July 2019 - Linux-stable-mirror

FAILED: patch "[PATCH] libnvdimm/bus: Stop holding nvdimm_bus_list_mutex over" failed to apply to 4.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.4-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>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From b70d31d054ee3a6fc1034b9d7fc0ae1e481aa018 Mon Sep 17 00:00:00 2001 From: Dan Williams <dan.j.williams(a)intel.com> Date: Wed, 17 Jul 2019 18:08:15 -0700 Subject: [PATCH] libnvdimm/bus: Stop holding nvdimm_bus_list_mutex over __nd_ioctl() In preparation for fixing a deadlock between wait_for_bus_probe_idle() and the nvdimm_bus_list_mutex arrange for __nd_ioctl() without nvdimm_bus_list_mutex held. This also unifies the 'dimm' and 'bus' level ioctls into a common nd_ioctl() preamble implementation. Marked for -stable as it is a pre-requisite for a follow-on fix. Cc: <stable(a)vger.kernel.org> Fixes: bf9bccc14c05 ("libnvdimm: pmem label sets and namespace instantiation") Cc: Vishal Verma <vishal.l.verma(a)intel.com> Tested-by: Jane Chu <jane.chu(a)oracle.com> Link: https://lore.kernel.org/r/156341209518.292348.7183897251740665198.stgit@dwi… Signed-off-by: Dan Williams <dan.j.williams(a)intel.com> diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c index a3180c28fb2b..a38572bf486b 100644 --- a/drivers/nvdimm/bus.c +++ b/drivers/nvdimm/bus.c @@ -73,7 +73,7 @@ static void nvdimm_bus_probe_end(struct nvdimm_bus *nvdimm_bus) { nvdimm_bus_lock(&nvdimm_bus->dev); if (--nvdimm_bus->probe_active == 0) - wake_up(&nvdimm_bus->probe_wait); + wake_up(&nvdimm_bus->wait); nvdimm_bus_unlock(&nvdimm_bus->dev); } @@ -341,7 +341,7 @@ struct nvdimm_bus *nvdimm_bus_register(struct device *parent, return NULL; INIT_LIST_HEAD(&nvdimm_bus->list); INIT_LIST_HEAD(&nvdimm_bus->mapping_list); - init_waitqueue_head(&nvdimm_bus->probe_wait); + init_waitqueue_head(&nvdimm_bus->wait); nvdimm_bus->id = ida_simple_get(&nd_ida, 0, 0, GFP_KERNEL); if (nvdimm_bus->id < 0) { kfree(nvdimm_bus); @@ -426,6 +426,9 @@ static int nd_bus_remove(struct device *dev) list_del_init(&nvdimm_bus->list); mutex_unlock(&nvdimm_bus_list_mutex); + wait_event(nvdimm_bus->wait, + atomic_read(&nvdimm_bus->ioctl_active) == 0); + nd_synchronize(); device_for_each_child(&nvdimm_bus->dev, NULL, child_unregister); @@ -885,7 +888,7 @@ void wait_nvdimm_bus_probe_idle(struct device *dev) if (nvdimm_bus->probe_active == 0) break; nvdimm_bus_unlock(&nvdimm_bus->dev); - wait_event(nvdimm_bus->probe_wait, + wait_event(nvdimm_bus->wait, nvdimm_bus->probe_active == 0); nvdimm_bus_lock(&nvdimm_bus->dev); } while (true); @@ -1130,24 +1133,10 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm, return rc; } -static long nd_ioctl(struct file *file, unsigned int cmd, unsigned long arg) -{ - long id = (long) file->private_data; - int rc = -ENXIO, ro; - struct nvdimm_bus *nvdimm_bus; - - ro = ((file->f_flags & O_ACCMODE) == O_RDONLY); - mutex_lock(&nvdimm_bus_list_mutex); - list_for_each_entry(nvdimm_bus, &nvdimm_bus_list, list) { - if (nvdimm_bus->id == id) { - rc = __nd_ioctl(nvdimm_bus, NULL, ro, cmd, arg); - break; - } - } - mutex_unlock(&nvdimm_bus_list_mutex); - - return rc; -} +enum nd_ioctl_mode { + BUS_IOCTL, + DIMM_IOCTL, +}; static int match_dimm(struct device *dev, void *data) { @@ -1162,31 +1151,62 @@ static int match_dimm(struct device *dev, void *data) return 0; } -static long nvdimm_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +static long nd_ioctl(struct file *file, unsigned int cmd, unsigned long arg, + enum nd_ioctl_mode mode) + { - int rc = -ENXIO, ro; - struct nvdimm_bus *nvdimm_bus; + struct nvdimm_bus *nvdimm_bus, *found = NULL; + long id = (long) file->private_data; + struct nvdimm *nvdimm = NULL; + int rc, ro; ro = ((file->f_flags & O_ACCMODE) == O_RDONLY); mutex_lock(&nvdimm_bus_list_mutex); list_for_each_entry(nvdimm_bus, &nvdimm_bus_list, list) { - struct device *dev = device_find_child(&nvdimm_bus->dev, - file->private_data, match_dimm); - struct nvdimm *nvdimm; - - if (!dev) - continue; + if (mode == DIMM_IOCTL) { + struct device *dev; + + dev = device_find_child(&nvdimm_bus->dev, + file->private_data, match_dimm); + if (!dev) + continue; + nvdimm = to_nvdimm(dev); + found = nvdimm_bus; + } else if (nvdimm_bus->id == id) { + found = nvdimm_bus; + } - nvdimm = to_nvdimm(dev); - rc = __nd_ioctl(nvdimm_bus, nvdimm, ro, cmd, arg); - put_device(dev); - break; + if (found) { + atomic_inc(&nvdimm_bus->ioctl_active); + break; + } } mutex_unlock(&nvdimm_bus_list_mutex); + if (!found) + return -ENXIO; + + nvdimm_bus = found; + rc = __nd_ioctl(nvdimm_bus, nvdimm, ro, cmd, arg); + + if (nvdimm) + put_device(&nvdimm->dev); + if (atomic_dec_and_test(&nvdimm_bus->ioctl_active)) + wake_up(&nvdimm_bus->wait); + return rc; } +static long bus_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + return nd_ioctl(file, cmd, arg, BUS_IOCTL); +} + +static long dimm_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + return nd_ioctl(file, cmd, arg, DIMM_IOCTL); +} + static int nd_open(struct inode *inode, struct file *file) { long minor = iminor(inode); @@ -1198,16 +1218,16 @@ static int nd_open(struct inode *inode, struct file *file) static const struct file_operations nvdimm_bus_fops = { .owner = THIS_MODULE, .open = nd_open, - .unlocked_ioctl = nd_ioctl, - .compat_ioctl = nd_ioctl, + .unlocked_ioctl = bus_ioctl, + .compat_ioctl = bus_ioctl, .llseek = noop_llseek, }; static const struct file_operations nvdimm_fops = { .owner = THIS_MODULE, .open = nd_open, - .unlocked_ioctl = nvdimm_ioctl, - .compat_ioctl = nvdimm_ioctl, + .unlocked_ioctl = dimm_ioctl, + .compat_ioctl = dimm_ioctl, .llseek = noop_llseek, }; diff --git a/drivers/nvdimm/nd-core.h b/drivers/nvdimm/nd-core.h index 391e88de3a29..6cd470547106 100644 --- a/drivers/nvdimm/nd-core.h +++ b/drivers/nvdimm/nd-core.h @@ -17,10 +17,11 @@ extern struct workqueue_struct *nvdimm_wq; struct nvdimm_bus { struct nvdimm_bus_descriptor *nd_desc; - wait_queue_head_t probe_wait; + wait_queue_head_t wait; struct list_head list; struct device dev; int id, probe_active; + atomic_t ioctl_active; struct list_head mapping_list; struct mutex reconfig_mutex; struct badrange badrange;

5 years, 5 months

1
0
0 0

FAILED: patch "[PATCH] libnvdimm/bus: Stop holding nvdimm_bus_list_mutex over" failed to apply to 4.14-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.14-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>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From b70d31d054ee3a6fc1034b9d7fc0ae1e481aa018 Mon Sep 17 00:00:00 2001 From: Dan Williams <dan.j.williams(a)intel.com> Date: Wed, 17 Jul 2019 18:08:15 -0700 Subject: [PATCH] libnvdimm/bus: Stop holding nvdimm_bus_list_mutex over __nd_ioctl() In preparation for fixing a deadlock between wait_for_bus_probe_idle() and the nvdimm_bus_list_mutex arrange for __nd_ioctl() without nvdimm_bus_list_mutex held. This also unifies the 'dimm' and 'bus' level ioctls into a common nd_ioctl() preamble implementation. Marked for -stable as it is a pre-requisite for a follow-on fix. Cc: <stable(a)vger.kernel.org> Fixes: bf9bccc14c05 ("libnvdimm: pmem label sets and namespace instantiation") Cc: Vishal Verma <vishal.l.verma(a)intel.com> Tested-by: Jane Chu <jane.chu(a)oracle.com> Link: https://lore.kernel.org/r/156341209518.292348.7183897251740665198.stgit@dwi… Signed-off-by: Dan Williams <dan.j.williams(a)intel.com> diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c index a3180c28fb2b..a38572bf486b 100644 --- a/drivers/nvdimm/bus.c +++ b/drivers/nvdimm/bus.c @@ -73,7 +73,7 @@ static void nvdimm_bus_probe_end(struct nvdimm_bus *nvdimm_bus) { nvdimm_bus_lock(&nvdimm_bus->dev); if (--nvdimm_bus->probe_active == 0) - wake_up(&nvdimm_bus->probe_wait); + wake_up(&nvdimm_bus->wait); nvdimm_bus_unlock(&nvdimm_bus->dev); } @@ -341,7 +341,7 @@ struct nvdimm_bus *nvdimm_bus_register(struct device *parent, return NULL; INIT_LIST_HEAD(&nvdimm_bus->list); INIT_LIST_HEAD(&nvdimm_bus->mapping_list); - init_waitqueue_head(&nvdimm_bus->probe_wait); + init_waitqueue_head(&nvdimm_bus->wait); nvdimm_bus->id = ida_simple_get(&nd_ida, 0, 0, GFP_KERNEL); if (nvdimm_bus->id < 0) { kfree(nvdimm_bus); @@ -426,6 +426,9 @@ static int nd_bus_remove(struct device *dev) list_del_init(&nvdimm_bus->list); mutex_unlock(&nvdimm_bus_list_mutex); + wait_event(nvdimm_bus->wait, + atomic_read(&nvdimm_bus->ioctl_active) == 0); + nd_synchronize(); device_for_each_child(&nvdimm_bus->dev, NULL, child_unregister); @@ -885,7 +888,7 @@ void wait_nvdimm_bus_probe_idle(struct device *dev) if (nvdimm_bus->probe_active == 0) break; nvdimm_bus_unlock(&nvdimm_bus->dev); - wait_event(nvdimm_bus->probe_wait, + wait_event(nvdimm_bus->wait, nvdimm_bus->probe_active == 0); nvdimm_bus_lock(&nvdimm_bus->dev); } while (true); @@ -1130,24 +1133,10 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm, return rc; } -static long nd_ioctl(struct file *file, unsigned int cmd, unsigned long arg) -{ - long id = (long) file->private_data; - int rc = -ENXIO, ro; - struct nvdimm_bus *nvdimm_bus; - - ro = ((file->f_flags & O_ACCMODE) == O_RDONLY); - mutex_lock(&nvdimm_bus_list_mutex); - list_for_each_entry(nvdimm_bus, &nvdimm_bus_list, list) { - if (nvdimm_bus->id == id) { - rc = __nd_ioctl(nvdimm_bus, NULL, ro, cmd, arg); - break; - } - } - mutex_unlock(&nvdimm_bus_list_mutex); - - return rc; -} +enum nd_ioctl_mode { + BUS_IOCTL, + DIMM_IOCTL, +}; static int match_dimm(struct device *dev, void *data) { @@ -1162,31 +1151,62 @@ static int match_dimm(struct device *dev, void *data) return 0; } -static long nvdimm_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +static long nd_ioctl(struct file *file, unsigned int cmd, unsigned long arg, + enum nd_ioctl_mode mode) + { - int rc = -ENXIO, ro; - struct nvdimm_bus *nvdimm_bus; + struct nvdimm_bus *nvdimm_bus, *found = NULL; + long id = (long) file->private_data; + struct nvdimm *nvdimm = NULL; + int rc, ro; ro = ((file->f_flags & O_ACCMODE) == O_RDONLY); mutex_lock(&nvdimm_bus_list_mutex); list_for_each_entry(nvdimm_bus, &nvdimm_bus_list, list) { - struct device *dev = device_find_child(&nvdimm_bus->dev, - file->private_data, match_dimm); - struct nvdimm *nvdimm; - - if (!dev) - continue; + if (mode == DIMM_IOCTL) { + struct device *dev; + + dev = device_find_child(&nvdimm_bus->dev, + file->private_data, match_dimm); + if (!dev) + continue; + nvdimm = to_nvdimm(dev); + found = nvdimm_bus; + } else if (nvdimm_bus->id == id) { + found = nvdimm_bus; + } - nvdimm = to_nvdimm(dev); - rc = __nd_ioctl(nvdimm_bus, nvdimm, ro, cmd, arg); - put_device(dev); - break; + if (found) { + atomic_inc(&nvdimm_bus->ioctl_active); + break; + } } mutex_unlock(&nvdimm_bus_list_mutex); + if (!found) + return -ENXIO; + + nvdimm_bus = found; + rc = __nd_ioctl(nvdimm_bus, nvdimm, ro, cmd, arg); + + if (nvdimm) + put_device(&nvdimm->dev); + if (atomic_dec_and_test(&nvdimm_bus->ioctl_active)) + wake_up(&nvdimm_bus->wait); + return rc; } +static long bus_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + return nd_ioctl(file, cmd, arg, BUS_IOCTL); +} + +static long dimm_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + return nd_ioctl(file, cmd, arg, DIMM_IOCTL); +} + static int nd_open(struct inode *inode, struct file *file) { long minor = iminor(inode); @@ -1198,16 +1218,16 @@ static int nd_open(struct inode *inode, struct file *file) static const struct file_operations nvdimm_bus_fops = { .owner = THIS_MODULE, .open = nd_open, - .unlocked_ioctl = nd_ioctl, - .compat_ioctl = nd_ioctl, + .unlocked_ioctl = bus_ioctl, + .compat_ioctl = bus_ioctl, .llseek = noop_llseek, }; static const struct file_operations nvdimm_fops = { .owner = THIS_MODULE, .open = nd_open, - .unlocked_ioctl = nvdimm_ioctl, - .compat_ioctl = nvdimm_ioctl, + .unlocked_ioctl = dimm_ioctl, + .compat_ioctl = dimm_ioctl, .llseek = noop_llseek, }; diff --git a/drivers/nvdimm/nd-core.h b/drivers/nvdimm/nd-core.h index 391e88de3a29..6cd470547106 100644 --- a/drivers/nvdimm/nd-core.h +++ b/drivers/nvdimm/nd-core.h @@ -17,10 +17,11 @@ extern struct workqueue_struct *nvdimm_wq; struct nvdimm_bus { struct nvdimm_bus_descriptor *nd_desc; - wait_queue_head_t probe_wait; + wait_queue_head_t wait; struct list_head list; struct device dev; int id, probe_active; + atomic_t ioctl_active; struct list_head mapping_list; struct mutex reconfig_mutex; struct badrange badrange;

5 years, 5 months

1
0
0 0

FAILED: patch "[PATCH] libnvdimm/bus: Prevent duplicate device_unregister() calls" failed to apply to 4.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.4-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>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 8aac0e2338916e273ccbd438a2b7a1e8c61749f5 Mon Sep 17 00:00:00 2001 From: Dan Williams <dan.j.williams(a)intel.com> Date: Wed, 17 Jul 2019 18:07:58 -0700 Subject: [PATCH] libnvdimm/bus: Prevent duplicate device_unregister() calls A multithreaded namespace creation/destruction stress test currently fails with signatures like the following: sysfs group 'power' not found for kobject 'dax1.1' RIP: 0010:sysfs_remove_group+0x76/0x80 Call Trace: device_del+0x73/0x370 device_unregister+0x16/0x50 nd_async_device_unregister+0x1e/0x30 [libnvdimm] async_run_entry_fn+0x39/0x160 process_one_work+0x23c/0x5e0 worker_thread+0x3c/0x390 BUG: kernel NULL pointer dereference, address: 0000000000000020 RIP: 0010:klist_put+0x1b/0x6c Call Trace: klist_del+0xe/0x10 device_del+0x8a/0x2c9 ? __switch_to_asm+0x34/0x70 ? __switch_to_asm+0x40/0x70 device_unregister+0x44/0x4f nd_async_device_unregister+0x22/0x2d [libnvdimm] async_run_entry_fn+0x47/0x15a process_one_work+0x1a2/0x2eb worker_thread+0x1b8/0x26e Use the kill_device() helper to atomically resolve the race of multiple threads issuing kill, device_unregister(), requests. Reported-by: Jane Chu <jane.chu(a)oracle.com> Reported-by: Erwin Tsaur <erwin.tsaur(a)oracle.com> Fixes: 4d88a97aa9e8 ("libnvdimm, nvdimm: dimm driver and base libnvdimm device-driver...") Cc: <stable(a)vger.kernel.org> Link: https://github.com/pmem/ndctl/issues/96 Tested-by: Tested-by: Jane Chu <jane.chu(a)oracle.com> Link: https://lore.kernel.org/r/156341207846.292348.10435719262819764054.stgit@dw… Signed-off-by: Dan Williams <dan.j.williams(a)intel.com> diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c index 2dca3034fee0..42713b210f51 100644 --- a/drivers/nvdimm/bus.c +++ b/drivers/nvdimm/bus.c @@ -547,13 +547,38 @@ EXPORT_SYMBOL(nd_device_register); void nd_device_unregister(struct device *dev, enum nd_async_mode mode) { + bool killed; + switch (mode) { case ND_ASYNC: + /* + * In the async case this is being triggered with the + * device lock held and the unregistration work needs to + * be moved out of line iff this is thread has won the + * race to schedule the deletion. + */ + if (!kill_device(dev)) + return; + get_device(dev); async_schedule_domain(nd_async_device_unregister, dev, &nd_async_domain); break; case ND_SYNC: + /* + * In the sync case the device is being unregistered due + * to a state change of the parent. Claim the kill state + * to synchronize against other unregistration requests, + * or otherwise let the async path handle it if the + * unregistration was already queued. + */ + device_lock(dev); + killed = kill_device(dev); + device_unlock(dev); + + if (!killed) + return; + nd_synchronize(); device_unregister(dev); break;

5 years, 5 months

1
0
0 0

FAILED: patch "[PATCH] libnvdimm/bus: Prevent duplicate device_unregister() calls" failed to apply to 4.9-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.9-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>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 8aac0e2338916e273ccbd438a2b7a1e8c61749f5 Mon Sep 17 00:00:00 2001 From: Dan Williams <dan.j.williams(a)intel.com> Date: Wed, 17 Jul 2019 18:07:58 -0700 Subject: [PATCH] libnvdimm/bus: Prevent duplicate device_unregister() calls A multithreaded namespace creation/destruction stress test currently fails with signatures like the following: sysfs group 'power' not found for kobject 'dax1.1' RIP: 0010:sysfs_remove_group+0x76/0x80 Call Trace: device_del+0x73/0x370 device_unregister+0x16/0x50 nd_async_device_unregister+0x1e/0x30 [libnvdimm] async_run_entry_fn+0x39/0x160 process_one_work+0x23c/0x5e0 worker_thread+0x3c/0x390 BUG: kernel NULL pointer dereference, address: 0000000000000020 RIP: 0010:klist_put+0x1b/0x6c Call Trace: klist_del+0xe/0x10 device_del+0x8a/0x2c9 ? __switch_to_asm+0x34/0x70 ? __switch_to_asm+0x40/0x70 device_unregister+0x44/0x4f nd_async_device_unregister+0x22/0x2d [libnvdimm] async_run_entry_fn+0x47/0x15a process_one_work+0x1a2/0x2eb worker_thread+0x1b8/0x26e Use the kill_device() helper to atomically resolve the race of multiple threads issuing kill, device_unregister(), requests. Reported-by: Jane Chu <jane.chu(a)oracle.com> Reported-by: Erwin Tsaur <erwin.tsaur(a)oracle.com> Fixes: 4d88a97aa9e8 ("libnvdimm, nvdimm: dimm driver and base libnvdimm device-driver...") Cc: <stable(a)vger.kernel.org> Link: https://github.com/pmem/ndctl/issues/96 Tested-by: Tested-by: Jane Chu <jane.chu(a)oracle.com> Link: https://lore.kernel.org/r/156341207846.292348.10435719262819764054.stgit@dw… Signed-off-by: Dan Williams <dan.j.williams(a)intel.com> diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c index 2dca3034fee0..42713b210f51 100644 --- a/drivers/nvdimm/bus.c +++ b/drivers/nvdimm/bus.c @@ -547,13 +547,38 @@ EXPORT_SYMBOL(nd_device_register); void nd_device_unregister(struct device *dev, enum nd_async_mode mode) { + bool killed; + switch (mode) { case ND_ASYNC: + /* + * In the async case this is being triggered with the + * device lock held and the unregistration work needs to + * be moved out of line iff this is thread has won the + * race to schedule the deletion. + */ + if (!kill_device(dev)) + return; + get_device(dev); async_schedule_domain(nd_async_device_unregister, dev, &nd_async_domain); break; case ND_SYNC: + /* + * In the sync case the device is being unregistered due + * to a state change of the parent. Claim the kill state + * to synchronize against other unregistration requests, + * or otherwise let the async path handle it if the + * unregistration was already queued. + */ + device_lock(dev); + killed = kill_device(dev); + device_unlock(dev); + + if (!killed) + return; + nd_synchronize(); device_unregister(dev); break;

5 years, 5 months

1
0
0 0

FAILED: patch "[PATCH] libnvdimm/bus: Prevent duplicate device_unregister() calls" failed to apply to 4.14-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.14-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>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 8aac0e2338916e273ccbd438a2b7a1e8c61749f5 Mon Sep 17 00:00:00 2001 From: Dan Williams <dan.j.williams(a)intel.com> Date: Wed, 17 Jul 2019 18:07:58 -0700 Subject: [PATCH] libnvdimm/bus: Prevent duplicate device_unregister() calls A multithreaded namespace creation/destruction stress test currently fails with signatures like the following: sysfs group 'power' not found for kobject 'dax1.1' RIP: 0010:sysfs_remove_group+0x76/0x80 Call Trace: device_del+0x73/0x370 device_unregister+0x16/0x50 nd_async_device_unregister+0x1e/0x30 [libnvdimm] async_run_entry_fn+0x39/0x160 process_one_work+0x23c/0x5e0 worker_thread+0x3c/0x390 BUG: kernel NULL pointer dereference, address: 0000000000000020 RIP: 0010:klist_put+0x1b/0x6c Call Trace: klist_del+0xe/0x10 device_del+0x8a/0x2c9 ? __switch_to_asm+0x34/0x70 ? __switch_to_asm+0x40/0x70 device_unregister+0x44/0x4f nd_async_device_unregister+0x22/0x2d [libnvdimm] async_run_entry_fn+0x47/0x15a process_one_work+0x1a2/0x2eb worker_thread+0x1b8/0x26e Use the kill_device() helper to atomically resolve the race of multiple threads issuing kill, device_unregister(), requests. Reported-by: Jane Chu <jane.chu(a)oracle.com> Reported-by: Erwin Tsaur <erwin.tsaur(a)oracle.com> Fixes: 4d88a97aa9e8 ("libnvdimm, nvdimm: dimm driver and base libnvdimm device-driver...") Cc: <stable(a)vger.kernel.org> Link: https://github.com/pmem/ndctl/issues/96 Tested-by: Tested-by: Jane Chu <jane.chu(a)oracle.com> Link: https://lore.kernel.org/r/156341207846.292348.10435719262819764054.stgit@dw… Signed-off-by: Dan Williams <dan.j.williams(a)intel.com> diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c index 2dca3034fee0..42713b210f51 100644 --- a/drivers/nvdimm/bus.c +++ b/drivers/nvdimm/bus.c @@ -547,13 +547,38 @@ EXPORT_SYMBOL(nd_device_register); void nd_device_unregister(struct device *dev, enum nd_async_mode mode) { + bool killed; + switch (mode) { case ND_ASYNC: + /* + * In the async case this is being triggered with the + * device lock held and the unregistration work needs to + * be moved out of line iff this is thread has won the + * race to schedule the deletion. + */ + if (!kill_device(dev)) + return; + get_device(dev); async_schedule_domain(nd_async_device_unregister, dev, &nd_async_domain); break; case ND_SYNC: + /* + * In the sync case the device is being unregistered due + * to a state change of the parent. Claim the kill state + * to synchronize against other unregistration requests, + * or otherwise let the async path handle it if the + * unregistration was already queued. + */ + device_lock(dev); + killed = kill_device(dev); + device_unlock(dev); + + if (!killed) + return; + nd_synchronize(); device_unregister(dev); break;

5 years, 5 months

1
0
0 0

FAILED: patch "[PATCH] libnvdimm/bus: Prevent duplicate device_unregister() calls" failed to apply to 4.19-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.19-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>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 8aac0e2338916e273ccbd438a2b7a1e8c61749f5 Mon Sep 17 00:00:00 2001 From: Dan Williams <dan.j.williams(a)intel.com> Date: Wed, 17 Jul 2019 18:07:58 -0700 Subject: [PATCH] libnvdimm/bus: Prevent duplicate device_unregister() calls A multithreaded namespace creation/destruction stress test currently fails with signatures like the following: sysfs group 'power' not found for kobject 'dax1.1' RIP: 0010:sysfs_remove_group+0x76/0x80 Call Trace: device_del+0x73/0x370 device_unregister+0x16/0x50 nd_async_device_unregister+0x1e/0x30 [libnvdimm] async_run_entry_fn+0x39/0x160 process_one_work+0x23c/0x5e0 worker_thread+0x3c/0x390 BUG: kernel NULL pointer dereference, address: 0000000000000020 RIP: 0010:klist_put+0x1b/0x6c Call Trace: klist_del+0xe/0x10 device_del+0x8a/0x2c9 ? __switch_to_asm+0x34/0x70 ? __switch_to_asm+0x40/0x70 device_unregister+0x44/0x4f nd_async_device_unregister+0x22/0x2d [libnvdimm] async_run_entry_fn+0x47/0x15a process_one_work+0x1a2/0x2eb worker_thread+0x1b8/0x26e Use the kill_device() helper to atomically resolve the race of multiple threads issuing kill, device_unregister(), requests. Reported-by: Jane Chu <jane.chu(a)oracle.com> Reported-by: Erwin Tsaur <erwin.tsaur(a)oracle.com> Fixes: 4d88a97aa9e8 ("libnvdimm, nvdimm: dimm driver and base libnvdimm device-driver...") Cc: <stable(a)vger.kernel.org> Link: https://github.com/pmem/ndctl/issues/96 Tested-by: Tested-by: Jane Chu <jane.chu(a)oracle.com> Link: https://lore.kernel.org/r/156341207846.292348.10435719262819764054.stgit@dw… Signed-off-by: Dan Williams <dan.j.williams(a)intel.com> diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c index 2dca3034fee0..42713b210f51 100644 --- a/drivers/nvdimm/bus.c +++ b/drivers/nvdimm/bus.c @@ -547,13 +547,38 @@ EXPORT_SYMBOL(nd_device_register); void nd_device_unregister(struct device *dev, enum nd_async_mode mode) { + bool killed; + switch (mode) { case ND_ASYNC: + /* + * In the async case this is being triggered with the + * device lock held and the unregistration work needs to + * be moved out of line iff this is thread has won the + * race to schedule the deletion. + */ + if (!kill_device(dev)) + return; + get_device(dev); async_schedule_domain(nd_async_device_unregister, dev, &nd_async_domain); break; case ND_SYNC: + /* + * In the sync case the device is being unregistered due + * to a state change of the parent. Claim the kill state + * to synchronize against other unregistration requests, + * or otherwise let the async path handle it if the + * unregistration was already queued. + */ + device_lock(dev); + killed = kill_device(dev); + device_unlock(dev); + + if (!killed) + return; + nd_synchronize(); device_unregister(dev); break;

5 years, 5 months

1
0
0 0

FAILED: patch "[PATCH] drivers/base: Introduce kill_device()" failed to apply to 4.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.4-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>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 00289cd87676e14913d2d8492d1ce05c4baafdae Mon Sep 17 00:00:00 2001 From: Dan Williams <dan.j.williams(a)intel.com> Date: Wed, 17 Jul 2019 18:07:53 -0700 Subject: [PATCH] drivers/base: Introduce kill_device() The libnvdimm subsystem arranges for devices to be destroyed as a result of a sysfs operation. Since device_unregister() cannot be called from an actively running sysfs attribute of the same device libnvdimm arranges for device_unregister() to be performed in an out-of-line async context. The driver core maintains a 'dead' state for coordinating its own racing async registration / de-registration requests. Rather than add local 'dead' state tracking infrastructure to libnvdimm device objects, export the existing state tracking via a new kill_device() helper. The kill_device() helper simply marks the device as dead, i.e. that it is on its way to device_del(), or returns that the device was already dead. This can be used in advance of calling device_unregister() for subsystems like libnvdimm that might need to handle multiple user threads racing to delete a device. This refactoring does not change any behavior, but it is a pre-requisite for follow-on fixes and therefore marked for -stable. Cc: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Cc: "Rafael J. Wysocki" <rafael(a)kernel.org> Fixes: 4d88a97aa9e8 ("libnvdimm, nvdimm: dimm driver and base libnvdimm device-driver...") Cc: <stable(a)vger.kernel.org> Tested-by: Jane Chu <jane.chu(a)oracle.com> Reviewed-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Link: https://lore.kernel.org/r/156341207332.292348.14959761496009347574.stgit@dw… Signed-off-by: Dan Williams <dan.j.williams(a)intel.com> diff --git a/drivers/base/core.c b/drivers/base/core.c index fd7511e04e62..eaf3aa0cb803 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -2211,6 +2211,24 @@ void put_device(struct device *dev) } EXPORT_SYMBOL_GPL(put_device); +bool kill_device(struct device *dev) +{ + /* + * Require the device lock and set the "dead" flag to guarantee that + * the update behavior is consistent with the other bitfields near + * it and that we cannot have an asynchronous probe routine trying + * to run while we are tearing out the bus/class/sysfs from + * underneath the device. + */ + lockdep_assert_held(&dev->mutex); + + if (dev->p->dead) + return false; + dev->p->dead = true; + return true; +} +EXPORT_SYMBOL_GPL(kill_device); + /** * device_del - delete device from system. * @dev: device. @@ -2230,15 +2248,8 @@ void device_del(struct device *dev) struct kobject *glue_dir = NULL; struct class_interface *class_intf; - /* - * Hold the device lock and set the "dead" flag to guarantee that - * the update behavior is consistent with the other bitfields near - * it and that we cannot have an asynchronous probe routine trying - * to run while we are tearing out the bus/class/sysfs from - * underneath the device. - */ device_lock(dev); - dev->p->dead = true; + kill_device(dev); device_unlock(dev); /* Notify clients of device removal. This call must come diff --git a/include/linux/device.h b/include/linux/device.h index e85264fb6616..0da5c67f6be1 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1373,6 +1373,7 @@ extern int (*platform_notify_remove)(struct device *dev); */ extern struct device *get_device(struct device *dev); extern void put_device(struct device *dev); +extern bool kill_device(struct device *dev); #ifdef CONFIG_DEVTMPFS extern int devtmpfs_create_node(struct device *dev);

5 years, 5 months

1
0
0 0

FAILED: patch "[PATCH] drivers/base: Introduce kill_device()" failed to apply to 4.14-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.14-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>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 00289cd87676e14913d2d8492d1ce05c4baafdae Mon Sep 17 00:00:00 2001 From: Dan Williams <dan.j.williams(a)intel.com> Date: Wed, 17 Jul 2019 18:07:53 -0700 Subject: [PATCH] drivers/base: Introduce kill_device() The libnvdimm subsystem arranges for devices to be destroyed as a result of a sysfs operation. Since device_unregister() cannot be called from an actively running sysfs attribute of the same device libnvdimm arranges for device_unregister() to be performed in an out-of-line async context. The driver core maintains a 'dead' state for coordinating its own racing async registration / de-registration requests. Rather than add local 'dead' state tracking infrastructure to libnvdimm device objects, export the existing state tracking via a new kill_device() helper. The kill_device() helper simply marks the device as dead, i.e. that it is on its way to device_del(), or returns that the device was already dead. This can be used in advance of calling device_unregister() for subsystems like libnvdimm that might need to handle multiple user threads racing to delete a device. This refactoring does not change any behavior, but it is a pre-requisite for follow-on fixes and therefore marked for -stable. Cc: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Cc: "Rafael J. Wysocki" <rafael(a)kernel.org> Fixes: 4d88a97aa9e8 ("libnvdimm, nvdimm: dimm driver and base libnvdimm device-driver...") Cc: <stable(a)vger.kernel.org> Tested-by: Jane Chu <jane.chu(a)oracle.com> Reviewed-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Link: https://lore.kernel.org/r/156341207332.292348.14959761496009347574.stgit@dw… Signed-off-by: Dan Williams <dan.j.williams(a)intel.com> diff --git a/drivers/base/core.c b/drivers/base/core.c index fd7511e04e62..eaf3aa0cb803 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -2211,6 +2211,24 @@ void put_device(struct device *dev) } EXPORT_SYMBOL_GPL(put_device); +bool kill_device(struct device *dev) +{ + /* + * Require the device lock and set the "dead" flag to guarantee that + * the update behavior is consistent with the other bitfields near + * it and that we cannot have an asynchronous probe routine trying + * to run while we are tearing out the bus/class/sysfs from + * underneath the device. + */ + lockdep_assert_held(&dev->mutex); + + if (dev->p->dead) + return false; + dev->p->dead = true; + return true; +} +EXPORT_SYMBOL_GPL(kill_device); + /** * device_del - delete device from system. * @dev: device. @@ -2230,15 +2248,8 @@ void device_del(struct device *dev) struct kobject *glue_dir = NULL; struct class_interface *class_intf; - /* - * Hold the device lock and set the "dead" flag to guarantee that - * the update behavior is consistent with the other bitfields near - * it and that we cannot have an asynchronous probe routine trying - * to run while we are tearing out the bus/class/sysfs from - * underneath the device. - */ device_lock(dev); - dev->p->dead = true; + kill_device(dev); device_unlock(dev); /* Notify clients of device removal. This call must come diff --git a/include/linux/device.h b/include/linux/device.h index e85264fb6616..0da5c67f6be1 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1373,6 +1373,7 @@ extern int (*platform_notify_remove)(struct device *dev); */ extern struct device *get_device(struct device *dev); extern void put_device(struct device *dev); +extern bool kill_device(struct device *dev); #ifdef CONFIG_DEVTMPFS extern int devtmpfs_create_node(struct device *dev);

5 years, 5 months

1
0
0 0

FAILED: patch "[PATCH] drivers/base: Introduce kill_device()" failed to apply to 4.9-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.9-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>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 00289cd87676e14913d2d8492d1ce05c4baafdae Mon Sep 17 00:00:00 2001 From: Dan Williams <dan.j.williams(a)intel.com> Date: Wed, 17 Jul 2019 18:07:53 -0700 Subject: [PATCH] drivers/base: Introduce kill_device() The libnvdimm subsystem arranges for devices to be destroyed as a result of a sysfs operation. Since device_unregister() cannot be called from an actively running sysfs attribute of the same device libnvdimm arranges for device_unregister() to be performed in an out-of-line async context. The driver core maintains a 'dead' state for coordinating its own racing async registration / de-registration requests. Rather than add local 'dead' state tracking infrastructure to libnvdimm device objects, export the existing state tracking via a new kill_device() helper. The kill_device() helper simply marks the device as dead, i.e. that it is on its way to device_del(), or returns that the device was already dead. This can be used in advance of calling device_unregister() for subsystems like libnvdimm that might need to handle multiple user threads racing to delete a device. This refactoring does not change any behavior, but it is a pre-requisite for follow-on fixes and therefore marked for -stable. Cc: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Cc: "Rafael J. Wysocki" <rafael(a)kernel.org> Fixes: 4d88a97aa9e8 ("libnvdimm, nvdimm: dimm driver and base libnvdimm device-driver...") Cc: <stable(a)vger.kernel.org> Tested-by: Jane Chu <jane.chu(a)oracle.com> Reviewed-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Link: https://lore.kernel.org/r/156341207332.292348.14959761496009347574.stgit@dw… Signed-off-by: Dan Williams <dan.j.williams(a)intel.com> diff --git a/drivers/base/core.c b/drivers/base/core.c index fd7511e04e62..eaf3aa0cb803 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -2211,6 +2211,24 @@ void put_device(struct device *dev) } EXPORT_SYMBOL_GPL(put_device); +bool kill_device(struct device *dev) +{ + /* + * Require the device lock and set the "dead" flag to guarantee that + * the update behavior is consistent with the other bitfields near + * it and that we cannot have an asynchronous probe routine trying + * to run while we are tearing out the bus/class/sysfs from + * underneath the device. + */ + lockdep_assert_held(&dev->mutex); + + if (dev->p->dead) + return false; + dev->p->dead = true; + return true; +} +EXPORT_SYMBOL_GPL(kill_device); + /** * device_del - delete device from system. * @dev: device. @@ -2230,15 +2248,8 @@ void device_del(struct device *dev) struct kobject *glue_dir = NULL; struct class_interface *class_intf; - /* - * Hold the device lock and set the "dead" flag to guarantee that - * the update behavior is consistent with the other bitfields near - * it and that we cannot have an asynchronous probe routine trying - * to run while we are tearing out the bus/class/sysfs from - * underneath the device. - */ device_lock(dev); - dev->p->dead = true; + kill_device(dev); device_unlock(dev); /* Notify clients of device removal. This call must come diff --git a/include/linux/device.h b/include/linux/device.h index e85264fb6616..0da5c67f6be1 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1373,6 +1373,7 @@ extern int (*platform_notify_remove)(struct device *dev); */ extern struct device *get_device(struct device *dev); extern void put_device(struct device *dev); +extern bool kill_device(struct device *dev); #ifdef CONFIG_DEVTMPFS extern int devtmpfs_create_node(struct device *dev);

5 years, 5 months

1
0
0 0

FAILED: patch "[PATCH] drivers/base: Introduce kill_device()" failed to apply to 4.19-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.19-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>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 00289cd87676e14913d2d8492d1ce05c4baafdae Mon Sep 17 00:00:00 2001 From: Dan Williams <dan.j.williams(a)intel.com> Date: Wed, 17 Jul 2019 18:07:53 -0700 Subject: [PATCH] drivers/base: Introduce kill_device() The libnvdimm subsystem arranges for devices to be destroyed as a result of a sysfs operation. Since device_unregister() cannot be called from an actively running sysfs attribute of the same device libnvdimm arranges for device_unregister() to be performed in an out-of-line async context. The driver core maintains a 'dead' state for coordinating its own racing async registration / de-registration requests. Rather than add local 'dead' state tracking infrastructure to libnvdimm device objects, export the existing state tracking via a new kill_device() helper. The kill_device() helper simply marks the device as dead, i.e. that it is on its way to device_del(), or returns that the device was already dead. This can be used in advance of calling device_unregister() for subsystems like libnvdimm that might need to handle multiple user threads racing to delete a device. This refactoring does not change any behavior, but it is a pre-requisite for follow-on fixes and therefore marked for -stable. Cc: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Cc: "Rafael J. Wysocki" <rafael(a)kernel.org> Fixes: 4d88a97aa9e8 ("libnvdimm, nvdimm: dimm driver and base libnvdimm device-driver...") Cc: <stable(a)vger.kernel.org> Tested-by: Jane Chu <jane.chu(a)oracle.com> Reviewed-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Link: https://lore.kernel.org/r/156341207332.292348.14959761496009347574.stgit@dw… Signed-off-by: Dan Williams <dan.j.williams(a)intel.com> diff --git a/drivers/base/core.c b/drivers/base/core.c index fd7511e04e62..eaf3aa0cb803 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -2211,6 +2211,24 @@ void put_device(struct device *dev) } EXPORT_SYMBOL_GPL(put_device); +bool kill_device(struct device *dev) +{ + /* + * Require the device lock and set the "dead" flag to guarantee that + * the update behavior is consistent with the other bitfields near + * it and that we cannot have an asynchronous probe routine trying + * to run while we are tearing out the bus/class/sysfs from + * underneath the device. + */ + lockdep_assert_held(&dev->mutex); + + if (dev->p->dead) + return false; + dev->p->dead = true; + return true; +} +EXPORT_SYMBOL_GPL(kill_device); + /** * device_del - delete device from system. * @dev: device. @@ -2230,15 +2248,8 @@ void device_del(struct device *dev) struct kobject *glue_dir = NULL; struct class_interface *class_intf; - /* - * Hold the device lock and set the "dead" flag to guarantee that - * the update behavior is consistent with the other bitfields near - * it and that we cannot have an asynchronous probe routine trying - * to run while we are tearing out the bus/class/sysfs from - * underneath the device. - */ device_lock(dev); - dev->p->dead = true; + kill_device(dev); device_unlock(dev); /* Notify clients of device removal. This call must come diff --git a/include/linux/device.h b/include/linux/device.h index e85264fb6616..0da5c67f6be1 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1373,6 +1373,7 @@ extern int (*platform_notify_remove)(struct device *dev); */ extern struct device *get_device(struct device *dev); extern void put_device(struct device *dev); +extern bool kill_device(struct device *dev); #ifdef CONFIG_DEVTMPFS extern int devtmpfs_create_node(struct device *dev);

5 years, 5 months

1
0
0 0

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror July 2019