From 1a229d8690a0f8951fc4aa8b76a7efab0d8de342 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 6 Nov 2023 12:06:54 +0100 Subject: Revert "usb: phy: add usb phy notify port status API" This reverts commit a08799cf17c22375752abfad3b4a2b34b3acb287. The recently added Realtek PHY drivers depend on the new port status notification mechanism which was built on the deprecated USB PHY implementation and devicetree binding. Specifically, using these PHYs would require describing the very same PHY using both the generic "phy" property and the deprecated "usb-phy" property which is clearly wrong. We should not be building new functionality on top of the legacy USB PHY implementation even if it is currently stuck in some kind of transitional limbo. Revert the new notification interface which is broken by design. Fixes: a08799cf17c2 ("usb: phy: add usb phy notify port status API") Cc: stable@vger.kernel.org # 6.6 Cc: Stanley Chang Signed-off-by: Johan Hovold Link: https://lore.kernel.org/r/20231106110654.31090-4-johan+linaro@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/phy.h | 13 ------------- 1 file changed, 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/phy.h b/include/linux/usb/phy.h index b513749582d7..e4de6bc1f69b 100644 --- a/include/linux/usb/phy.h +++ b/include/linux/usb/phy.h @@ -144,10 +144,6 @@ struct usb_phy { */ int (*set_wakeup)(struct usb_phy *x, bool enabled); - /* notify phy port status change */ - int (*notify_port_status)(struct usb_phy *x, int port, - u16 portstatus, u16 portchange); - /* notify phy connect status change */ int (*notify_connect)(struct usb_phy *x, enum usb_device_speed speed); @@ -320,15 +316,6 @@ usb_phy_set_wakeup(struct usb_phy *x, bool enabled) return 0; } -static inline int -usb_phy_notify_port_status(struct usb_phy *x, int port, u16 portstatus, u16 portchange) -{ - if (x && x->notify_port_status) - return x->notify_port_status(x, port, portstatus, portchange); - else - return 0; -} - static inline int usb_phy_notify_connect(struct usb_phy *x, enum usb_device_speed speed) { -- cgit v1.2.3 From 762321dab9a72760bf9aec48362f932717c9424d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 25 Oct 2023 16:10:17 +0200 Subject: filemap: add a per-mapping stable writes flag folio_wait_stable waits for writeback to finish before modifying the contents of a folio again, e.g. to support check summing of the data in the block integrity code. Currently this behavior is controlled by the SB_I_STABLE_WRITES flag on the super_block, which means it is uniform for the entire file system. This is wrong for the block device pseudofs which is shared by all block devices, or file systems that can use multiple devices like XFS witht the RT subvolume or btrfs (although btrfs currently reimplements folio_wait_stable anyway). Add a per-address_space AS_STABLE_WRITES flag to control the behavior in a more fine grained way. The existing SB_I_STABLE_WRITES is kept to initialize AS_STABLE_WRITES to the existing default which covers most cases. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20231025141020.192413-2-hch@lst.de Tested-by: Ilya Dryomov Reviewed-by: Matthew Wilcox (Oracle) Reviewed-by: Darrick J. Wong Signed-off-by: Christian Brauner --- fs/inode.c | 2 ++ include/linux/pagemap.h | 17 +++++++++++++++++ mm/page-writeback.c | 2 +- 3 files changed, 20 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/fs/inode.c b/fs/inode.c index edcd8a61975f..f238d987dec9 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -215,6 +215,8 @@ int inode_init_always(struct super_block *sb, struct inode *inode) lockdep_set_class_and_name(&mapping->invalidate_lock, &sb->s_type->invalidate_lock_key, "mapping.invalidate_lock"); + if (sb->s_iflags & SB_I_STABLE_WRITES) + mapping_set_stable_writes(mapping); inode->i_private = NULL; inode->i_mapping = mapping; INIT_HLIST_HEAD(&inode->i_dentry); /* buggered by rcu freeing */ diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index bcc1ea44b4e8..06142ff7f9ce 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -204,6 +204,8 @@ enum mapping_flags { AS_NO_WRITEBACK_TAGS = 5, AS_LARGE_FOLIO_SUPPORT = 6, AS_RELEASE_ALWAYS, /* Call ->release_folio(), even if no private data */ + AS_STABLE_WRITES, /* must wait for writeback before modifying + folio contents */ }; /** @@ -289,6 +291,21 @@ static inline void mapping_clear_release_always(struct address_space *mapping) clear_bit(AS_RELEASE_ALWAYS, &mapping->flags); } +static inline bool mapping_stable_writes(const struct address_space *mapping) +{ + return test_bit(AS_STABLE_WRITES, &mapping->flags); +} + +static inline void mapping_set_stable_writes(struct address_space *mapping) +{ + set_bit(AS_STABLE_WRITES, &mapping->flags); +} + +static inline void mapping_clear_stable_writes(struct address_space *mapping) +{ + clear_bit(AS_STABLE_WRITES, &mapping->flags); +} + static inline gfp_t mapping_gfp_mask(struct address_space * mapping) { return mapping->gfp_mask; diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 46f2f5d3d183..ee2fd6a6af40 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -3107,7 +3107,7 @@ EXPORT_SYMBOL_GPL(folio_wait_writeback_killable); */ void folio_wait_stable(struct folio *folio) { - if (folio_inode(folio)->i_sb->s_iflags & SB_I_STABLE_WRITES) + if (mapping_stable_writes(folio_mapping(folio))) folio_wait_writeback(folio); } EXPORT_SYMBOL_GPL(folio_wait_stable); -- cgit v1.2.3 From c96b8175522a2c52e297ee0a49827a668f95e1e8 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Mon, 20 Nov 2023 16:06:11 +0900 Subject: block: Remove blk_set_runtime_active() The function blk_set_runtime_active() is called only from blk_post_runtime_resume(), so there is no need for that function to be exported. Open-code this function directly in blk_post_runtime_resume() and remove it. Signed-off-by: Damien Le Moal Reviewed-by: Bart Van Assche Reviewed-by: Johannes Thumshirn Link: https://lore.kernel.org/r/20231120070611.33951-1-dlemoal@kernel.org Signed-off-by: Jens Axboe --- block/blk-pm.c | 33 +++++---------------------------- include/linux/blk-pm.h | 1 - 2 files changed, 5 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/block/blk-pm.c b/block/blk-pm.c index 6b72b2e03fc8..42e842074715 100644 --- a/block/blk-pm.c +++ b/block/blk-pm.c @@ -163,38 +163,15 @@ EXPORT_SYMBOL(blk_pre_runtime_resume); * @q: the queue of the device * * Description: - * For historical reasons, this routine merely calls blk_set_runtime_active() - * to do the real work of restarting the queue. It does this regardless of - * whether the device's runtime-resume succeeded; even if it failed the + * Restart the queue of a runtime suspended device. It does this regardless + * of whether the device's runtime-resume succeeded; even if it failed the * driver or error handler will need to communicate with the device. * * This function should be called near the end of the device's - * runtime_resume callback. + * runtime_resume callback to correct queue runtime PM status and re-enable + * peeking requests from the queue. */ void blk_post_runtime_resume(struct request_queue *q) -{ - blk_set_runtime_active(q); -} -EXPORT_SYMBOL(blk_post_runtime_resume); - -/** - * blk_set_runtime_active - Force runtime status of the queue to be active - * @q: the queue of the device - * - * If the device is left runtime suspended during system suspend the resume - * hook typically resumes the device and corrects runtime status - * accordingly. However, that does not affect the queue runtime PM status - * which is still "suspended". This prevents processing requests from the - * queue. - * - * This function can be used in driver's resume hook to correct queue - * runtime PM status and re-enable peeking requests from the queue. It - * should be called before first request is added to the queue. - * - * This function is also called by blk_post_runtime_resume() for - * runtime resumes. It does everything necessary to restart the queue. - */ -void blk_set_runtime_active(struct request_queue *q) { int old_status; @@ -211,4 +188,4 @@ void blk_set_runtime_active(struct request_queue *q) if (old_status != RPM_ACTIVE) blk_clear_pm_only(q); } -EXPORT_SYMBOL(blk_set_runtime_active); +EXPORT_SYMBOL(blk_post_runtime_resume); diff --git a/include/linux/blk-pm.h b/include/linux/blk-pm.h index 2580e05a8ab6..004b38a538ff 100644 --- a/include/linux/blk-pm.h +++ b/include/linux/blk-pm.h @@ -15,7 +15,6 @@ extern int blk_pre_runtime_suspend(struct request_queue *q); extern void blk_post_runtime_suspend(struct request_queue *q, int err); extern void blk_pre_runtime_resume(struct request_queue *q); extern void blk_post_runtime_resume(struct request_queue *q); -extern void blk_set_runtime_active(struct request_queue *q); #else static inline void blk_pm_runtime_init(struct request_queue *q, struct device *dev) {} -- cgit v1.2.3 From fc43e9c857b7aa55efba9398419b14d9e35dcc7d Mon Sep 17 00:00:00 2001 From: Charles Yi Date: Tue, 31 Oct 2023 12:32:39 +0800 Subject: HID: fix HID device resource race between HID core and debugging support hid_debug_events_release releases resources bound to the HID device instance. hid_device_release releases the underlying HID device instance potentially before hid_debug_events_release has completed releasing debug resources bound to the same HID device instance. Reference count to prevent the HID device instance from being torn down preemptively when HID debugging support is used. When count reaches zero, release core resources of HID device instance using hiddev_free. The crash: [ 120.728477][ T4396] kernel BUG at lib/list_debug.c:53! [ 120.728505][ T4396] Internal error: Oops - BUG: 0 [#1] PREEMPT SMP [ 120.739806][ T4396] Modules linked in: bcmdhd dhd_static_buf 8822cu pcie_mhi r8168 [ 120.747386][ T4396] CPU: 1 PID: 4396 Comm: hidt_bridge Not tainted 5.10.110 #257 [ 120.754771][ T4396] Hardware name: Rockchip RK3588 EVB4 LP4 V10 Board (DT) [ 120.761643][ T4396] pstate: 60400089 (nZCv daIf +PAN -UAO -TCO BTYPE=--) [ 120.768338][ T4396] pc : __list_del_entry_valid+0x98/0xac [ 120.773730][ T4396] lr : __list_del_entry_valid+0x98/0xac [ 120.779120][ T4396] sp : ffffffc01e62bb60 [ 120.783126][ T4396] x29: ffffffc01e62bb60 x28: ffffff818ce3a200 [ 120.789126][ T4396] x27: 0000000000000009 x26: 0000000000980000 [ 120.795126][ T4396] x25: ffffffc012431000 x24: ffffff802c6d4e00 [ 120.801125][ T4396] x23: ffffff8005c66f00 x22: ffffffc01183b5b8 [ 120.807125][ T4396] x21: ffffff819df2f100 x20: 0000000000000000 [ 120.813124][ T4396] x19: ffffff802c3f0700 x18: ffffffc01d2cd058 [ 120.819124][ T4396] x17: 0000000000000000 x16: 0000000000000000 [ 120.825124][ T4396] x15: 0000000000000004 x14: 0000000000003fff [ 120.831123][ T4396] x13: ffffffc012085588 x12: 0000000000000003 [ 120.837123][ T4396] x11: 00000000ffffbfff x10: 0000000000000003 [ 120.843123][ T4396] x9 : 455103d46b329300 x8 : 455103d46b329300 [ 120.849124][ T4396] x7 : 74707572726f6320 x6 : ffffffc0124b8cb5 [ 120.855124][ T4396] x5 : ffffffffffffffff x4 : 0000000000000000 [ 120.861123][ T4396] x3 : ffffffc011cf4f90 x2 : ffffff81fee7b948 [ 120.867122][ T4396] x1 : ffffffc011cf4f90 x0 : 0000000000000054 [ 120.873122][ T4396] Call trace: [ 120.876259][ T4396] __list_del_entry_valid+0x98/0xac [ 120.881304][ T4396] hid_debug_events_release+0x48/0x12c [ 120.886617][ T4396] full_proxy_release+0x50/0xbc [ 120.891323][ T4396] __fput+0xdc/0x238 [ 120.895075][ T4396] ____fput+0x14/0x24 [ 120.898911][ T4396] task_work_run+0x90/0x148 [ 120.903268][ T4396] do_exit+0x1bc/0x8a4 [ 120.907193][ T4396] do_group_exit+0x8c/0xa4 [ 120.911458][ T4396] get_signal+0x468/0x744 [ 120.915643][ T4396] do_signal+0x84/0x280 [ 120.919650][ T4396] do_notify_resume+0xd0/0x218 [ 120.924262][ T4396] work_pending+0xc/0x3f0 [ Rahul Rameshbabu : rework changelog ] Fixes: cd667ce24796 ("HID: use debugfs for events/reports dumping") Signed-off-by: Charles Yi Signed-off-by: Jiri Kosina --- drivers/hid/hid-core.c | 12 ++++++++++-- drivers/hid/hid-debug.c | 3 +++ include/linux/hid.h | 3 +++ 3 files changed, 16 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 8992e3c1e769..e0181218ad85 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -702,15 +702,22 @@ static void hid_close_report(struct hid_device *device) * Free a device structure, all reports, and all fields. */ -static void hid_device_release(struct device *dev) +void hiddev_free(struct kref *ref) { - struct hid_device *hid = to_hid_device(dev); + struct hid_device *hid = container_of(ref, struct hid_device, ref); hid_close_report(hid); kfree(hid->dev_rdesc); kfree(hid); } +static void hid_device_release(struct device *dev) +{ + struct hid_device *hid = to_hid_device(dev); + + kref_put(&hid->ref, hiddev_free); +} + /* * Fetch a report description item from the data stream. We support long * items, though they are not used yet. @@ -2846,6 +2853,7 @@ struct hid_device *hid_allocate_device(void) spin_lock_init(&hdev->debug_list_lock); sema_init(&hdev->driver_input_lock, 1); mutex_init(&hdev->ll_open_lock); + kref_init(&hdev->ref); hid_bpf_device_init(hdev); diff --git a/drivers/hid/hid-debug.c b/drivers/hid/hid-debug.c index e7ef1ea107c9..7dd83ec74f8a 100644 --- a/drivers/hid/hid-debug.c +++ b/drivers/hid/hid-debug.c @@ -1135,6 +1135,7 @@ static int hid_debug_events_open(struct inode *inode, struct file *file) goto out; } list->hdev = (struct hid_device *) inode->i_private; + kref_get(&list->hdev->ref); file->private_data = list; mutex_init(&list->read_mutex); @@ -1227,6 +1228,8 @@ static int hid_debug_events_release(struct inode *inode, struct file *file) list_del(&list->node); spin_unlock_irqrestore(&list->hdev->debug_list_lock, flags); kfifo_free(&list->hid_debug_fifo); + + kref_put(&list->hdev->ref, hiddev_free); kfree(list); return 0; diff --git a/include/linux/hid.h b/include/linux/hid.h index 5a8387a4a712..bf43f3ff6664 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -679,6 +679,7 @@ struct hid_device { /* device report descriptor */ struct list_head debug_list; spinlock_t debug_list_lock; wait_queue_head_t debug_wait; + struct kref ref; unsigned int id; /* system unique id */ @@ -687,6 +688,8 @@ struct hid_device { /* device report descriptor */ #endif /* CONFIG_BPF */ }; +void hiddev_free(struct kref *ref); + #define to_hid_device(pdev) \ container_of(pdev, struct hid_device, dev) -- cgit v1.2.3 From ef5828805842204dd0259ecfc132b5916c8a77ae Mon Sep 17 00:00:00 2001 From: Michael-CY Lee Date: Wed, 22 Nov 2023 11:02:37 +0800 Subject: wifi: avoid offset calculation on NULL pointer ieee80211_he_6ghz_oper() can be passed a NULL pointer and checks for that, but already did the calculation to inside of it before. Move it after the check. Signed-off-by: Michael-CY Lee Link: https://lore.kernel.org/r/20231122030237.31276-1-michael-cy.lee@mediatek.com [rewrite commit message] Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 958771bac9c0..c2ac9e9e7ee9 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2830,12 +2830,14 @@ ieee80211_he_oper_size(const u8 *he_oper_ie) static inline const struct ieee80211_he_6ghz_oper * ieee80211_he_6ghz_oper(const struct ieee80211_he_operation *he_oper) { - const u8 *ret = (const void *)&he_oper->optional; + const u8 *ret; u32 he_oper_params; if (!he_oper) return NULL; + ret = (const void *)&he_oper->optional; + he_oper_params = le32_to_cpu(he_oper->he_oper_params); if (!(he_oper_params & IEEE80211_HE_OPERATION_6GHZ_OP_INFO)) -- cgit v1.2.3 From 8c88a474357ead632b07c70bf7f119ace8c3b39e Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 24 Nov 2023 17:25:26 +0100 Subject: debugfs: add API to allow debugfs operations cancellation In some cases there might be longer-running hardware accesses in debugfs files, or attempts to acquire locks, and we want to still be able to quickly remove the files. Introduce a cancellations API to use inside the debugfs handler functions to be able to cancel such operations on a per-file basis. Acked-by: Greg Kroah-Hartman Signed-off-by: Johannes Berg --- fs/debugfs/file.c | 82 +++++++++++++++++++++++++++++++++++++++++++++++++ fs/debugfs/inode.c | 32 ++++++++++++++++++- fs/debugfs/internal.h | 5 +++ include/linux/debugfs.h | 19 ++++++++++++ 4 files changed, 137 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c index 3eff92450fd5..5568cdea3490 100644 --- a/fs/debugfs/file.c +++ b/fs/debugfs/file.c @@ -114,6 +114,8 @@ int debugfs_file_get(struct dentry *dentry) lockdep_init_map(&fsd->lockdep_map, fsd->lock_name ?: "debugfs", &fsd->key, 0); #endif + INIT_LIST_HEAD(&fsd->cancellations); + mutex_init(&fsd->cancellations_mtx); } /* @@ -156,6 +158,86 @@ void debugfs_file_put(struct dentry *dentry) } EXPORT_SYMBOL_GPL(debugfs_file_put); +/** + * debugfs_enter_cancellation - enter a debugfs cancellation + * @file: the file being accessed + * @cancellation: the cancellation object, the cancel callback + * inside of it must be initialized + * + * When a debugfs file is removed it needs to wait for all active + * operations to complete. However, the operation itself may need + * to wait for hardware or completion of some asynchronous process + * or similar. As such, it may need to be cancelled to avoid long + * waits or even deadlocks. + * + * This function can be used inside a debugfs handler that may + * need to be cancelled. As soon as this function is called, the + * cancellation's 'cancel' callback may be called, at which point + * the caller should proceed to call debugfs_leave_cancellation() + * and leave the debugfs handler function as soon as possible. + * Note that the 'cancel' callback is only ever called in the + * context of some kind of debugfs_remove(). + * + * This function must be paired with debugfs_leave_cancellation(). + */ +void debugfs_enter_cancellation(struct file *file, + struct debugfs_cancellation *cancellation) +{ + struct debugfs_fsdata *fsd; + struct dentry *dentry = F_DENTRY(file); + + INIT_LIST_HEAD(&cancellation->list); + + if (WARN_ON(!d_is_reg(dentry))) + return; + + if (WARN_ON(!cancellation->cancel)) + return; + + fsd = READ_ONCE(dentry->d_fsdata); + if (WARN_ON(!fsd || + ((unsigned long)fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT))) + return; + + mutex_lock(&fsd->cancellations_mtx); + list_add(&cancellation->list, &fsd->cancellations); + mutex_unlock(&fsd->cancellations_mtx); + + /* if we're already removing wake it up to cancel */ + if (d_unlinked(dentry)) + complete(&fsd->active_users_drained); +} +EXPORT_SYMBOL_GPL(debugfs_enter_cancellation); + +/** + * debugfs_leave_cancellation - leave cancellation section + * @file: the file being accessed + * @cancellation: the cancellation previously registered with + * debugfs_enter_cancellation() + * + * See the documentation of debugfs_enter_cancellation(). + */ +void debugfs_leave_cancellation(struct file *file, + struct debugfs_cancellation *cancellation) +{ + struct debugfs_fsdata *fsd; + struct dentry *dentry = F_DENTRY(file); + + if (WARN_ON(!d_is_reg(dentry))) + return; + + fsd = READ_ONCE(dentry->d_fsdata); + if (WARN_ON(!fsd || + ((unsigned long)fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT))) + return; + + mutex_lock(&fsd->cancellations_mtx); + if (!list_empty(&cancellation->list)) + list_del(&cancellation->list); + mutex_unlock(&fsd->cancellations_mtx); +} +EXPORT_SYMBOL_GPL(debugfs_leave_cancellation); + /* * Only permit access to world-readable files when the kernel is locked down. * We also need to exclude any file that has ways to write or alter it as root diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 80f4f000dcc1..d53c2860b03c 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -247,6 +247,8 @@ static void debugfs_release_dentry(struct dentry *dentry) lockdep_unregister_key(&fsd->key); kfree(fsd->lock_name); #endif + WARN_ON(!list_empty(&fsd->cancellations)); + mutex_destroy(&fsd->cancellations_mtx); } kfree(fsd); @@ -756,8 +758,36 @@ static void __debugfs_file_removed(struct dentry *dentry) lock_map_acquire(&fsd->lockdep_map); lock_map_release(&fsd->lockdep_map); - if (!refcount_dec_and_test(&fsd->active_users)) + /* if we hit zero, just wait for all to finish */ + if (!refcount_dec_and_test(&fsd->active_users)) { wait_for_completion(&fsd->active_users_drained); + return; + } + + /* if we didn't hit zero, try to cancel any we can */ + while (refcount_read(&fsd->active_users)) { + struct debugfs_cancellation *c; + + /* + * Lock the cancellations. Note that the cancellations + * structs are meant to be on the stack, so we need to + * ensure we either use them here or don't touch them, + * and debugfs_leave_cancellation() will wait for this + * to be finished processing before exiting one. It may + * of course win and remove the cancellation, but then + * chances are we never even got into this bit, we only + * do if the refcount isn't zero already. + */ + mutex_lock(&fsd->cancellations_mtx); + while ((c = list_first_entry_or_null(&fsd->cancellations, + typeof(*c), list))) { + list_del_init(&c->list); + c->cancel(dentry, c->cancel_data); + } + mutex_unlock(&fsd->cancellations_mtx); + + wait_for_completion(&fsd->active_users_drained); + } } static void remove_one(struct dentry *victim) diff --git a/fs/debugfs/internal.h b/fs/debugfs/internal.h index c7d61cfc97d2..0c4c68cf161f 100644 --- a/fs/debugfs/internal.h +++ b/fs/debugfs/internal.h @@ -8,6 +8,7 @@ #ifndef _DEBUGFS_INTERNAL_H_ #define _DEBUGFS_INTERNAL_H_ #include +#include struct file_operations; @@ -29,6 +30,10 @@ struct debugfs_fsdata { struct lock_class_key key; char *lock_name; #endif + + /* protect cancellations */ + struct mutex cancellations_mtx; + struct list_head cancellations; }; }; }; diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h index ea2d919fd9c7..c9c65b132c0f 100644 --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -171,6 +171,25 @@ ssize_t debugfs_write_file_bool(struct file *file, const char __user *user_buf, ssize_t debugfs_read_file_str(struct file *file, char __user *user_buf, size_t count, loff_t *ppos); +/** + * struct debugfs_cancellation - cancellation data + * @list: internal, for keeping track + * @cancel: callback to call + * @cancel_data: extra data for the callback to call + */ +struct debugfs_cancellation { + struct list_head list; + void (*cancel)(struct dentry *, void *); + void *cancel_data; +}; + +void __acquires(cancellation) +debugfs_enter_cancellation(struct file *file, + struct debugfs_cancellation *cancellation); +void __releases(cancellation) +debugfs_leave_cancellation(struct file *file, + struct debugfs_cancellation *cancellation); + #else #include -- cgit v1.2.3 From 8866730aed5100f06d3d965c22f1c61f74942541 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Tue, 28 Nov 2023 17:25:56 -0800 Subject: bpf, sockmap: af_unix stream sockets need to hold ref for pair sock AF_UNIX stream sockets are a paired socket. So sending on one of the pairs will lookup the paired socket as part of the send operation. It is possible however to put just one of the pairs in a BPF map. This currently increments the refcnt on the sock in the sockmap to ensure it is not free'd by the stack before sockmap cleans up its state and stops any skbs being sent/recv'd to that socket. But we missed a case. If the peer socket is closed it will be free'd by the stack. However, the paired socket can still be referenced from BPF sockmap side because we hold a reference there. Then if we are sending traffic through BPF sockmap to that socket it will try to dereference the free'd pair in its send logic creating a use after free. And following splat: [59.900375] BUG: KASAN: slab-use-after-free in sk_wake_async+0x31/0x1b0 [59.901211] Read of size 8 at addr ffff88811acbf060 by task kworker/1:2/954 [...] [59.905468] Call Trace: [59.905787] [59.906066] dump_stack_lvl+0x130/0x1d0 [59.908877] print_report+0x16f/0x740 [59.910629] kasan_report+0x118/0x160 [59.912576] sk_wake_async+0x31/0x1b0 [59.913554] sock_def_readable+0x156/0x2a0 [59.914060] unix_stream_sendmsg+0x3f9/0x12a0 [59.916398] sock_sendmsg+0x20e/0x250 [59.916854] skb_send_sock+0x236/0xac0 [59.920527] sk_psock_backlog+0x287/0xaa0 To fix let BPF sockmap hold a refcnt on both the socket in the sockmap and its paired socket. It wasn't obvious how to contain the fix to bpf_unix logic. The primarily problem with keeping this logic in bpf_unix was: In the sock close() we could handle the deref by having a close handler. But, when we are destroying the psock through a map delete operation we wouldn't have gotten any signal thorugh the proto struct other than it being replaced. If we do the deref from the proto replace its too early because we need to deref the sk_pair after the backlog worker has been stopped. Given all this it seems best to just cache it at the end of the psock and eat 8B for the af_unix and vsock users. Notice dgram sockets are OK because they handle locking already. Fixes: 94531cfcbe79 ("af_unix: Add unix_stream_proto for sockmap") Signed-off-by: John Fastabend Signed-off-by: Daniel Borkmann Reviewed-by: Jakub Sitnicki Link: https://lore.kernel.org/bpf/20231129012557.95371-2-john.fastabend@gmail.com --- include/linux/skmsg.h | 1 + include/net/af_unix.h | 1 + net/core/skmsg.c | 2 ++ net/unix/af_unix.c | 2 -- net/unix/unix_bpf.c | 5 +++++ 5 files changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index c1637515a8a4..c953b8c0d2f4 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -106,6 +106,7 @@ struct sk_psock { struct mutex work_mutex; struct sk_psock_work_state work_state; struct delayed_work work; + struct sock *sk_pair; struct rcu_work rwork; }; diff --git a/include/net/af_unix.h b/include/net/af_unix.h index 824c258143a3..49c4640027d8 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -75,6 +75,7 @@ struct unix_sock { }; #define unix_sk(ptr) container_of_const(ptr, struct unix_sock, sk) +#define unix_peer(sk) (unix_sk(sk)->peer) #define peer_wait peer_wq.wait diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 6c31eefbd777..93ecfceac1bc 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -826,6 +826,8 @@ static void sk_psock_destroy(struct work_struct *work) if (psock->sk_redir) sock_put(psock->sk_redir); + if (psock->sk_pair) + sock_put(psock->sk_pair); sock_put(psock->sk); kfree(psock); } diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index a357dc5f2404..ac1f2bc18fc9 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -213,8 +213,6 @@ static inline bool unix_secdata_eq(struct scm_cookie *scm, struct sk_buff *skb) } #endif /* CONFIG_SECURITY_NETWORK */ -#define unix_peer(sk) (unix_sk(sk)->peer) - static inline int unix_our_peer(struct sock *sk, struct sock *osk) { return unix_peer(osk) == sk; diff --git a/net/unix/unix_bpf.c b/net/unix/unix_bpf.c index 2f9d8271c6ec..7ea7c3a0d0d0 100644 --- a/net/unix/unix_bpf.c +++ b/net/unix/unix_bpf.c @@ -159,12 +159,17 @@ int unix_dgram_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool re int unix_stream_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore) { + struct sock *sk_pair; + if (restore) { sk->sk_write_space = psock->saved_write_space; sock_replace_proto(sk, psock->sk_proto); return 0; } + sk_pair = unix_peer(sk); + sock_hold(sk_pair); + psock->sk_pair = sk_pair; unix_stream_bpf_check_needs_rebuild(psock->sk_proto); sock_replace_proto(sk, &unix_stream_bpf_prot); return 0; -- cgit v1.2.3