporation Virtual Machine/Virtual Machine, BIOS Hyper-V UEFI Release v4.1 09/28/2024 > [ 19.644514] RIP: 0010:hv_uio_channel_cb+0xd/0x20 [uio_hv_generic] > [ 19.646994] Code: 02 00 00 5b 5d e9 53 98 69 e9 0f 1f 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 f3 0f 1e fa 0f 1f 44 00 00 48 8b 47 10 <48> 8b b8 a0 00 00 00 f0 83 44 24 fc 00 e9 51 6f fa ff 90 90 90 90 > [ 19.654377] RSP: 0018:ffffb15ac01a4fa8 EFLAGS: 00010046 > [ 19.656385] RAX: 0000000000000000 RBX: 0000000000000015 RCX: 0000000000000015 > [ 19.659240] RDX: 0000000000000001 RSI: ffffffffffffffff RDI: ffff8ff69c759400 > [ 19.662168] RBP: ffff8ff548790200 R08: ffff8ff548790200 R09: 00fca75150b080e9 > [ 19.665239] R10: 0000000000000000 R11: ffffb15ac01a4ff8 R12: ffff8ff871dc1480 > [ 19.668193] R13: ffff8ff69c759400 R14: ffff8ff69c7596a0 R15: ffffffffc106e160 > [ 19.671106] FS: 0000000000000000(0000) GS:ffff8ff871d80000(0000) knlGS:0000000000000000 > [ 19.674281] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 > [ 19.676533] CR2: 00000000000000a0 CR3: 0000000100ba6003 CR4: 00000000003706f0 > [ 19.679385] Call Trace: > [ 19.680361] <IRQ> > [ 19.681181] vmbus_isr+0x1a5/0x210 [hv_vmbus] > [ 19.682916] __sysvec_hyperv_callback+0x32/0x60 > [ 19.684991] sysvec_hyperv_callback+0x6c/0x90 > [ 19.686665] </IRQ> > [ 19.687509] <TASK> > [ 19.688366] asm_sysvec_hyperv_callback+0x1a/0x20 > [ 19.690262] RIP: 0010:pv_native_safe_halt+0xf/0x20 > [ 19.692067] Code: 09 e9 c5 08 01 00 0f 1f 44 00 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 f3 0f 1e fa 66 90 0f 00 2d e5 3b 31 00 fb f4 <c3> cc cc cc cc 66 66 2e 0f 1f 84 00 00 00 00 00 90 90 90 90 90 90 > [ 19.699119] RSP: 0018:ffffb15ac0103ed8 EFLAGS: 00000246 > [ 19.701412] RAX: 0000000000000003 RBX: ffff8ff5403b1fc0 RCX: ffff8ff54c64ce30 > [ 19.704328] RDX: 0000000000000000 RSI: 0000000000000003 RDI: 000000000001f894 > [ 19.706910] RBP: 0000000000000003 R08: 000000000bb760d9 R09: 00fca75150b080e9 > [ 19.709762] R10: 0000000000000003 R11: 0000000000000001 R12: 0000000000000000 > [ 19.712510] R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 > [ 19.715173] default_idle+0x9/0x20 > [ 19.716846] default_idle_call+0x29/0x100 > [ 19.718623] do_idle+0x1fe/0x240 > [ 19.720045] cpu_startup_entry+0x29/0x30 > [ 19.721595] start_secondary+0x11e/0x140 > [ 19.723080] common_startup_64+0x13e/0x141 > [ 19.725222] </TASK> > [ 19.726387] Modules linked in: isofs cdrom uio_hv_generic uio binfmt_misc intel_rapl_msr intel_rapl_common intel_uncore_frequency_common isst_if_mbox_msr isst_if_common rpcrdma skx_edac_common nfit sunrpc libnvdimm crct10dif_pclmul ghash_clmulni_intel sha512_ssse3 sha256_ssse3 rdma_ucm ib_iser sha1_ssse3 rdma_cm aesni_intel iw_cm gf128mul crypto_simd libiscsi cryptd ib_umad ib_ipoib scsi_transport_iscsi ib_cm rapl sg hv_utils hv_balloon evdev pcspkr joydev mpls_router ip_tunnel ramoops configfs pstore_blk efi_pstore pstore_zone nfnetlink vsock_loopback vmw_vsock_virtio_transport_common hv_sock vmw_vsock_vmci_transport vsock vmw_vmci efivarfs ip_tables x_tables autofs4 overlay squashfs dm_verity dm_bufio reed_solomon dm_mod loop ext4 crc16 mbcache jbd2 crc32c_generic mlx5_ib ib_uverbs ib_core mlx5_core mlxfw pci_hyperv pci_hyperv_intf hyperv_drm drm_shmem_helper sd_mod drm_kms_helper hv_storvsc scsi_transport_fc drm scsi_mod hid_generic hid_hyperv hid serio_raw hv_netvsc hyperv_keyboard scsi_common hv_vmbus > [ 19.726466] crc32_pclmul crc32c_intel > [ 19.765771] CR2: 00000000000000a0 > [ 19.767524] ---[ end trace 0000000000000000 ]--- > [ 19.800433] RIP: 0010:hv_uio_channel_cb+0xd/0x20 [uio_hv_generic] > [ 19.803170] Code: 02 00 00 5b 5d e9 53 98 69 e9 0f 1f 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 f3 0f 1e fa 0f 1f 44 00 00 48 8b 47 10 <48> 8b b8 a0 00 00 00 f0 83 44 24 fc 00 e9 51 6f fa ff 90 90 90 90 > [ 19.811041] RSP: 0018:ffffb15ac01a4fa8 EFLAGS: 00010046 > [ 19.813466] RAX: 0000000000000000 RBX: 0000000000000015 RCX: 0000000000000015 > [ 19.816504] RDX: 0000000000000001 RSI: ffffffffffffffff RDI: ffff8ff69c759400 > [ 19.819484] RBP: ffff8ff548790200 R08: ffff8ff548790200 R09: 00fca75150b080e9 > [ 19.822625] R10: 0000000000000000 R11: ffffb15ac01a4ff8 R12: ffff8ff871dc1480 > [ 19.825569] R13: ffff8ff69c759400 R14: ffff8ff69c7596a0 R15: ffffffffc106e160 > [ 19.828804] FS: 0000000000000000(0000) GS:ffff8ff871d80000(0000) knlGS:0000000000000000 > [ 19.832214] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 > [ 19.834709] CR2: 00000000000000a0 CR3: 0000000100ba6003 CR4: 00000000003706f0 > [ 19.837976] Kernel panic - not syncing: Fatal exception in interrupt > [ 19.841825] Kernel Offset: 0x28a00000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff) > [ 19.896620] ---[ end Kernel panic - not syncing: Fatal exception in interrupt ]--- > > > lspci output: > > Collected from a system that is not crashing (6.12.41+deb13-amd64 #1 SMP PREEMPT_DYNAMIC Debian 6.12.41-1 (2025-08-12) x86_64 GNU/Linux)... > > $ sudo lspci -v > 2f22:00:02.0 Ethernet controller: Mellanox Technologies MT27710 Family [ConnectX-4 Lx Virtual Function] (rev 80) > Subsystem: Mellanox Technologies Device 0190 > Physical Slot: 3 > Flags: bus master, fast devsel, latency 0, NUMA node 0 > Memory at fe0100000 (64-bit, prefetchable) [size=1M] > Capabilities: [60] Express Endpoint, IntMsgNum 0 > Capabilities: [9c] MSI-X: Enable+ Count=8 Masked- > Kernel driver in use: mlx5_core > Kernel modules: mlx5_core > > 52f7:00:02.0 Ethernet controller: Mellanox Technologies MT27710 Family [ConnectX-4 Lx Virtual Function] (rev 80) > Subsystem: Mellanox Technologies Device 0190 > Physical Slot: 2 > Flags: bus master, fast devsel, latency 0, NUMA node 0 > Memory at fe0000000 (64-bit, prefetchable) [size=1M] > Capabilities: [60] Express Endpoint, IntMsgNum 0 > Capabilities: [9c] MSI-X: Enable+ Count=8 Masked- > Kernel driver in use: mlx5_core > Kernel modules: mlx5_core > > 7852:00:02.0 Ethernet controller: Mellanox Technologies MT27710 Family [ConnectX-4 Lx Virtual Function] (rev 80) > Subsystem: Mellanox Technologies Device 0190 > Physical Slot: 4 > Flags: bus master, fast devsel, latency 0, NUMA node 0 > Memory at fe0200000 (64-bit, prefetchable) [size=1M] > Capabilities: [60] Express Endpoint, IntMsgNum 0 > Capabilities: [9c] MSI-X: Enable+ Count=8 Masked- > Kernel driver in use: mlx5_core > Kernel modules: mlx5_core > > dmidecode output: > > $ sudo dmidecode > # dmidecode 3.6 > Getting SMBIOS data from sysfs. > SMBIOS 3.1.0 present. > Table at 0x3FF82000. > > Handle 0x0000, DMI type 0, 26 bytes > BIOS Information > Vendor: Microsoft Corporation > Version: Hyper-V UEFI Release v4.1 > Release Date: 05/13/2024 > ROM Size: 64 kB > Characteristics: > BIOS characteristics not supported > ACPI is supported > Targeted content distribution is supported > UEFI is supported > System is a virtual machine > BIOS Revision: 4.1 > > Handle 0x0001, DMI type 1, 27 bytes > System Information > Manufacturer: Microsoft Corporation > Product Name: Virtual Machine > Version: Hyper-V UEFI Release v4.1 > Serial Number: 0000-0010-5437-9499-5225-4477-46 > UUID: 925315af-4af4-4d42-915a-1516b5a1fe5c > Wake-up Type: Power Switch > SKU Number: None > Family: Virtual Machine > > Handle 0x0002, DMI type 3, 24 bytes > Chassis Information > Manufacturer: Microsoft Corporation > Type: Desktop > Lock: Not Present > Version: Hyper-V UEFI Release v4.1 > Serial Number: 2466-9316-1078-9783-6078-7718-80 > Asset Tag: 7783-7084-3265-9085-8269-3286-77 > Boot-up State: Safe > Power Supply State: Safe > Thermal State: Safe > Security Status: Unknown > OEM Information: 0x00000000 > Height: Unspecified > Number Of Power Cords: Unspecified > Contained Elements: 0 > SKU Number: Virtual Machine > > Handle 0x0003, DMI type 2, 17 bytes > Base Board Information > Manufacturer: Microsoft Corporation > Product Name: Virtual Machine > Version: Hyper-V UEFI Release v4.1 > Serial Number: 0000-0010-4737-0707-0684-2660-76 > Asset Tag: None > Features: > Board is a hosting board > Location In Chassis: Virtual Machine > Chassis Handle: 0x0002 > Type: Motherboard > Contained Object Handles: 0 > > Handle 0x0004, DMI type 4, 48 bytes > Processor Information > Socket Designation: None > Type: Central Processor > Family: Unknown > Manufacturer: None > ID: 00 00 00 00 00 00 00 00 > Version: None > Voltage: Unknown > External Clock: Unknown > Max Speed: Unknown > Current Speed: Unknown > Status: Unpopulated > Upgrade: Other > L1 Cache Handle: Not Provided > L2 Cache Handle: Not Provided > L3 Cache Handle: Not Provided > Serial Number: None > Asset Tag: None > Part Number: None > Core Count: 4 > Core Enabled: 4 > Thread Count: 1 > Characteristics: None > > Handle 0x0005, DMI type 11, 5 bytes > OEM Strings > String 1: [MS_VM_CERT/SHA1/9b80ca0d5dd061ec9da4e494f4c3fd1196270c22] > String 2: None > String 3: To be filled by OEM > > Handle 0x0006, DMI type 16, 23 bytes > Physical Memory Array > Location: System Board Or Motherboard > Use: System Memory > Error Correction Type: None > Maximum Capacity: 0 bytes > Error Information Handle: Not Provided > Number Of Devices: 3 > > Handle 0x0007, DMI type 17, 92 bytes > Memory Device > Array Handle: 0x0006 > Error Information Handle: Not Provided > Total Width: Unknown > Data Width: Unknown > Size: 26 MB > Form Factor: Unknown > Set: None > Locator: M0001 > Bank Locator: None > Type: Unknown > Type Detail: Unknown > Speed: Unknown > Manufacturer: Microsoft Corporation > Serial Number: None > Asset Tag: None > Part Number: None > Rank: Unknown > Configured Memory Speed: Unknown > Minimum Voltage: Unknown > Maximum Voltage: Unknown > Configured Voltage: Unknown > Memory Technology: <OUT OF SPEC> > Memory Operating Mode Capability: None > Firmware Version: Not Specified > Module Manufacturer ID: Unknown > Module Product ID: Unknown > Memory Subsystem Controller Manufacturer ID: Unknown > Memory Subsystem Controller Product ID: Unknown > Non-Volatile Size: None > Volatile Size: None > Cache Size: None > Logical Size: None > > Handle 0x0008, DMI type 19, 31 bytes > Memory Array Mapped Address > Starting Address: 0x00000000000 > Ending Address: 0x00001A003FF > Range Size: 26625 kB > Physical Array Handle: 0x0006 > Partition Width: 0 > > Handle 0x0009, DMI type 20, 35 bytes > Memory Device Mapped Address > Starting Address: 0x00000000000 > Ending Address: 0x00001A003FF > Range Size: 26625 kB > Physical Device Handle: 0x0007 > Memory Array Mapped Address Handle: 0x0008 > Partition Row Position: Unknown > > Handle 0x000A, DMI type 17, 92 bytes > Memory Device > Array Handle: 0x0006 > Error Information Handle: Not Provided > Total Width: Unknown > Data Width: Unknown > Size: 948 MB > Form Factor: Unknown > Set: None > Locator: M0002 > Bank Locator: None > Type: Unknown > Type Detail: Unknown > Speed: Unknown > Manufacturer: Microsoft Corporation > Serial Number: None > Asset Tag: None > Part Number: None > Rank: Unknown > Configured Memory Speed: Unknown > Minimum Voltage: Unknown > Maximum Voltage: Unknown > Configured Voltage: Unknown > Memory Technology: <OUT OF SPEC> > Memory Operating Mode Capability: None > Firmware Version: Not Specified > Module Manufacturer ID: Unknown > Module Product ID: Unknown > Memory Subsystem Controller Manufacturer ID: Unknown > Memory Subsystem Controller Product ID: Unknown > Non-Volatile Size: None > Volatile Size: None > Cache Size: None > Logical Size: None > > Handle 0x000B, DMI type 19, 31 bytes > Memory Array Mapped Address > Starting Address: 0x00004C00000 > Ending Address: 0x000400003FF > Range Size: 970753 kB > Physical Array Handle: 0x0006 > Partition Width: 0 > > Handle 0x000C, DMI type 20, 35 bytes > Memory Device Mapped Address > Starting Address: 0x00004C00000 > Ending Address: 0x000400003FF > Range Size: 970753 kB > Physical Device Handle: 0x000A > Memory Array Mapped Address Handle: 0x000B > Partition Row Position: Unknown > > Handle 0x000D, DMI type 17, 92 bytes > Memory Device > Array Handle: 0x0006 > Error Information Handle: Not Provided > Total Width: Unknown > Data Width: Unknown > Size: 13 GB > Form Factor: Unknown > Set: None > Locator: M0003 > Bank Locator: None > Type: Unknown > Type Detail: Unknown > Speed: Unknown > Manufacturer: Microsoft Corporation > Serial Number: None > Asset Tag: None > Part Number: None > Rank: Unknown > Configured Memory Speed: Unknown > Minimum Voltage: Unknown > Maximum Voltage: Unknown > Configured Voltage: Unknown > Memory Technology: <OUT OF SPEC> > Memory Operating Mode Capability: None > Firmware Version: Not Specified > Module Manufacturer ID: Unknown > Module Product ID: Unknown > Memory Subsystem Controller Manufacturer ID: Unknown > Memory Subsystem Controller Product ID: Unknown > Non-Volatile Size: None > Volatile Size: None > Cache Size: None > Logical Size: None > > Handle 0x000E, DMI type 19, 31 bytes > Memory Array Mapped Address > Starting Address: 0x00100000000 > Ending Address: 0x004400003FF > Range Size: 13 GB > Physical Array Handle: 0x0006 > Partition Width: 0 > > Handle 0x000F, DMI type 20, 35 bytes > Memory Device Mapped Address > Starting Address: 0x00100000000 > Ending Address: 0x004400003FF > Range Size: 13 GB > Physical Device Handle: 0x000D > Memory Array Mapped Address Handle: 0x000E > Partition Row Position: Unknown > > Handle 0x0010, DMI type 32, 11 bytes > System Boot Information > Status: No errors detected > > Handle 0xFEFF, DMI type 127, 4 bytes > End Of Table The offending commit appers to be the backport of b15b7d2a1b09 ("uio_hv_generic: Let userspace take care of interrupt mask") for 6.12.y. Peter confirmed that reverting this commit on top of 6.12.57-1 as packaged in Debian resolves indeed the issue. Interestingly the issue is *not* seen with 6.17.7 based kernel in Debian. #regzbot introduced: 37bd91f22794dc05436130d6983302cb90ecfe7e #regzbot monitor: https://bugs.debian.org/1120602 Thank you already! Regards, Salvatore

8 hours, 50 minutes

3
6
0 0

[PATCH printk v2 0/2] Fix reported suspend failures

by John Ogness

This is v2 of a series to address multiple reports [0][1] (+ 2 offlist) of suspend failing when NBCON console drivers are in use. With the help of NXP and NVIDIA we were able to isolate the problem and verify the fix. v1 is here [2]. The first NBCON drivers appeared in 6.13, so currently there is no LTS kernel that requires this series. But it should go into 6.17.x and 6.18. The changes since v1: - For printk_trigger_flush() add support for all flush types that are available. This will prevent printk_trigger_flush() from trying to inappropriately queue irq_work after this series is applied. - Add WARN_ON_ONCE() to the printk irq_work queueing functions in case they are called when irq_work is blocked. There should never be (and currently are no) such callers, but these functions are externally available. John Ogness [0] https://lore.kernel.org/lkml/80b020fc-c18a-4da4-b222-16da1cab2f4c@nvidia.com [1] https://lore.kernel.org/lkml/DB9PR04MB8429E7DDF2D93C2695DE401D92C4A@DB9PR04… [2] https://lore.kernel.org/lkml/20251111144328.887159-1-john.ogness@linutronix… John Ogness (2): printk: Allow printk_trigger_flush() to flush all types printk: Avoid scheduling irq_work on suspend kernel/printk/internal.h | 8 ++-- kernel/printk/nbcon.c | 9 ++++- kernel/printk/printk.c | 81 ++++++++++++++++++++++++++++++++-------- 3 files changed, 78 insertions(+), 20 deletions(-) base-commit: e9a6fb0bcdd7609be6969112f3fbfcce3b1d4a7c -- 2.47.3

8 hours, 59 minutes

6
14
0 0

FAILED: patch "[PATCH] xfs: fix various problems in xfs_atomic_write_cow_iomap_begin" failed to apply to 6.17-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.17-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-6.17.y git checkout FETCH_HEAD git cherry-pick -x 8d7bba1e8314013ecc817a91624104ceb9352ddc # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025110942-language-suspect-13bc@gregkh' --subject-prefix 'PATCH 6.17.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 8d7bba1e8314013ecc817a91624104ceb9352ddc Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" <djwong(a)kernel.org> Date: Tue, 4 Nov 2025 16:15:38 -0800 Subject: [PATCH] xfs: fix various problems in xfs_atomic_write_cow_iomap_begin I think there are several things wrong with this function: A) xfs_bmapi_write can return a much larger unwritten mapping than what the caller asked for. We convert part of that range to written, but return the entire written mapping to iomap even though that's inaccurate. B) The arguments to xfs_reflink_convert_cow_locked are wrong -- an unwritten mapping could be *smaller* than the write range (or even the hole range). In this case, we convert too much file range to written state because we then return a smaller mapping to iomap. C) It doesn't handle delalloc mappings. This I covered in the patch that I already sent to the list. D) Reassigning count_fsb to handle the hole means that if the second cmap lookup attempt succeeds (due to racing with someone else) we trim the mapping more than is strictly necessary. The changing meaning of count_fsb makes this harder to notice. E) The tracepoint is kinda wrong because @length is mutated. That makes it harder to chase the data flows through this function because you can't just grep on the pos/bytecount strings. F) We don't actually check that the br_state = XFS_EXT_NORM assignment is accurate, i.e that the cow fork actually contains a written mapping for the range we're interested in G) Somewhat inadequate documentation of why we need to xfs_trim_extent so aggressively in this function. H) Not sure why xfs_iomap_end_fsb is used here, the vfs already clamped the write range to s_maxbytes. Fix these issues, and then the atomic writes regressions in generic/760, generic/617, generic/091, generic/263, and generic/521 all go away for me. Cc: stable(a)vger.kernel.org # v6.16 Fixes: bd1d2c21d5d249 ("xfs: add xfs_atomic_write_cow_iomap_begin()") Signed-off-by: Darrick J. Wong <djwong(a)kernel.org> Reviewed-by: John Garry <john.g.garry(a)oracle.com> Signed-off-by: Carlos Maiolino <cem(a)kernel.org> diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 788bfdce608a..490e12cb99be 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -1091,6 +1091,29 @@ const struct iomap_ops xfs_zoned_direct_write_iomap_ops = { }; #endif /* CONFIG_XFS_RT */ +#ifdef DEBUG +static void +xfs_check_atomic_cow_conversion( + struct xfs_inode *ip, + xfs_fileoff_t offset_fsb, + xfs_filblks_t count_fsb, + const struct xfs_bmbt_irec *cmap) +{ + struct xfs_iext_cursor icur; + struct xfs_bmbt_irec cmap2 = { }; + + if (xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &cmap2)) + xfs_trim_extent(&cmap2, offset_fsb, count_fsb); + + ASSERT(cmap2.br_startoff == cmap->br_startoff); + ASSERT(cmap2.br_blockcount == cmap->br_blockcount); + ASSERT(cmap2.br_startblock == cmap->br_startblock); + ASSERT(cmap2.br_state == cmap->br_state); +} +#else +# define xfs_check_atomic_cow_conversion(...) ((void)0) +#endif + static int xfs_atomic_write_cow_iomap_begin( struct inode *inode, @@ -1102,9 +1125,10 @@ xfs_atomic_write_cow_iomap_begin( { struct xfs_inode *ip = XFS_I(inode); struct xfs_mount *mp = ip->i_mount; - const xfs_fileoff_t offset_fsb = XFS_B_TO_FSBT(mp, offset); - xfs_fileoff_t end_fsb = xfs_iomap_end_fsb(mp, offset, length); - xfs_filblks_t count_fsb = end_fsb - offset_fsb; + const xfs_fileoff_t offset_fsb = XFS_B_TO_FSBT(mp, offset); + const xfs_fileoff_t end_fsb = XFS_B_TO_FSB(mp, offset + length); + const xfs_filblks_t count_fsb = end_fsb - offset_fsb; + xfs_filblks_t hole_count_fsb; int nmaps = 1; xfs_filblks_t resaligned; struct xfs_bmbt_irec cmap; @@ -1143,14 +1167,20 @@ xfs_atomic_write_cow_iomap_begin( if (cmap.br_startoff <= offset_fsb) { if (isnullstartblock(cmap.br_startblock)) goto convert_delay; + + /* + * cmap could extend outside the write range due to previous + * speculative preallocations. We must trim cmap to the write + * range because the cow fork treats written mappings to mean + * "write in progress". + */ xfs_trim_extent(&cmap, offset_fsb, count_fsb); goto found; } - end_fsb = cmap.br_startoff; - count_fsb = end_fsb - offset_fsb; + hole_count_fsb = cmap.br_startoff - offset_fsb; - resaligned = xfs_aligned_fsb_count(offset_fsb, count_fsb, + resaligned = xfs_aligned_fsb_count(offset_fsb, hole_count_fsb, xfs_get_cowextsz_hint(ip)); xfs_iunlock(ip, XFS_ILOCK_EXCL); @@ -1186,7 +1216,7 @@ xfs_atomic_write_cow_iomap_begin( * atomic writes to that same range will be aligned (and don't require * this COW-based method). */ - error = xfs_bmapi_write(tp, ip, offset_fsb, count_fsb, + error = xfs_bmapi_write(tp, ip, offset_fsb, hole_count_fsb, XFS_BMAPI_COWFORK | XFS_BMAPI_PREALLOC | XFS_BMAPI_EXTSZALIGN, 0, &cmap, &nmaps); if (error) { @@ -1199,17 +1229,26 @@ xfs_atomic_write_cow_iomap_begin( if (error) goto out_unlock; + /* + * cmap could map more blocks than the range we passed into bmapi_write + * because of EXTSZALIGN or adjacent pre-existing unwritten mappings + * that were merged. Trim cmap to the original write range so that we + * don't convert more than we were asked to do for this write. + */ + xfs_trim_extent(&cmap, offset_fsb, count_fsb); + found: if (cmap.br_state != XFS_EXT_NORM) { - error = xfs_reflink_convert_cow_locked(ip, offset_fsb, - count_fsb); + error = xfs_reflink_convert_cow_locked(ip, cmap.br_startoff, + cmap.br_blockcount); if (error) goto out_unlock; cmap.br_state = XFS_EXT_NORM; + xfs_check_atomic_cow_conversion(ip, offset_fsb, count_fsb, + &cmap); } - length = XFS_FSB_TO_B(mp, cmap.br_startoff + cmap.br_blockcount); - trace_xfs_iomap_found(ip, offset, length - offset, XFS_COW_FORK, &cmap); + trace_xfs_iomap_found(ip, offset, length, XFS_COW_FORK, &cmap); seq = xfs_iomap_inode_sequence(ip, IOMAP_F_SHARED); xfs_iunlock(ip, XFS_ILOCK_EXCL); return xfs_bmbt_to_iomap(ip, iomap, &cmap, flags, IOMAP_F_SHARED, seq);

9 hours, 7 minutes

3
4
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror