February 2025 - Linux-stable-mirror

[PATCH] usb: dwc3: Set SUSPENDENABLE soon after phy init

by Thinh Nguyen

After phy initialization, some phy operations can only be executed while in lower P states. Ensure GUSB3PIPECTL.SUSPENDENABLE and GUSB2PHYCFG.SUSPHY are set soon after initialization to avoid blocking phy ops. Previously the SUSPENDENABLE bits are only set after the controller initialization, which may not happen right away if there's no gadget driver or xhci driver bound. Revise this to clear SUSPENDENABLE bits only when there's mode switching (change in GCTL.PRTCAPDIR). Fixes: 6d735722063a ("usb: dwc3: core: Prevent phy suspend during init") Cc: stable(a)vger.kernel.org Signed-off-by: Thinh Nguyen <Thinh.Nguyen(a)synopsys.com> --- drivers/usb/dwc3/core.c | 69 +++++++++++++++++++++++++---------------- drivers/usb/dwc3/core.h | 2 +- drivers/usb/dwc3/drd.c | 4 +-- 3 files changed, 45 insertions(+), 30 deletions(-) diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index dfa1b5fe48dc..87b4c04a868c 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -131,11 +131,24 @@ void dwc3_enable_susphy(struct dwc3 *dwc, bool enable) } } -void dwc3_set_prtcap(struct dwc3 *dwc, u32 mode) +void dwc3_set_prtcap(struct dwc3 *dwc, u32 mode, bool ignore_susphy) { + unsigned int hw_mode; u32 reg; reg = dwc3_readl(dwc->regs, DWC3_GCTL); + + /* + * For DRD controllers, GUSB3PIPECTL.SUSPENDENABLE and + * GUSB2PHYCFG.SUSPHY should be cleared during mode switching, + * and they can be set after core initialization. + */ + hw_mode = DWC3_GHWPARAMS0_MODE(dwc->hwparams.hwparams0); + if (hw_mode == DWC3_GHWPARAMS0_MODE_DRD && !ignore_susphy) { + if (DWC3_GCTL_PRTCAP(reg) != mode) + dwc3_enable_susphy(dwc, false); + } + reg &= ~(DWC3_GCTL_PRTCAPDIR(DWC3_GCTL_PRTCAP_OTG)); reg |= DWC3_GCTL_PRTCAPDIR(mode); dwc3_writel(dwc->regs, DWC3_GCTL, reg); @@ -216,7 +229,7 @@ static void __dwc3_set_mode(struct work_struct *work) spin_lock_irqsave(&dwc->lock, flags); - dwc3_set_prtcap(dwc, desired_dr_role); + dwc3_set_prtcap(dwc, desired_dr_role, false); spin_unlock_irqrestore(&dwc->lock, flags); @@ -658,16 +671,7 @@ static int dwc3_ss_phy_setup(struct dwc3 *dwc, int index) */ reg &= ~DWC3_GUSB3PIPECTL_UX_EXIT_PX; - /* - * Above DWC_usb3.0 1.94a, it is recommended to set - * DWC3_GUSB3PIPECTL_SUSPHY to '0' during coreConsultant configuration. - * So default value will be '0' when the core is reset. Application - * needs to set it to '1' after the core initialization is completed. - * - * Similarly for DRD controllers, GUSB3PIPECTL.SUSPENDENABLE must be - * cleared after power-on reset, and it can be set after core - * initialization. - */ + /* Ensure the GUSB3PIPECTL.SUSPENDENABLE is cleared prior to phy init. */ reg &= ~DWC3_GUSB3PIPECTL_SUSPHY; if (dwc->u2ss_inp3_quirk) @@ -747,15 +751,7 @@ static int dwc3_hs_phy_setup(struct dwc3 *dwc, int index) break; } - /* - * Above DWC_usb3.0 1.94a, it is recommended to set - * DWC3_GUSB2PHYCFG_SUSPHY to '0' during coreConsultant configuration. - * So default value will be '0' when the core is reset. Application - * needs to set it to '1' after the core initialization is completed. - * - * Similarly for DRD controllers, GUSB2PHYCFG.SUSPHY must be cleared - * after power-on reset, and it can be set after core initialization. - */ + /* Ensure the GUSB2PHYCFG.SUSPHY is cleared prior to phy init. */ reg &= ~DWC3_GUSB2PHYCFG_SUSPHY; if (dwc->dis_enblslpm_quirk) @@ -830,6 +826,25 @@ static int dwc3_phy_init(struct dwc3 *dwc) goto err_exit_usb3_phy; } + /* + * Above DWC_usb3.0 1.94a, it is recommended to set + * DWC3_GUSB3PIPECTL_SUSPHY and DWC3_GUSB2PHYCFG_SUSPHY to '0' during + * coreConsultant configuration. So default value will be '0' when the + * core is reset. Application needs to set it to '1' after the core + * initialization is completed. + * + * Certain phy requires to be in P0 power state during initialization. + * Make sure GUSB3PIPECTL.SUSPENDENABLE and GUSB2PHYCFG.SUSPHY are clear + * prior to phy init to maintain in the P0 state. + * + * After phy initialization, some phy operations can only be executed + * while in lower P states. Ensure GUSB3PIPECTL.SUSPENDENABLE and + * GUSB2PHYCFG.SUSPHY are set soon after initialization to avoid + * blocking phy ops. + */ + if (!DWC3_VER_IS_WITHIN(DWC3, ANY, 194A)) + dwc3_enable_susphy(dwc, true); + return 0; err_exit_usb3_phy: @@ -1588,7 +1603,7 @@ static int dwc3_core_init_mode(struct dwc3 *dwc) switch (dwc->dr_mode) { case USB_DR_MODE_PERIPHERAL: - dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_DEVICE); + dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_DEVICE, false); if (dwc->usb2_phy) otg_set_vbus(dwc->usb2_phy->otg, false); @@ -1600,7 +1615,7 @@ static int dwc3_core_init_mode(struct dwc3 *dwc) return dev_err_probe(dev, ret, "failed to initialize gadget\n"); break; case USB_DR_MODE_HOST: - dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_HOST); + dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_HOST, false); if (dwc->usb2_phy) otg_set_vbus(dwc->usb2_phy->otg, true); @@ -1645,7 +1660,7 @@ static void dwc3_core_exit_mode(struct dwc3 *dwc) } /* de-assert DRVVBUS for HOST and OTG mode */ - dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_DEVICE); + dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_DEVICE, true); } static void dwc3_get_software_properties(struct dwc3 *dwc) @@ -2457,7 +2472,7 @@ static int dwc3_resume_common(struct dwc3 *dwc, pm_message_t msg) if (ret) return ret; - dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_DEVICE); + dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_DEVICE, true); dwc3_gadget_resume(dwc); break; case DWC3_GCTL_PRTCAP_HOST: @@ -2465,7 +2480,7 @@ static int dwc3_resume_common(struct dwc3 *dwc, pm_message_t msg) ret = dwc3_core_init_for_resume(dwc); if (ret) return ret; - dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_HOST); + dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_HOST, true); break; } /* Restore GUSB2PHYCFG bits that were modified in suspend */ @@ -2494,7 +2509,7 @@ static int dwc3_resume_common(struct dwc3 *dwc, pm_message_t msg) if (ret) return ret; - dwc3_set_prtcap(dwc, dwc->current_dr_role); + dwc3_set_prtcap(dwc, dwc->current_dr_role, true); dwc3_otg_init(dwc); if (dwc->current_otg_role == DWC3_OTG_ROLE_HOST) { diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h index ac7c730f81ac..19ad5b6e1ede 100644 --- a/drivers/usb/dwc3/core.h +++ b/drivers/usb/dwc3/core.h @@ -1557,7 +1557,7 @@ struct dwc3_gadget_ep_cmd_params { #define DWC3_HAS_OTG BIT(3) /* prototypes */ -void dwc3_set_prtcap(struct dwc3 *dwc, u32 mode); +void dwc3_set_prtcap(struct dwc3 *dwc, u32 mode, bool ignore_susphy); void dwc3_set_mode(struct dwc3 *dwc, u32 mode); u32 dwc3_core_fifo_space(struct dwc3_ep *dep, u8 type); diff --git a/drivers/usb/dwc3/drd.c b/drivers/usb/dwc3/drd.c index d76ae676783c..7977860932b1 100644 --- a/drivers/usb/dwc3/drd.c +++ b/drivers/usb/dwc3/drd.c @@ -173,7 +173,7 @@ void dwc3_otg_init(struct dwc3 *dwc) * block "Initialize GCTL for OTG operation". */ /* GCTL.PrtCapDir=2'b11 */ - dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_OTG); + dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_OTG, true); /* GUSB2PHYCFG0.SusPHY=0 */ reg = dwc3_readl(dwc->regs, DWC3_GUSB2PHYCFG(0)); reg &= ~DWC3_GUSB2PHYCFG_SUSPHY; @@ -556,7 +556,7 @@ int dwc3_drd_init(struct dwc3 *dwc) dwc3_drd_update(dwc); } else { - dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_OTG); + dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_OTG, true); /* use OTG block to get ID event */ irq = dwc3_otg_get_irq(dwc); base-commit: 72deda0abee6e705ae71a93f69f55e33be5bca5c -- 2.28.0

6 hours, 1 minute

1
1
0 0

[PATCH v4 0/2] rust: lockdep: Fix soundness issue affecting LockClassKeys

by Mitchell Levy

This series is aimed at fixing a soundness issue with how dynamically allocated LockClassKeys are handled. Currently, LockClassKeys can be used without being Pin'd, which can break lockdep since it relies on address stability. Similarly, these keys are not automatically (de)registered with lockdep. At the suggestion of Alice Ryhl, this series includes a patch for -stable kernels that disables dynamically allocated keys. This prevents backported patches from using the unsound implementation. Currently, this series requires that all dynamically allocated LockClassKeys have a lifetime of 'static (i.e., they must be leaked after allocation). This is because Lock does not currently keep a reference to the LockClassKey, instead passing it to C via FFI. This causes a problem because the rust compiler would allow creating a 'static Lock with a 'a LockClassKey (with 'a < 'static) while C would expect the LockClassKey to live as long as the lock. This problem represents an avenue for future work. --- Changes in v4: - Expand the cover letter in the 2nd patch to explain why Pin is used despite being redundant at the moment (Thanks Benno Lossin). - Include a Fixes tag in the 1st patch (Thanks Miguel Ojeda). - Link to v3: https://lore.kernel.org/r/20250205-rust-lockdep-v3-0-5313e83a0bef@gmail.com Changes in v3: - Rebased on rust-next - Fixed clippy/compiler warninings (Thanks Boqun Feng) - Link to v2: https://lore.kernel.org/r/20241219-rust-lockdep-v2-0-f65308fbc5ca@gmail.com Changes in v2: - Dropped formatting change that's already fixed upstream (Thanks Dirk Behme). - Moved safety comment to the right point in the patch series (Thanks Dirk Behme and Boqun Feng). - Added an example of dynamic LockClassKey usage (Thanks Boqun Feng). - Link to v1: https://lore.kernel.org/r/20241004-rust-lockdep-v1-0-e9a5c45721fc@gmail.com Changes from RFC: - Split into two commits so that dynamically allocated LockClassKeys are removed from stable kernels. (Thanks Alice Ryhl) - Extract calls to C lockdep functions into helpers so things build properly when LOCKDEP=n. (Thanks Benno Lossin) - Remove extraneous `get_ref()` calls. (Thanks Benno Lossin) - Provide better documentation for `new_dynamic()`. (Thanks Benno Lossin) - Ran rustfmt to fix formatting and some extraneous changes. (Thanks Alice Ryhl and Benno Lossin) - Link to RFC: https://lore.kernel.org/r/20240905-rust-lockdep-v1-1-d2c9c21aa8b2@gmail.com --- Mitchell Levy (2): rust: lockdep: Remove support for dynamically allocated LockClassKeys rust: lockdep: Use Pin for all LockClassKey usages rust/helpers/helpers.c | 1 + rust/helpers/sync.c | 13 +++++++++ rust/kernel/sync.rs | 63 ++++++++++++++++++++++++++++++++++------- rust/kernel/sync/condvar.rs | 5 ++-- rust/kernel/sync/lock.rs | 9 ++---- rust/kernel/sync/lock/global.rs | 5 ++-- rust/kernel/sync/poll.rs | 2 +- rust/kernel/workqueue.rs | 2 +- 8 files changed, 77 insertions(+), 23 deletions(-) --- base-commit: beeb78d46249cab8b2b8359a2ce8fa5376b5ad2d change-id: 20240905-rust-lockdep-d3e30521c8ba Best regards, -- Mitchell Levy <levymitchell0(a)gmail.com>

9 hours, 56 minutes

2
2
0 0

[PATCH v1 2/2] mm/slab/kvfree_rcu: Switch to WQ_MEM_RECLAIM wq

by Uladzislau Rezki (Sony)

Currently kvfree_rcu() APIs use a system workqueue which is "system_unbound_wq" to driver RCU machinery to reclaim a memory. Recently, it has been noted that the following kernel warning can be observed: <snip> workqueue: WQ_MEM_RECLAIM nvme-wq:nvme_scan_work is flushing !WQ_MEM_RECLAIM events_unbound:kfree_rcu_work WARNING: CPU: 21 PID: 330 at kernel/workqueue.c:3719 check_flush_dependency+0x112/0x120 Modules linked in: intel_uncore_frequency(E) intel_uncore_frequency_common(E) skx_edac(E) ... CPU: 21 UID: 0 PID: 330 Comm: kworker/u144:6 Tainted: G E 6.13.2-0_g925d379822da #1 Hardware name: Wiwynn Twin Lakes MP/Twin Lakes Passive MP, BIOS YMM20 02/01/2023 Workqueue: nvme-wq nvme_scan_work RIP: 0010:check_flush_dependency+0x112/0x120 Code: 05 9a 40 14 02 01 48 81 c6 c0 00 00 00 48 8b 50 18 48 81 c7 c0 00 00 00 48 89 f9 48 ... RSP: 0018:ffffc90000df7bd8 EFLAGS: 00010082 RAX: 000000000000006a RBX: ffffffff81622390 RCX: 0000000000000027 RDX: 00000000fffeffff RSI: 000000000057ffa8 RDI: ffff88907f960c88 RBP: 0000000000000000 R08: ffffffff83068e50 R09: 000000000002fffd R10: 0000000000000004 R11: 0000000000000000 R12: ffff8881001a4400 R13: 0000000000000000 R14: ffff88907f420fb8 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff88907f940000(0000) knlGS:0000000000000000 CR2: 00007f60c3001000 CR3: 000000107d010005 CR4: 00000000007726f0 PKRU: 55555554 Call Trace: <TASK> ? __warn+0xa4/0x140 ? check_flush_dependency+0x112/0x120 ? report_bug+0xe1/0x140 ? check_flush_dependency+0x112/0x120 ? handle_bug+0x5e/0x90 ? exc_invalid_op+0x16/0x40 ? asm_exc_invalid_op+0x16/0x20 ? timer_recalc_next_expiry+0x190/0x190 ? check_flush_dependency+0x112/0x120 ? check_flush_dependency+0x112/0x120 __flush_work.llvm.1643880146586177030+0x174/0x2c0 flush_rcu_work+0x28/0x30 kvfree_rcu_barrier+0x12f/0x160 kmem_cache_destroy+0x18/0x120 bioset_exit+0x10c/0x150 disk_release.llvm.6740012984264378178+0x61/0xd0 device_release+0x4f/0x90 kobject_put+0x95/0x180 nvme_put_ns+0x23/0xc0 nvme_remove_invalid_namespaces+0xb3/0xd0 nvme_scan_work+0x342/0x490 process_scheduled_works+0x1a2/0x370 worker_thread+0x2ff/0x390 ? pwq_release_workfn+0x1e0/0x1e0 kthread+0xb1/0xe0 ? __kthread_parkme+0x70/0x70 ret_from_fork+0x30/0x40 ? __kthread_parkme+0x70/0x70 ret_from_fork_asm+0x11/0x20 </TASK> ---[ end trace 0000000000000000 ]--- <snip> To address this switch to use of independent WQ_MEM_RECLAIM workqueue, so the rules are not violated from workqueue framework point of view. Apart of that, since kvfree_rcu() does reclaim memory it is worth to go with WQ_MEM_RECLAIM type of wq because it is designed for this purpose. Cc: <stable(a)vger.kernel.org> Cc: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Cc: Keith Busch <kbusch(a)kernel.org> Closes: https://www.spinics.net/lists/kernel/msg5563270.html Fixes: 6c6c47b063b5 ("mm, slab: call kvfree_rcu_barrier() from kmem_cache_destroy()"), Reported-by: Keith Busch <kbusch(a)kernel.org> Signed-off-by: Uladzislau Rezki (Sony) <urezki(a)gmail.com> --- mm/slab_common.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/mm/slab_common.c b/mm/slab_common.c index 4030907b6b7d..4c9f0a87f733 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -1304,6 +1304,8 @@ module_param(rcu_min_cached_objs, int, 0444); static int rcu_delay_page_cache_fill_msec = 5000; module_param(rcu_delay_page_cache_fill_msec, int, 0444); +static struct workqueue_struct *rcu_reclaim_wq; + /* Maximum number of jiffies to wait before draining a batch. */ #define KFREE_DRAIN_JIFFIES (5 * HZ) #define KFREE_N_BATCHES 2 @@ -1632,10 +1634,10 @@ __schedule_delayed_monitor_work(struct kfree_rcu_cpu *krcp) if (delayed_work_pending(&krcp->monitor_work)) { delay_left = krcp->monitor_work.timer.expires - jiffies; if (delay < delay_left) - mod_delayed_work(system_unbound_wq, &krcp->monitor_work, delay); + mod_delayed_work(rcu_reclaim_wq, &krcp->monitor_work, delay); return; } - queue_delayed_work(system_unbound_wq, &krcp->monitor_work, delay); + queue_delayed_work(rcu_reclaim_wq, &krcp->monitor_work, delay); } static void @@ -1733,7 +1735,7 @@ kvfree_rcu_queue_batch(struct kfree_rcu_cpu *krcp) // "free channels", the batch can handle. Break // the loop since it is done with this CPU thus // queuing an RCU work is _always_ success here. - queued = queue_rcu_work(system_unbound_wq, &krwp->rcu_work); + queued = queue_rcu_work(rcu_reclaim_wq, &krwp->rcu_work); WARN_ON_ONCE(!queued); break; } @@ -1883,7 +1885,7 @@ run_page_cache_worker(struct kfree_rcu_cpu *krcp) if (rcu_scheduler_active == RCU_SCHEDULER_RUNNING && !atomic_xchg(&krcp->work_in_progress, 1)) { if (atomic_read(&krcp->backoff_page_cache_fill)) { - queue_delayed_work(system_unbound_wq, + queue_delayed_work(rcu_reclaim_wq, &krcp->page_cache_work, msecs_to_jiffies(rcu_delay_page_cache_fill_msec)); } else { @@ -2120,6 +2122,10 @@ void __init kvfree_rcu_init(void) int i, j; struct shrinker *kfree_rcu_shrinker; + rcu_reclaim_wq = alloc_workqueue("kvfree_rcu_reclaim", + WQ_UNBOUND | WQ_MEM_RECLAIM, 0); + WARN_ON(!rcu_reclaim_wq); + /* Clamp it to [0:100] seconds interval. */ if (rcu_delay_page_cache_fill_msec < 0 || rcu_delay_page_cache_fill_msec > 100 * MSEC_PER_SEC) { -- 2.39.5

12 hours, 40 minutes

4
3
0 0

[PATCH] mailbox: tegra-hsp: Add check for devm_kstrdup_const()

by Haoxiang Li

Add check for the return value of devm_kstrdup_const() in tegra_hsp_doorbell_create() to catch potential exception. Fixes: a54d03ed01b4 ("mailbox: tegra-hsp: use devm_kstrdup_const()") Cc: stable(a)vger.kernel.org Signed-off-by: Haoxiang Li <haoxiang_li2024(a)163.com> --- drivers/mailbox/tegra-hsp.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/mailbox/tegra-hsp.c b/drivers/mailbox/tegra-hsp.c index c1981f091bd1..773a1cf6d93d 100644 --- a/drivers/mailbox/tegra-hsp.c +++ b/drivers/mailbox/tegra-hsp.c @@ -285,6 +285,8 @@ tegra_hsp_doorbell_create(struct tegra_hsp *hsp, const char *name, db->channel.hsp = hsp; db->name = devm_kstrdup_const(hsp->dev, name, GFP_KERNEL); + if (!db->name) + return ERR_PTR(-ENOMEM); db->master = master; db->index = index; -- 2.25.1

13 hours, 8 minutes

3
2
0 0

[PATCH] media: uvcvideo: Fix deferred probing error

by Ricardo Ribalda

uvc_gpio_parse() can return -EPROBE_DEFER when the GPIOs it depends on have not yet been probed. This return code should be propagated to the caller of uvc_probe() to ensure that probing is retried when the required GPIOs become available. Currently, this error code is incorrectly converted to -ENODEV, causing some internal cameras to be ignored. This commit fixes this issue by propagating the -EPROBE_DEFER error. Cc: stable(a)vger.kernel.org Fixes: 2886477ff987 ("media: uvcvideo: Implement UVC_EXT_GPIO_UNIT") Signed-off-by: Ricardo Ribalda <ribalda(a)chromium.org> --- drivers/media/usb/uvc/uvc_driver.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/media/usb/uvc/uvc_driver.c b/drivers/media/usb/uvc/uvc_driver.c index a10d4f4d9f95..73a7f23b616c 100644 --- a/drivers/media/usb/uvc/uvc_driver.c +++ b/drivers/media/usb/uvc/uvc_driver.c @@ -2253,9 +2253,10 @@ static int uvc_probe(struct usb_interface *intf, } /* Parse the associated GPIOs. */ - if (uvc_gpio_parse(dev) < 0) { + ret = uvc_gpio_parse(dev); + if (ret < 0) { uvc_dbg(dev, PROBE, "Unable to parse UVC GPIOs\n"); - goto error; + goto error_retcode; } dev_info(&dev->udev->dev, "Found UVC %u.%02x device %s (%04x:%04x)\n", @@ -2328,9 +2329,11 @@ static int uvc_probe(struct usb_interface *intf, return 0; error: + ret = -ENODEV; +error_retcode: uvc_unregister_video(dev); kref_put(&dev->ref, uvc_delete); - return -ENODEV; + return ret; } static void uvc_disconnect(struct usb_interface *intf) --- base-commit: c4b7779abc6633677e6edb79e2809f4f61fde157 change-id: 20250129-uvc-eprobedefer-b5ebb4db63cc Best regards, -- Ricardo Ribalda <ribalda(a)chromium.org>

13 hours, 30 minutes

3
4
0 0

[PATCH v4 1/6] Revert "wifi: mt76: mt7925: Update mt7925_mcu_uni_[tx,rx]_ba for MLO"

by sean.wang＠kernel.org

From: Sean Wang <sean.wang(a)mediatek.com> For MLO, mac80211 will send the BA action for each link to the driver, so the driver does not need to handle it itself. Therefore, revert this patch. Fixes: e38a82d25b08 ("wifi: mt76: connac: Extend mt76_connac_mcu_uni_add_dev for MLO") Cc: stable(a)vger.kernel.org Signed-off-by: Ming Yen Hsieh <mingyen.hsieh(a)mediatek.com> Tested-by: Caleb Jorden <cjorden(a)gmail.com> Signed-off-by: Sean Wang <sean.wang(a)mediatek.com> --- v2: 1) generate the patch based on the latest mt76 tree 2) update the commit message v3: 1) fixed the merge conflict v4: 1) added tested-by tag --- .../net/wireless/mediatek/mt76/mt7925/main.c | 10 ++-- .../net/wireless/mediatek/mt76/mt7925/mcu.c | 50 ++++--------------- .../wireless/mediatek/mt76/mt7925/mt7925.h | 2 - 3 files changed, 15 insertions(+), 47 deletions(-) diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/main.c b/drivers/net/wireless/mediatek/mt76/mt7925/main.c index 98daf80ac131..8dba17c8697c 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/main.c @@ -1289,22 +1289,22 @@ mt7925_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, case IEEE80211_AMPDU_RX_START: mt76_rx_aggr_start(&dev->mt76, &msta->deflink.wcid, tid, ssn, params->buf_size); - mt7925_mcu_uni_rx_ba(dev, vif, params, true); + mt7925_mcu_uni_rx_ba(dev, params, true); break; case IEEE80211_AMPDU_RX_STOP: mt76_rx_aggr_stop(&dev->mt76, &msta->deflink.wcid, tid); - mt7925_mcu_uni_rx_ba(dev, vif, params, false); + mt7925_mcu_uni_rx_ba(dev, params, false); break; case IEEE80211_AMPDU_TX_OPERATIONAL: mtxq->aggr = true; mtxq->send_bar = false; - mt7925_mcu_uni_tx_ba(dev, vif, params, true); + mt7925_mcu_uni_tx_ba(dev, params, true); break; case IEEE80211_AMPDU_TX_STOP_FLUSH: case IEEE80211_AMPDU_TX_STOP_FLUSH_CONT: mtxq->aggr = false; clear_bit(tid, &msta->deflink.wcid.ampdu_state); - mt7925_mcu_uni_tx_ba(dev, vif, params, false); + mt7925_mcu_uni_tx_ba(dev, params, false); break; case IEEE80211_AMPDU_TX_START: set_bit(tid, &msta->deflink.wcid.ampdu_state); @@ -1313,7 +1313,7 @@ mt7925_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, case IEEE80211_AMPDU_TX_STOP_CONT: mtxq->aggr = false; clear_bit(tid, &msta->deflink.wcid.ampdu_state); - mt7925_mcu_uni_tx_ba(dev, vif, params, false); + mt7925_mcu_uni_tx_ba(dev, params, false); ieee80211_stop_tx_ba_cb_irqsafe(vif, sta->addr, tid); break; } diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c index 15815ad84713..4c133200c70b 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c @@ -607,60 +607,30 @@ mt7925_mcu_sta_ba(struct mt76_dev *dev, struct mt76_vif_link *mvif, /** starec & wtbl **/ int mt7925_mcu_uni_tx_ba(struct mt792x_dev *dev, - struct ieee80211_vif *vif, struct ieee80211_ampdu_params *params, bool enable) { struct mt792x_sta *msta = (struct mt792x_sta *)params->sta->drv_priv; - struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv; - struct mt792x_link_sta *mlink; - struct mt792x_bss_conf *mconf; - unsigned long usable_links = ieee80211_vif_usable_links(vif); - struct mt76_wcid *wcid; - u8 link_id, ret; - - for_each_set_bit(link_id, &usable_links, IEEE80211_MLD_MAX_NUM_LINKS) { - mconf = mt792x_vif_to_link(mvif, link_id); - mlink = mt792x_sta_to_link(msta, link_id); - wcid = &mlink->wcid; - - if (enable && !params->amsdu) - mlink->wcid.amsdu = false; + struct mt792x_vif *mvif = msta->vif; + struct mt76_wcid *wcid = &mvif->sta.deflink.wcid; - ret = mt7925_mcu_sta_ba(&dev->mt76, &mconf->mt76, wcid, params, - enable, true); - if (ret < 0) - break; - } + if (enable && !params->amsdu) + msta->deflink.wcid.amsdu = false; - return ret; + return mt7925_mcu_sta_ba(&dev->mt76, &mvif->bss_conf.mt76, wcid, + params, enable, true); } int mt7925_mcu_uni_rx_ba(struct mt792x_dev *dev, - struct ieee80211_vif *vif, struct ieee80211_ampdu_params *params, bool enable) { struct mt792x_sta *msta = (struct mt792x_sta *)params->sta->drv_priv; - struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv; - struct mt792x_link_sta *mlink; - struct mt792x_bss_conf *mconf; - unsigned long usable_links = ieee80211_vif_usable_links(vif); - struct mt76_wcid *wcid; - u8 link_id, ret; - - for_each_set_bit(link_id, &usable_links, IEEE80211_MLD_MAX_NUM_LINKS) { - mconf = mt792x_vif_to_link(mvif, link_id); - mlink = mt792x_sta_to_link(msta, link_id); - wcid = &mlink->wcid; - - ret = mt7925_mcu_sta_ba(&dev->mt76, &mconf->mt76, wcid, params, - enable, false); - if (ret < 0) - break; - } + struct mt792x_vif *mvif = msta->vif; + struct mt76_wcid *wcid = &mvif->sta.deflink.wcid; - return ret; + return mt7925_mcu_sta_ba(&dev->mt76, &mvif->bss_conf.mt76, wcid, + params, enable, false); } static int mt7925_load_clc(struct mt792x_dev *dev, const char *fw_name) diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h b/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h index 8707b5d04743..fd5f9d4ea4a7 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h +++ b/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h @@ -263,11 +263,9 @@ int mt7925_mcu_set_beacon_filter(struct mt792x_dev *dev, struct ieee80211_vif *vif, bool enable); int mt7925_mcu_uni_tx_ba(struct mt792x_dev *dev, - struct ieee80211_vif *vif, struct ieee80211_ampdu_params *params, bool enable); int mt7925_mcu_uni_rx_ba(struct mt792x_dev *dev, - struct ieee80211_vif *vif, struct ieee80211_ampdu_params *params, bool enable); void mt7925_scan_work(struct work_struct *work); -- 2.25.1

14 hours, 2 minutes

3
7
0 0

[PATCH v2] drm/imagination: only init job done fences once

by Brendan King via B4 Relay

From: Brendan King <Brendan.King(a)imgtec.com> Ensure job done fences are only initialised once. This fixes a memory manager not clean warning from drm_mm_takedown on module unload. Cc: stable(a)vger.kernel.org Fixes: eaf01ee5ba28 ("drm/imagination: Implement job submission and scheduling") Signed-off-by: Brendan King <brendan.king(a)imgtec.com> --- Changes in v2: - Added 'Cc:' and 'Fixes:' tags - Link to v1: https://lore.kernel.org/r/20250203-init-done-fences-once-v1-1-a2d62406564b@… --- drivers/gpu/drm/imagination/pvr_queue.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/imagination/pvr_queue.c b/drivers/gpu/drm/imagination/pvr_queue.c index c4f08432882b12f5cdfeb7fc991fd941f0946676..9a67e646f1eae709859f664c796e1940f0b45300 100644 --- a/drivers/gpu/drm/imagination/pvr_queue.c +++ b/drivers/gpu/drm/imagination/pvr_queue.c @@ -304,8 +304,9 @@ pvr_queue_cccb_fence_init(struct dma_fence *fence, struct pvr_queue *queue) static void pvr_queue_job_fence_init(struct dma_fence *fence, struct pvr_queue *queue) { - pvr_queue_fence_init(fence, queue, &pvr_queue_job_fence_ops, - &queue->job_fence_ctx); + if (!fence->ops) + pvr_queue_fence_init(fence, queue, &pvr_queue_job_fence_ops, + &queue->job_fence_ctx); } /** --- base-commit: 3ab334814dc7dff39075e055e12847d51878916e change-id: 20250131-init-done-fences-once-c55c5d0f4d8c Best regards, -- Brendan King <Brendan.King(a)imgtec.com>

16 hours, 34 minutes

2
1
0 0

[PATCH v2] drm/imagination: Hold drm_gem_gpuva lock for unmap

by Brendan King via B4 Relay

From: Brendan King <Brendan.King(a)imgtec.com> Avoid a warning from drm_gem_gpuva_assert_lock_held in drm_gpuva_unlink. The Imagination driver uses the GEM object reservation lock to protect the gpuva list, but the GEM object was not always known in the code paths that ended up calling drm_gpuva_unlink. When the GEM object isn't known, it is found by calling drm_gpuva_find to lookup the object associated with a given virtual address range, or by calling drm_gpuva_find_first when removing all mappings. Cc: stable(a)vger.kernel.org Fixes: 4bc736f890ce ("drm/imagination: vm: make use of GPUVM's drm_exec helper") Signed-off-by: Brendan King <brendan.king(a)imgtec.com> --- Changes in v2: - Added 'Cc:' and 'Fixes:' tags - Link to v1: https://lore.kernel.org/r/20250203-hold-drm_gem_gpuva-lock-for-unmap-v1-1-d… --- drivers/gpu/drm/imagination/pvr_fw_meta.c | 6 +- drivers/gpu/drm/imagination/pvr_vm.c | 134 ++++++++++++++++++++++++------ drivers/gpu/drm/imagination/pvr_vm.h | 3 + 3 files changed, 115 insertions(+), 28 deletions(-) diff --git a/drivers/gpu/drm/imagination/pvr_fw_meta.c b/drivers/gpu/drm/imagination/pvr_fw_meta.c index c39beb70c3173ebdab13b4e810ce5d9a3419f0ba..6d13864851fc2e83bdaa94f16435b97841e5de94 100644 --- a/drivers/gpu/drm/imagination/pvr_fw_meta.c +++ b/drivers/gpu/drm/imagination/pvr_fw_meta.c @@ -527,8 +527,10 @@ pvr_meta_vm_map(struct pvr_device *pvr_dev, struct pvr_fw_object *fw_obj) static void pvr_meta_vm_unmap(struct pvr_device *pvr_dev, struct pvr_fw_object *fw_obj) { - pvr_vm_unmap(pvr_dev->kernel_vm_ctx, fw_obj->fw_mm_node.start, - fw_obj->fw_mm_node.size); + struct pvr_gem_object *pvr_obj = fw_obj->gem; + + pvr_vm_unmap_obj(pvr_dev->kernel_vm_ctx, pvr_obj, + fw_obj->fw_mm_node.start, fw_obj->fw_mm_node.size); } static bool diff --git a/drivers/gpu/drm/imagination/pvr_vm.c b/drivers/gpu/drm/imagination/pvr_vm.c index 363f885a709826efa3d45a906c5f65131f7ed7b9..2896fa7501b1ccddaae48b212b6a724d152df9f2 100644 --- a/drivers/gpu/drm/imagination/pvr_vm.c +++ b/drivers/gpu/drm/imagination/pvr_vm.c @@ -293,8 +293,9 @@ pvr_vm_bind_op_map_init(struct pvr_vm_bind_op *bind_op, static int pvr_vm_bind_op_unmap_init(struct pvr_vm_bind_op *bind_op, - struct pvr_vm_context *vm_ctx, u64 device_addr, - u64 size) + struct pvr_vm_context *vm_ctx, + struct pvr_gem_object *pvr_obj, + u64 device_addr, u64 size) { int err; @@ -318,6 +319,7 @@ pvr_vm_bind_op_unmap_init(struct pvr_vm_bind_op *bind_op, goto err_bind_op_fini; } + bind_op->pvr_obj = pvr_obj; bind_op->vm_ctx = vm_ctx; bind_op->device_addr = device_addr; bind_op->size = size; @@ -597,20 +599,6 @@ pvr_vm_create_context(struct pvr_device *pvr_dev, bool is_userspace_context) return ERR_PTR(err); } -/** - * pvr_vm_unmap_all() - Unmap all mappings associated with a VM context. - * @vm_ctx: Target VM context. - * - * This function ensures that no mappings are left dangling by unmapping them - * all in order of ascending device-virtual address. - */ -void -pvr_vm_unmap_all(struct pvr_vm_context *vm_ctx) -{ - WARN_ON(pvr_vm_unmap(vm_ctx, vm_ctx->gpuvm_mgr.mm_start, - vm_ctx->gpuvm_mgr.mm_range)); -} - /** * pvr_vm_context_release() - Teardown a VM context. * @ref_count: Pointer to reference counter of the VM context. @@ -703,11 +691,7 @@ pvr_vm_lock_extra(struct drm_gpuvm_exec *vm_exec) struct pvr_vm_bind_op *bind_op = vm_exec->extra.priv; struct pvr_gem_object *pvr_obj = bind_op->pvr_obj; - /* Unmap operations don't have an object to lock. */ - if (!pvr_obj) - return 0; - - /* Acquire lock on the GEM being mapped. */ + /* Acquire lock on the GEM object being mapped/unmapped. */ return drm_exec_lock_obj(&vm_exec->exec, gem_from_pvr_gem(pvr_obj)); } @@ -772,8 +756,10 @@ pvr_vm_map(struct pvr_vm_context *vm_ctx, struct pvr_gem_object *pvr_obj, } /** - * pvr_vm_unmap() - Unmap an already mapped section of device-virtual memory. + * pvr_vm_unmap_obj_locked() - Unmap an already mapped section of device-virtual + * memory. * @vm_ctx: Target VM context. + * @pvr_obj: Target PowerVR memory object. * @device_addr: Virtual device address at the start of the target mapping. * @size: Size of the target mapping. * @@ -784,9 +770,13 @@ pvr_vm_map(struct pvr_vm_context *vm_ctx, struct pvr_gem_object *pvr_obj, * * Any error encountered while performing internal operations required to * destroy the mapping (returned from pvr_vm_gpuva_unmap or * pvr_vm_gpuva_remap). + * + * The vm_ctx->lock must be held when calling this function. */ -int -pvr_vm_unmap(struct pvr_vm_context *vm_ctx, u64 device_addr, u64 size) +static int +pvr_vm_unmap_obj_locked(struct pvr_vm_context *vm_ctx, + struct pvr_gem_object *pvr_obj, + u64 device_addr, u64 size) { struct pvr_vm_bind_op bind_op = {0}; struct drm_gpuvm_exec vm_exec = { @@ -799,11 +789,13 @@ pvr_vm_unmap(struct pvr_vm_context *vm_ctx, u64 device_addr, u64 size) }, }; - int err = pvr_vm_bind_op_unmap_init(&bind_op, vm_ctx, device_addr, - size); + int err = pvr_vm_bind_op_unmap_init(&bind_op, vm_ctx, pvr_obj, + device_addr, size); if (err) return err; + pvr_gem_object_get(pvr_obj); + err = drm_gpuvm_exec_lock(&vm_exec); if (err) goto err_cleanup; @@ -818,6 +810,96 @@ pvr_vm_unmap(struct pvr_vm_context *vm_ctx, u64 device_addr, u64 size) return err; } +/** + * pvr_vm_unmap_obj() - Unmap an already mapped section of device-virtual + * memory. + * @vm_ctx: Target VM context. + * @pvr_obj: Target PowerVR memory object. + * @device_addr: Virtual device address at the start of the target mapping. + * @size: Size of the target mapping. + * + * Return: + * * 0 on success, + * * Any error encountered by pvr_vm_unmap_obj_locked. + */ +int +pvr_vm_unmap_obj(struct pvr_vm_context *vm_ctx, struct pvr_gem_object *pvr_obj, + u64 device_addr, u64 size) +{ + int err; + + mutex_lock(&vm_ctx->lock); + err = pvr_vm_unmap_obj_locked(vm_ctx, pvr_obj, device_addr, size); + mutex_unlock(&vm_ctx->lock); + + return err; +} + +/** + * pvr_vm_unmap() - Unmap an already mapped section of device-virtual memory. + * @vm_ctx: Target VM context. + * @device_addr: Virtual device address at the start of the target mapping. + * @size: Size of the target mapping. + * + * Return: + * * 0 on success, + * * Any error encountered by drm_gpuva_find, + * * Any error encountered by pvr_vm_unmap_obj_locked. + */ +int +pvr_vm_unmap(struct pvr_vm_context *vm_ctx, u64 device_addr, u64 size) +{ + struct pvr_gem_object *pvr_obj; + struct drm_gpuva *va; + int err; + + mutex_lock(&vm_ctx->lock); + + va = drm_gpuva_find(&vm_ctx->gpuvm_mgr, device_addr, size); + if (va) { + pvr_obj = gem_to_pvr_gem(va->gem.obj); + err = pvr_vm_unmap_obj_locked(vm_ctx, pvr_obj, + va->va.addr, va->va.range); + } else { + err = -ENOENT; + } + + mutex_unlock(&vm_ctx->lock); + + return err; +} + +/** + * pvr_vm_unmap_all() - Unmap all mappings associated with a VM context. + * @vm_ctx: Target VM context. + * + * This function ensures that no mappings are left dangling by unmapping them + * all in order of ascending device-virtual address. + */ +void +pvr_vm_unmap_all(struct pvr_vm_context *vm_ctx) +{ + mutex_lock(&vm_ctx->lock); + + for (;;) { + struct pvr_gem_object *pvr_obj; + struct drm_gpuva *va; + + va = drm_gpuva_find_first(&vm_ctx->gpuvm_mgr, + vm_ctx->gpuvm_mgr.mm_start, + vm_ctx->gpuvm_mgr.mm_range); + if (!va) + break; + + pvr_obj = gem_to_pvr_gem(va->gem.obj); + + WARN_ON(pvr_vm_unmap_obj_locked(vm_ctx, pvr_obj, + va->va.addr, va->va.range)); + } + + mutex_unlock(&vm_ctx->lock); +} + /* Static data areas are determined by firmware. */ static const struct drm_pvr_static_data_area static_data_areas[] = { { diff --git a/drivers/gpu/drm/imagination/pvr_vm.h b/drivers/gpu/drm/imagination/pvr_vm.h index 79406243617c1f025c0119eb8deeaa13c0415586..b0528dffa7f1ba4342c98c2abd7fac31d254d0e7 100644 --- a/drivers/gpu/drm/imagination/pvr_vm.h +++ b/drivers/gpu/drm/imagination/pvr_vm.h @@ -38,6 +38,9 @@ struct pvr_vm_context *pvr_vm_create_context(struct pvr_device *pvr_dev, int pvr_vm_map(struct pvr_vm_context *vm_ctx, struct pvr_gem_object *pvr_obj, u64 pvr_obj_offset, u64 device_addr, u64 size); +int pvr_vm_unmap_obj(struct pvr_vm_context *vm_ctx, + struct pvr_gem_object *pvr_obj, + u64 device_addr, u64 size); int pvr_vm_unmap(struct pvr_vm_context *vm_ctx, u64 device_addr, u64 size); void pvr_vm_unmap_all(struct pvr_vm_context *vm_ctx); --- base-commit: 3ab334814dc7dff39075e055e12847d51878916e change-id: 20250203-hold-drm_gem_gpuva-lock-for-unmap-da4338395b23 Best regards, -- Brendan King <Brendan.King(a)imgtec.com>

16 hours, 34 minutes

2
1
0 0

[PATCH v2] drm/imagination: avoid deadlock on fence release

by Brendan King via B4 Relay

From: Brendan King <Brendan.King(a)imgtec.com> Do scheduler queue fence release processing on a workqueue, rather than in the release function itself. Fixes deadlock issues such as the following: [ 607.400437] ============================================ [ 607.405755] WARNING: possible recursive locking detected [ 607.415500] -------------------------------------------- [ 607.420817] weston:zfq0/24149 is trying to acquire lock: [ 607.426131] ffff000017d041a0 (reservation_ww_class_mutex){+.+.}-{3:3}, at: pvr_gem_object_vunmap+0x40/0xc0 [powervr] [ 607.436728] but task is already holding lock: [ 607.442554] ffff000017d105a0 (reservation_ww_class_mutex){+.+.}-{3:3}, at: dma_buf_ioctl+0x250/0x554 [ 607.451727] other info that might help us debug this: [ 607.458245] Possible unsafe locking scenario: [ 607.464155] CPU0 [ 607.466601] ---- [ 607.469044] lock(reservation_ww_class_mutex); [ 607.473584] lock(reservation_ww_class_mutex); [ 607.478114] *** DEADLOCK *** Cc: stable(a)vger.kernel.org Fixes: eaf01ee5ba28 ("drm/imagination: Implement job submission and scheduling") Signed-off-by: Brendan King <brendan.king(a)imgtec.com> --- Changes in v2: - Added 'Cc:' and 'Fixes:' tags - Link to v1: https://lore.kernel.org/r/20250203-fence-release-deadlock-v1-1-6e1de1260b38… --- drivers/gpu/drm/imagination/pvr_queue.c | 13 +++++++++++-- drivers/gpu/drm/imagination/pvr_queue.h | 4 ++++ 2 files changed, 15 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/imagination/pvr_queue.c b/drivers/gpu/drm/imagination/pvr_queue.c index c4f08432882b12f5cdfeb7fc991fd941f0946676..f3f1c5212df7432161919ddc510cececacbbe143 100644 --- a/drivers/gpu/drm/imagination/pvr_queue.c +++ b/drivers/gpu/drm/imagination/pvr_queue.c @@ -109,12 +109,20 @@ pvr_queue_fence_get_driver_name(struct dma_fence *f) return PVR_DRIVER_NAME; } +static void pvr_queue_fence_release_work(struct work_struct *w) +{ + struct pvr_queue_fence *fence = container_of(w, struct pvr_queue_fence, release_work); + + pvr_context_put(fence->queue->ctx); + dma_fence_free(&fence->base); +} + static void pvr_queue_fence_release(struct dma_fence *f) { struct pvr_queue_fence *fence = container_of(f, struct pvr_queue_fence, base); + struct pvr_device *pvr_dev = fence->queue->ctx->pvr_dev; - pvr_context_put(fence->queue->ctx); - dma_fence_free(f); + queue_work(pvr_dev->sched_wq, &fence->release_work); } static const char * @@ -268,6 +276,7 @@ pvr_queue_fence_init(struct dma_fence *f, pvr_context_get(queue->ctx); fence->queue = queue; + INIT_WORK(&fence->release_work, pvr_queue_fence_release_work); dma_fence_init(&fence->base, fence_ops, &fence_ctx->lock, fence_ctx->id, atomic_inc_return(&fence_ctx->seqno)); diff --git a/drivers/gpu/drm/imagination/pvr_queue.h b/drivers/gpu/drm/imagination/pvr_queue.h index e06ced69302fca47fc26451dfb09ebbb24b57f52..93fe9ac9f58ccc020615485e86be438548dcee43 100644 --- a/drivers/gpu/drm/imagination/pvr_queue.h +++ b/drivers/gpu/drm/imagination/pvr_queue.h @@ -5,6 +5,7 @@ #define PVR_QUEUE_H #include <drm/gpu_scheduler.h> +#include <linux/workqueue.h> #include "pvr_cccb.h" #include "pvr_device.h" @@ -63,6 +64,9 @@ struct pvr_queue_fence { /** @queue: Queue that created this fence. */ struct pvr_queue *queue; + + /** @release_work: Fence release work structure. */ + struct work_struct release_work; }; /** --- base-commit: 3ab334814dc7dff39075e055e12847d51878916e change-id: 20250203-fence-release-deadlock-a0753c07bfdd Best regards, -- Brendan King <Brendan.King(a)imgtec.com>

16 hours, 34 minutes

2
1
0 0

[PATCH 1/1] PCI/bwctrl: Disable PCIe BW controller during reset

by Ilpo Järvinen

PCIe BW controller enables BW notifications for Downstream Ports by setting Link Bandwidth Management Interrupt Enable (LBMIE) and Link Autonomous Bandwidth Interrupt Enable (LABIE) (PCIe Spec. r6.2 sec. 7.5.3.7). It was discovered that performing a reset can lead to the device underneath the Downstream Port becoming unavailable if BW notifications are left enabled throughout the reset sequence (at least LBMIE was found to cause an issue). While the PCIe Specifications do not indicate BW notifications could not be kept enabled during resets, the PCIe Link state during an intentional reset is not of large interest. Thus, disable BW controller for the bridge while reset is performed and re-enable it after the reset has completed to workaround the problems some devices encounter if BW notifications are left on throughout the reset sequence. Keep a counter for the disable/enable because MFD will execute pci_dev_save_and_disable() and pci_dev_restore() back to back for sibling devices: [ 50.139010] vfio-pci 0000:01:00.0: resetting [ 50.139053] vfio-pci 0000:01:00.1: resetting [ 50.141126] pcieport 0000:00:01.1: PME: Spurious native interrupt! [ 50.141133] pcieport 0000:00:01.1: PME: Spurious native interrupt! [ 50.441466] vfio-pci 0000:01:00.0: reset done [ 50.501534] vfio-pci 0000:01:00.1: reset done Fixes: 665745f27487 ("PCI/bwctrl: Re-add BW notification portdrv as PCIe BW controller") Closes: https://bugzilla.kernel.org/show_bug.cgi?id=219765 Tested-by: Joel Mathew Thomas <proxy0(a)tutamail.com> Signed-off-by: Ilpo Järvinen <ilpo.jarvinen(a)linux.intel.com> Cc: stable(a)vger.kernel.org --- I suspect the root cause is some kind of violation of specifications. Resets shouldn't cause devices to become unavailable just because BW notifications have been enabled. Before somebody comments on those dual rwsems, I do have yet to be submitted patch to simplify the locking as per Lukas Wunner's earlier suggestion. I've just focused on solving the regressions first. drivers/pci/pci.c | 8 +++++++ drivers/pci/pci.h | 4 ++++ drivers/pci/pcie/bwctrl.c | 49 ++++++++++++++++++++++++++++++++------- 3 files changed, 53 insertions(+), 8 deletions(-) diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 869d204a70a3..7a53d7474175 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -5148,6 +5148,7 @@ static void pci_dev_save_and_disable(struct pci_dev *dev) { const struct pci_error_handlers *err_handler = dev->driver ? dev->driver->err_handler : NULL; + struct pci_dev *bridge = pci_upstream_bridge(dev); /* * dev->driver->err_handler->reset_prepare() is protected against @@ -5166,6 +5167,9 @@ static void pci_dev_save_and_disable(struct pci_dev *dev) */ pci_set_power_state(dev, PCI_D0); + if (bridge) + pcie_bwnotif_disable(bridge); + pci_save_state(dev); /* * Disable the device by clearing the Command register, except for @@ -5181,9 +5185,13 @@ static void pci_dev_restore(struct pci_dev *dev) { const struct pci_error_handlers *err_handler = dev->driver ? dev->driver->err_handler : NULL; + struct pci_dev *bridge = pci_upstream_bridge(dev); pci_restore_state(dev); + if (bridge) + pcie_bwnotif_enable(bridge); + /* * dev->driver->err_handler->reset_done() is protected against * races with ->remove() by the device lock, which must be held by diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 01e51db8d285..856546f1aad9 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -759,12 +759,16 @@ static inline void pcie_ecrc_get_policy(char *str) { } #ifdef CONFIG_PCIEPORTBUS void pcie_reset_lbms_count(struct pci_dev *port); int pcie_lbms_count(struct pci_dev *port, unsigned long *val); +void pcie_bwnotif_enable(struct pci_dev *port); +void pcie_bwnotif_disable(struct pci_dev *port); #else static inline void pcie_reset_lbms_count(struct pci_dev *port) {} static inline int pcie_lbms_count(struct pci_dev *port, unsigned long *val) { return -EOPNOTSUPP; } +static inline void pcie_bwnotif_enable(struct pci_dev *port) {} +static inline void pcie_bwnotif_disable(struct pci_dev *port) {} #endif struct pci_dev_reset_methods { diff --git a/drivers/pci/pcie/bwctrl.c b/drivers/pci/pcie/bwctrl.c index 0a5e7efbce2c..a117f6f67c07 100644 --- a/drivers/pci/pcie/bwctrl.c +++ b/drivers/pci/pcie/bwctrl.c @@ -40,11 +40,13 @@ * @set_speed_mutex: Serializes link speed changes * @lbms_count: Count for LBMS (since last reset) * @cdev: Thermal cooling device associated with the port + * @disable_count: BW notifications disabled/enabled counter */ struct pcie_bwctrl_data { struct mutex set_speed_mutex; atomic_t lbms_count; struct thermal_cooling_device *cdev; + int disable_count; }; /* @@ -200,10 +202,9 @@ int pcie_set_target_speed(struct pci_dev *port, enum pci_bus_speed speed_req, return ret; } -static void pcie_bwnotif_enable(struct pcie_device *srv) +static void __pcie_bwnotif_enable(struct pci_dev *port) { - struct pcie_bwctrl_data *data = srv->port->link_bwctrl; - struct pci_dev *port = srv->port; + struct pcie_bwctrl_data *data = port->link_bwctrl; u16 link_status; int ret; @@ -224,12 +225,44 @@ static void pcie_bwnotif_enable(struct pcie_device *srv) pcie_update_link_speed(port->subordinate); } -static void pcie_bwnotif_disable(struct pci_dev *port) +void pcie_bwnotif_enable(struct pci_dev *port) +{ + guard(rwsem_read)(&pcie_bwctrl_setspeed_rwsem); + guard(rwsem_read)(&pcie_bwctrl_lbms_rwsem); + + if (!port->link_bwctrl) + return; + + port->link_bwctrl->disable_count--; + if (!port->link_bwctrl->disable_count) { + __pcie_bwnotif_enable(port); + pci_dbg(port, "BW notifications enabled\n"); + } + WARN_ON_ONCE(port->link_bwctrl->disable_count < 0); +} + +static void __pcie_bwnotif_disable(struct pci_dev *port) { pcie_capability_clear_word(port, PCI_EXP_LNKCTL, PCI_EXP_LNKCTL_LBMIE | PCI_EXP_LNKCTL_LABIE); } +void pcie_bwnotif_disable(struct pci_dev *port) +{ + guard(rwsem_read)(&pcie_bwctrl_setspeed_rwsem); + guard(rwsem_read)(&pcie_bwctrl_lbms_rwsem); + + if (!port->link_bwctrl) + return; + + port->link_bwctrl->disable_count++; + + if (port->link_bwctrl->disable_count == 1) { + __pcie_bwnotif_disable(port); + pci_dbg(port, "BW notifications disabled\n"); + } +} + static irqreturn_t pcie_bwnotif_irq(int irq, void *context) { struct pcie_device *srv = context; @@ -314,7 +347,7 @@ static int pcie_bwnotif_probe(struct pcie_device *srv) return ret; } - pcie_bwnotif_enable(srv); + __pcie_bwnotif_enable(port); } } @@ -336,7 +369,7 @@ static void pcie_bwnotif_remove(struct pcie_device *srv) scoped_guard(rwsem_write, &pcie_bwctrl_setspeed_rwsem) { scoped_guard(rwsem_write, &pcie_bwctrl_lbms_rwsem) { - pcie_bwnotif_disable(srv->port); + __pcie_bwnotif_disable(srv->port); free_irq(srv->irq, srv); @@ -347,13 +380,13 @@ static void pcie_bwnotif_remove(struct pcie_device *srv) static int pcie_bwnotif_suspend(struct pcie_device *srv) { - pcie_bwnotif_disable(srv->port); + __pcie_bwnotif_disable(srv->port); return 0; } static int pcie_bwnotif_resume(struct pcie_device *srv) { - pcie_bwnotif_enable(srv); + __pcie_bwnotif_enable(srv->port); return 0; } base-commit: 2014c95afecee3e76ca4a56956a936e23283f05b -- 2.39.5

16 hours, 50 minutes

2
6
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror February 2025