May 2025 - Linux-stable-mirror

+ kasan-avoid-sleepable-page-allocation-from-atomic-context-v9.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: kasan: avoid sleepable page allocation from atomic context has been added to the -mm mm-hotfixes-unstable branch. Its filename is kasan-avoid-sleepable-page-allocation-from-atomic-context-v9.patch This patch will shortly appear at https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patche… This patch will later appear in the mm-hotfixes-unstable branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next via the mm-everything branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there every 2-3 working days ------------------------------------------------------ From: Alexander Gordeev <agordeev(a)linux.ibm.com> Subject: kasan: avoid sleepable page allocation from atomic context Date: Thu, 15 May 2025 15:55:38 +0200 apply_to_pte_range() enters the lazy MMU mode and then invokes kasan_populate_vmalloc_pte() callback on each page table walk iteration. However, the callback can go into sleep when trying to allocate a single page, e.g. if an architecutre disables preemption on lazy MMU mode enter. On s390 if make arch_enter_lazy_mmu_mode() -> preempt_enable() and arch_leave_lazy_mmu_mode() -> preempt_disable(), such crash occurs: [ 0.663336] BUG: sleeping function called from invalid context at ./include/linux/sched/mm.h:321 [ 0.663348] in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 2, name: kthreadd [ 0.663358] preempt_count: 1, expected: 0 [ 0.663366] RCU nest depth: 0, expected: 0 [ 0.663375] no locks held by kthreadd/2. [ 0.663383] Preemption disabled at: [ 0.663386] [<0002f3284cbb4eda>] apply_to_pte_range+0xfa/0x4a0 [ 0.663405] CPU: 0 UID: 0 PID: 2 Comm: kthreadd Not tainted 6.15.0-rc5-gcc-kasan-00043-gd76bb1ebb558-dirty #162 PREEMPT [ 0.663408] Hardware name: IBM 3931 A01 701 (KVM/Linux) [ 0.663409] Call Trace: [ 0.663410] [<0002f3284c385f58>] dump_stack_lvl+0xe8/0x140 [ 0.663413] [<0002f3284c507b9e>] __might_resched+0x66e/0x700 [ 0.663415] [<0002f3284cc4f6c0>] __alloc_frozen_pages_noprof+0x370/0x4b0 [ 0.663419] [<0002f3284ccc73c0>] alloc_pages_mpol+0x1a0/0x4a0 [ 0.663421] [<0002f3284ccc8518>] alloc_frozen_pages_noprof+0x88/0xc0 [ 0.663424] [<0002f3284ccc8572>] alloc_pages_noprof+0x22/0x120 [ 0.663427] [<0002f3284cc341ac>] get_free_pages_noprof+0x2c/0xc0 [ 0.663429] [<0002f3284cceba70>] kasan_populate_vmalloc_pte+0x50/0x120 [ 0.663433] [<0002f3284cbb4ef8>] apply_to_pte_range+0x118/0x4a0 [ 0.663435] [<0002f3284cbc7c14>] apply_to_pmd_range+0x194/0x3e0 [ 0.663437] [<0002f3284cbc99be>] __apply_to_page_range+0x2fe/0x7a0 [ 0.663440] [<0002f3284cbc9e88>] apply_to_page_range+0x28/0x40 [ 0.663442] [<0002f3284ccebf12>] kasan_populate_vmalloc+0x82/0xa0 [ 0.663445] [<0002f3284cc1578c>] alloc_vmap_area+0x34c/0xc10 [ 0.663448] [<0002f3284cc1c2a6>] __get_vm_area_node+0x186/0x2a0 [ 0.663451] [<0002f3284cc1e696>] __vmalloc_node_range_noprof+0x116/0x310 [ 0.663454] [<0002f3284cc1d950>] __vmalloc_node_noprof+0xd0/0x110 [ 0.663457] [<0002f3284c454b88>] alloc_thread_stack_node+0xf8/0x330 [ 0.663460] [<0002f3284c458d56>] dup_task_struct+0x66/0x4d0 [ 0.663463] [<0002f3284c45be90>] copy_process+0x280/0x4b90 [ 0.663465] [<0002f3284c460940>] kernel_clone+0xd0/0x4b0 [ 0.663467] [<0002f3284c46115e>] kernel_thread+0xbe/0xe0 [ 0.663469] [<0002f3284c4e440e>] kthreadd+0x50e/0x7f0 [ 0.663472] [<0002f3284c38c04a>] __ret_from_fork+0x8a/0xf0 [ 0.663475] [<0002f3284ed57ff2>] ret_from_fork+0xa/0x38 Instead of allocating single pages per-PTE, bulk-allocate the shadow memory prior to applying kasan_populate_vmalloc_pte() callback on a page range. Link: https://lkml.kernel.org/r/c61d3560297c93ed044f0b1af085610353a06a58.17473169… Fixes: 3c5c3cfb9ef4 ("kasan: support backing vmalloc space with real shadow memory") Signed-off-by: Alexander Gordeev <agordeev(a)linux.ibm.com> Suggested-by: Andrey Ryabinin <ryabinin.a.a(a)gmail.com> Reviewed-by: Harry Yoo <harry.yoo(a)oracle.com> Cc: Daniel Axtens <dja(a)axtens.net> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/kasan/shadow.c | 92 +++++++++++++++++++++++++++++++++++++------- 1 file changed, 78 insertions(+), 14 deletions(-) --- a/mm/kasan/shadow.c~kasan-avoid-sleepable-page-allocation-from-atomic-context-v9 +++ a/mm/kasan/shadow.c @@ -292,33 +292,99 @@ void __init __weak kasan_populate_early_ { } +struct vmalloc_populate_data { + unsigned long start; + struct page **pages; +}; + static int kasan_populate_vmalloc_pte(pte_t *ptep, unsigned long addr, - void *unused) + void *_data) { - unsigned long page; + struct vmalloc_populate_data *data = _data; + struct page *page; pte_t pte; + int index; if (likely(!pte_none(ptep_get(ptep)))) return 0; - page = __get_free_page(GFP_KERNEL); - if (!page) - return -ENOMEM; - - __memset((void *)page, KASAN_VMALLOC_INVALID, PAGE_SIZE); - pte = pfn_pte(PFN_DOWN(__pa(page)), PAGE_KERNEL); + index = PFN_DOWN(addr - data->start); + page = data->pages[index]; + __memset(page_to_virt(page), KASAN_VMALLOC_INVALID, PAGE_SIZE); + pte = pfn_pte(page_to_pfn(page), PAGE_KERNEL); spin_lock(&init_mm.page_table_lock); if (likely(pte_none(ptep_get(ptep)))) { set_pte_at(&init_mm, addr, ptep, pte); - page = 0; + data->pages[index] = NULL; } spin_unlock(&init_mm.page_table_lock); - if (page) - free_page(page); + + return 0; +} + +static void ___free_pages_bulk(struct page **pages, int nr_pages) +{ + int i; + + for (i = 0; i < nr_pages; i++) { + if (pages[i]) { + __free_pages(pages[i], 0); + pages[i] = NULL; + } + } +} + +static int ___alloc_pages_bulk(struct page **pages, int nr_pages) +{ + unsigned long nr_populated, nr_total = nr_pages; + struct page **page_array = pages; + + while (nr_pages) { + nr_populated = alloc_pages_bulk(GFP_KERNEL, nr_pages, pages); + if (!nr_populated) { + ___free_pages_bulk(page_array, nr_total - nr_pages); + return -ENOMEM; + } + pages += nr_populated; + nr_pages -= nr_populated; + } + return 0; } +static int __kasan_populate_vmalloc(unsigned long start, unsigned long end) +{ + unsigned long nr_pages, nr_total = PFN_UP(end - start); + struct vmalloc_populate_data data; + int ret = 0; + + data.pages = (struct page **)__get_free_page(GFP_KERNEL | __GFP_ZERO); + if (!data.pages) + return -ENOMEM; + + while (nr_total) { + nr_pages = min(nr_total, PAGE_SIZE / sizeof(data.pages[0])); + ret = ___alloc_pages_bulk(data.pages, nr_pages); + if (ret) + break; + + data.start = start; + ret = apply_to_page_range(&init_mm, start, nr_pages * PAGE_SIZE, + kasan_populate_vmalloc_pte, &data); + ___free_pages_bulk(data.pages, nr_pages); + if (ret) + break; + + start += nr_pages * PAGE_SIZE; + nr_total -= nr_pages; + } + + free_page((unsigned long)data.pages); + + return ret; +} + int kasan_populate_vmalloc(unsigned long addr, unsigned long size) { unsigned long shadow_start, shadow_end; @@ -348,9 +414,7 @@ int kasan_populate_vmalloc(unsigned long shadow_start = PAGE_ALIGN_DOWN(shadow_start); shadow_end = PAGE_ALIGN(shadow_end); - ret = apply_to_page_range(&init_mm, shadow_start, - shadow_end - shadow_start, - kasan_populate_vmalloc_pte, NULL); + ret = __kasan_populate_vmalloc(shadow_start, shadow_end); if (ret) return ret; _ Patches currently in -mm which might be from agordeev(a)linux.ibm.com are kasan-avoid-sleepable-page-allocation-from-atomic-context-v9.patch

3 months, 3 weeks

1
0
0 0

FAILED: patch "[PATCH] iio: light: opt3001: fix deadlock due to concurrent flag" failed to apply to 6.12-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.12-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.12.y git checkout FETCH_HEAD git cherry-pick -x f063a28002e3350088b4577c5640882bf4ea17ea # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025051215-economist-traffic-fa57@gregkh' --subject-prefix 'PATCH 6.12.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From f063a28002e3350088b4577c5640882bf4ea17ea Mon Sep 17 00:00:00 2001 From: Luca Ceresoli <luca.ceresoli(a)bootlin.com> Date: Fri, 21 Mar 2025 19:10:00 +0100 Subject: [PATCH] iio: light: opt3001: fix deadlock due to concurrent flag access The threaded IRQ function in this driver is reading the flag twice: once to lock a mutex and once to unlock it. Even though the code setting the flag is designed to prevent it, there are subtle cases where the flag could be true at the mutex_lock stage and false at the mutex_unlock stage. This results in the mutex not being unlocked, resulting in a deadlock. Fix it by making the opt3001_irq() code generally more robust, reading the flag into a variable and using the variable value at both stages. Fixes: 94a9b7b1809f ("iio: light: add support for TI's opt3001 light sensor") Cc: stable(a)vger.kernel.org Signed-off-by: Luca Ceresoli <luca.ceresoli(a)bootlin.com> Link: https://patch.msgid.link/20250321-opt3001-irq-fix-v1-1-6c520d851562@bootlin… Signed-off-by: Jonathan Cameron <Jonathan.Cameron(a)huawei.com> diff --git a/drivers/iio/light/opt3001.c b/drivers/iio/light/opt3001.c index 65b295877b41..393a3d2fbe1d 100644 --- a/drivers/iio/light/opt3001.c +++ b/drivers/iio/light/opt3001.c @@ -788,8 +788,9 @@ static irqreturn_t opt3001_irq(int irq, void *_iio) int ret; bool wake_result_ready_queue = false; enum iio_chan_type chan_type = opt->chip_info->chan_type; + bool ok_to_ignore_lock = opt->ok_to_ignore_lock; - if (!opt->ok_to_ignore_lock) + if (!ok_to_ignore_lock) mutex_lock(&opt->lock); ret = i2c_smbus_read_word_swapped(opt->client, OPT3001_CONFIGURATION); @@ -826,7 +827,7 @@ static irqreturn_t opt3001_irq(int irq, void *_iio) } out: - if (!opt->ok_to_ignore_lock) + if (!ok_to_ignore_lock) mutex_unlock(&opt->lock); if (wake_result_ready_queue)

3 months, 3 weeks

3
5
0 0

Propuesla

by laraweer24＠gmail.com

Dear there [Email: linux-stable-mirror(a)lists.linaro.org], I came across your website and really think it has great potential. I'd love to share a proposal with you on how we can help improve your website's visibility on Google — possibly even get it to the first page. Would it be okay if I send you the proposal and pricing details? Thanks,

3 months, 3 weeks

1
0
0 0

[PATCH v9 0/1] kasan: Avoid sleepable page allocation from atomic context

by Alexander Gordeev

Hi All, I dropped Harry Yoo's Reviewed-by from this version. Chages since v8: - fixed page_owner=on issue preventing bulk allocations on x86 Chages since v7: - drop "unnecessary free pages" optimization - fix error path page leak Chages since v6: - do not unnecessary free pages across iterations Chages since v5: - full error message included into commit description Chages since v4: - unused pages leak is avoided Chages since v3: - pfn_to_virt() changed to page_to_virt() due to compile error Chages since v2: - page allocation moved out of the atomic context Chages since v1: - Fixes: and -stable tags added to the patch description Thanks! Alexander Gordeev (1): kasan: Avoid sleepable page allocation from atomic context mm/kasan/shadow.c | 92 +++++++++++++++++++++++++++++++++++++++-------- 1 file changed, 78 insertions(+), 14 deletions(-) -- 2.45.2

3 months, 3 weeks

2
2
0 0

[PATCH v2 1/2] xhci: Add a quirk for full reset on removal

by Roy Luo

Commit 6ccb83d6c497 ("usb: xhci: Implement xhci_handshake_check_state() helper") introduced an optimization to xhci_reset() during xhci removal, allowing it to bail out early without waiting for the reset to complete. This behavior can cause issues on SNPS DWC3 USB controller with dual-role capability. When the DWC3 controller exits host mode and removes xhci while a reset is still in progress, and then tries to configure its hardware for device mode, the ongoing reset leads to register access issues; specifically, all register reads returns 0. These issues extend beyond the xhci register space (which is expected during a reset) and affect the entire DWC3 IP block, causing the DWC3 device mode to malfunction. To address this, introduce the `XHCI_FULL_RESET_ON_REMOVE` quirk. When this quirk is set, xhci_reset() always completes its reset handshake, ensuring the controller is in a fully reset state before proceeding. Cc: stable(a)vger.kernel.org Fixes: 6ccb83d6c497 ("usb: xhci: Implement xhci_handshake_check_state() helper") Signed-off-by: Roy Luo <royluo(a)google.com> --- drivers/usb/host/xhci-plat.c | 3 +++ drivers/usb/host/xhci.c | 8 +++++++- drivers/usb/host/xhci.h | 1 + 3 files changed, 11 insertions(+), 1 deletion(-) diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c index 3155e3a842da..19c5c26a8e63 100644 --- a/drivers/usb/host/xhci-plat.c +++ b/drivers/usb/host/xhci-plat.c @@ -265,6 +265,9 @@ int xhci_plat_probe(struct platform_device *pdev, struct device *sysdev, const s if (device_property_read_bool(tmpdev, "xhci-skip-phy-init-quirk")) xhci->quirks |= XHCI_SKIP_PHY_INIT; + if (device_property_read_bool(tmpdev, "xhci-full-reset-on-remove-quirk")) + xhci->quirks |= XHCI_FULL_RESET_ON_REMOVE; + device_property_read_u32(tmpdev, "imod-interval-ns", &xhci->imod_interval); } diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 90eb491267b5..4f091d618c01 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -198,6 +198,7 @@ int xhci_reset(struct xhci_hcd *xhci, u64 timeout_us) u32 command; u32 state; int ret; + unsigned int exit_state; state = readl(&xhci->op_regs->status); @@ -226,8 +227,13 @@ int xhci_reset(struct xhci_hcd *xhci, u64 timeout_us) if (xhci->quirks & XHCI_INTEL_HOST) udelay(1000); + if (xhci->quirks & XHCI_FULL_RESET_ON_REMOVE) + exit_state = 0; + else + exit_state = XHCI_STATE_REMOVING; + ret = xhci_handshake_check_state(xhci, &xhci->op_regs->command, - CMD_RESET, 0, timeout_us, XHCI_STATE_REMOVING); + CMD_RESET, 0, timeout_us, exit_state); if (ret) return ret; diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 242ab9fbc8ae..ac65af788298 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -1637,6 +1637,7 @@ struct xhci_hcd { #define XHCI_WRITE_64_HI_LO BIT_ULL(47) #define XHCI_CDNS_SCTX_QUIRK BIT_ULL(48) #define XHCI_ETRON_HOST BIT_ULL(49) +#define XHCI_FULL_RESET_ON_REMOVE BIT_ULL(50) unsigned int num_active_eps; unsigned int limit_active_eps; -- 2.49.0.1112.g889b7c5bd8-goog

3 months, 3 weeks

3
6
0 0

[PATCH v1 1/3] s390/uv: don't return 0 from make_hva_secure() if the operation was not successful

by David Hildenbrand

If s390_wiggle_split_folio() returns 0 because splitting a large folio succeeded, we will return 0 from make_hva_secure() even though a retry is required. Return -EAGAIN in that case. Otherwise, we'll return 0 from gmap_make_secure(), and consequently from unpack_one(). In kvm_s390_pv_unpack(), we assume that unpacking succeeded and skip unpacking this page. Later on, we run into issues and fail booting the VM. So far, this issue was only observed with follow-up patches where we split large pagecache XFS folios. Maybe it can also be triggered with shmem? We'll cleanup s390_wiggle_split_folio() a bit next, to also return 0 if no split was required. Fixes: d8dfda5af0be ("KVM: s390: pv: fix race when making a page secure") Cc: stable(a)vger.kernel.org Signed-off-by: David Hildenbrand <david(a)redhat.com> --- arch/s390/kernel/uv.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c index 9a5d5be8acf41..2cc3b599c7fe3 100644 --- a/arch/s390/kernel/uv.c +++ b/arch/s390/kernel/uv.c @@ -393,8 +393,11 @@ int make_hva_secure(struct mm_struct *mm, unsigned long hva, struct uv_cb_header folio_walk_end(&fw, vma); mmap_read_unlock(mm); - if (rc == -E2BIG || rc == -EBUSY) + if (rc == -E2BIG || rc == -EBUSY) { rc = s390_wiggle_split_folio(mm, folio, rc == -E2BIG); + if (!rc) + rc = -EAGAIN; + } folio_put(folio); return rc; -- 2.49.0

3 months, 3 weeks

2
4
0 0

[PATCH v3 rc] iommu: Skip PASID validation for devices without PASID capability

by Tushar Dave

Generally PASID support requires ACS settings that usually create single device groups, but there are some niche cases where we can get multi-device groups and still have working PASID support. The primary issue is that PCI switches are not required to treat PASID tagged TLPs specially so appropriate ACS settings are required to route all TLPs to the host bridge if PASID is going to work properly. pci_enable_pasid() does check that each device that will use PASID has the proper ACS settings to achieve this routing. However, no-PASID devices can be combined with PASID capable devices within the same topology using non-uniform ACS settings. In this case the no-PASID devices may not have strict route to host ACS flags and end up being grouped with the PASID devices. This configuration fails to allow use of the PASID within the iommu core code which wrongly checks if the no-PASID device supports PASID. Fix this by ignoring no-PASID devices during the PASID validation. They will never issue a PASID TLP anyhow so they can be ignored. Fixes: c404f55c26fc ("iommu: Validate the PASID in iommu_attach_device_pasid()") Cc: stable(a)vger.kernel.org Signed-off-by: Tushar Dave <tdave(a)nvidia.com> --- changes in v3: - addressed review comment from Vasant. drivers/iommu/iommu.c | 27 +++++++++++++++++++-------- 1 file changed, 19 insertions(+), 8 deletions(-) diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 60aed01e54f2..636fc68a8ec0 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -3329,10 +3329,12 @@ static int __iommu_set_group_pasid(struct iommu_domain *domain, int ret; for_each_group_device(group, device) { - ret = domain->ops->set_dev_pasid(domain, device->dev, - pasid, NULL); - if (ret) - goto err_revert; + if (device->dev->iommu->max_pasids > 0) { + ret = domain->ops->set_dev_pasid(domain, device->dev, + pasid, NULL); + if (ret) + goto err_revert; + } } return 0; @@ -3342,7 +3344,8 @@ static int __iommu_set_group_pasid(struct iommu_domain *domain, for_each_group_device(group, device) { if (device == last_gdev) break; - iommu_remove_dev_pasid(device->dev, pasid, domain); + if (device->dev->iommu->max_pasids > 0) + iommu_remove_dev_pasid(device->dev, pasid, domain); } return ret; } @@ -3353,8 +3356,10 @@ static void __iommu_remove_group_pasid(struct iommu_group *group, { struct group_device *device; - for_each_group_device(group, device) - iommu_remove_dev_pasid(device->dev, pasid, domain); + for_each_group_device(group, device) { + if (device->dev->iommu->max_pasids > 0) + iommu_remove_dev_pasid(device->dev, pasid, domain); + } } /* @@ -3391,7 +3396,13 @@ int iommu_attach_device_pasid(struct iommu_domain *domain, mutex_lock(&group->mutex); for_each_group_device(group, device) { - if (pasid >= device->dev->iommu->max_pasids) { + /* + * Skip PASID validation for devices without PASID support + * (max_pasids = 0). These devices cannot issue transactions + * with PASID, so they don't affect group's PASID usage. + */ + if ((device->dev->iommu->max_pasids > 0) && + (pasid >= device->dev->iommu->max_pasids)) { ret = -EINVAL; goto out_unlock; } -- 2.34.1

3 months, 3 weeks

6
8
0 0

[PATCH net v2] vmxnet3: update MTU after device quiesce

by Ronak Doshi

Currently, when device mtu is updated, vmxnet3 updates netdev mtu, quiesces the device and then reactivates it for the ESXi to know about the new mtu. So, technically the OS stack can start using the new mtu before ESXi knows about the new mtu. This can lead to issues for TSO packets which use mss as per the new mtu configured. This patch fixes this issue by moving the mtu write after device quiesce. Cc: stable(a)vger.kernel.org Fixes: d1a890fa37f2 ("net: VMware virtual Ethernet NIC driver: vmxnet3") Signed-off-by: Ronak Doshi <ronak.doshi(a)broadcom.com> Acked-by: Guolin Yang <guolin.yang(a)broadcom.com> Changes v1-> v2: Moved MTU write after destroy of rx rings --- drivers/net/vmxnet3/vmxnet3_drv.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index 3df6aabc7e33..c676979c7ab9 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -3607,8 +3607,6 @@ vmxnet3_change_mtu(struct net_device *netdev, int new_mtu) struct vmxnet3_adapter *adapter = netdev_priv(netdev); int err = 0; - WRITE_ONCE(netdev->mtu, new_mtu); - /* * Reset_work may be in the middle of resetting the device, wait for its * completion. @@ -3622,6 +3620,7 @@ vmxnet3_change_mtu(struct net_device *netdev, int new_mtu) /* we need to re-create the rx queue based on the new mtu */ vmxnet3_rq_destroy_all(adapter); + WRITE_ONCE(netdev->mtu, new_mtu); vmxnet3_adjust_rx_ring_size(adapter); err = vmxnet3_rq_create_all(adapter); if (err) { @@ -3638,6 +3637,8 @@ vmxnet3_change_mtu(struct net_device *netdev, int new_mtu) "Closing it\n", err); goto out; } + } else { + WRITE_ONCE(netdev->mtu, new_mtu); } out: -- 2.45.2

3 months, 3 weeks

2
1
0 0

[PATCH net v3] net: dsa: microchip: linearize skb for tail-tagging switches

by Jakob Unterwurzacher

The pointer arithmentic for accessing the tail tag only works for linear skbs. For nonlinear skbs, it reads uninitialized memory inside the skb headroom, essentially randomizing the tag. I have observed it gets set to 6 most of the time. Example where ksz9477_rcv thinks that the packet from port 1 comes from port 6 (which does not exist for the ksz9896 that's in use), dropping the packet. Debug prints added by me (not included in this patch): [ 256.645337] ksz9477_rcv:323 tag0=6 [ 256.645349] skb len=47 headroom=78 headlen=0 tailroom=0 mac=(64,14) mac_len=14 net=(78,0) trans=78 shinfo(txflags=0 nr_frags=1 gso(size=0 type=0 segs=0)) csum(0x0 start=0 offset=0 ip_summed=0 complete_sw=0 valid=0 level=0) hash(0x0 sw=0 l4=0) proto=0x00f8 pkttype=1 iif=3 priority=0x0 mark=0x0 alloc_cpu=0 vlan_all=0x0 encapsulation=0 inner(proto=0x0000, mac=0, net=0, trans=0) [ 256.645377] dev name=end1 feat=0x0002e10200114bb3 [ 256.645386] skb headroom: 00000000: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 256.645395] skb headroom: 00000010: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 256.645403] skb headroom: 00000020: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 256.645411] skb headroom: 00000030: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 256.645420] skb headroom: 00000040: ff ff ff ff ff ff 00 1c 19 f2 e2 db 08 06 [ 256.645428] skb frag: 00000000: 00 01 08 00 06 04 00 01 00 1c 19 f2 e2 db 0a 02 [ 256.645436] skb frag: 00000010: 00 83 00 00 00 00 00 00 0a 02 a0 2f 00 00 00 00 [ 256.645444] skb frag: 00000020: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 01 [ 256.645452] ksz_common_rcv:92 dsa_conduit_find_user returned NULL Call skb_linearize before trying to access the tag. This patch fixes ksz9477_rcv which is used by the ksz9896 I have at hand, and also applies the same fix to ksz8795_rcv which seems to have the same problem. Signed-off-by: Jakob Unterwurzacher <jakob.unterwurzacher(a)cherry.de> CC: stable(a)vger.kernel.org Fixes: 016e43a26bab ("net: dsa: ksz: Add KSZ8795 tag code") Fixes: 8b8010fb7876 ("dsa: add support for Microchip KSZ tail tagging") Reviewed-by: Vladimir Oltean <olteanv(a)gmail.com> --- v1: Initial submission https://lore.kernel.org/netdev/20250509071820.4100022-1-jakob.unterwurzache… v2: Add Fixes tags, Cc stable, "[PATCH net]" prefix https://lore.kernel.org/netdev/20250512144416.3697054-1-jakob.unterwurzache… v3: Move declarations before skb_linearize call, pick up Reviewed-By net/dsa/tag_ksz.c | 19 +++++++++++++++---- 1 file changed, 15 insertions(+), 4 deletions(-) diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c index c33d4bf17929..0b7564b53790 100644 --- a/net/dsa/tag_ksz.c +++ b/net/dsa/tag_ksz.c @@ -140,7 +140,12 @@ static struct sk_buff *ksz8795_xmit(struct sk_buff *skb, struct net_device *dev) static struct sk_buff *ksz8795_rcv(struct sk_buff *skb, struct net_device *dev) { - u8 *tag = skb_tail_pointer(skb) - KSZ_EGRESS_TAG_LEN; + u8 *tag; + + if (skb_linearize(skb)) + return NULL; + + tag = skb_tail_pointer(skb) - KSZ_EGRESS_TAG_LEN; return ksz_common_rcv(skb, dev, tag[0] & KSZ8795_TAIL_TAG_EG_PORT_M, KSZ_EGRESS_TAG_LEN); @@ -311,10 +316,16 @@ static struct sk_buff *ksz9477_xmit(struct sk_buff *skb, static struct sk_buff *ksz9477_rcv(struct sk_buff *skb, struct net_device *dev) { - /* Tag decoding */ - u8 *tag = skb_tail_pointer(skb) - KSZ_EGRESS_TAG_LEN; - unsigned int port = tag[0] & KSZ9477_TAIL_TAG_EG_PORT_M; unsigned int len = KSZ_EGRESS_TAG_LEN; + unsigned int port; + u8 *tag; + + if (skb_linearize(skb)) + return NULL; + + /* Tag decoding */ + tag = skb_tail_pointer(skb) - KSZ_EGRESS_TAG_LEN; + port = tag[0] & KSZ9477_TAIL_TAG_EG_PORT_M; /* Extra 4-bytes PTP timestamp */ if (tag[0] & KSZ9477_PTP_TAG_INDICATION) { -- 2.39.5

3 months, 3 weeks

2
1
0 0

[PATCH] wifi: ath11k: fix rx completion meta data corruption

by Johan Hovold

Add the missing memory barrier to make sure that the REO dest ring descriptor is read after the head pointer to avoid using stale data on weakly ordered architectures like aarch64. This may fix the ring-buffer corruption worked around by commit f9fff67d2d7c ("wifi: ath11k: Fix SKB corruption in REO destination ring") by silently discarding data, and may possibly also address user reported errors like: ath11k_pci 0006:01:00.0: msdu_done bit in attention is not set Tested-on: WCN6855 hw2.1 WLAN.HSP.1.1-03125-QCAHSPSWPL_V1_V2_SILICONZ_LITE-3.6510.41 Fixes: d5c65159f289 ("ath11k: driver for Qualcomm IEEE 802.11ax devices") Cc: stable(a)vger.kernel.org # 5.6 Link: https://bugzilla.kernel.org/show_bug.cgi?id=218005 Signed-off-by: Johan Hovold <johan+linaro(a)kernel.org> --- As I reported here: https://lore.kernel.org/lkml/Z9G5zEOcTdGKm7Ei@hovoldconsulting.com/ the ath11k and ath12k appear to be missing a number of memory barriers that are required on weakly ordered architectures like aarch64 to avoid memory corruption issues. Here's a fix for one more such case which people already seem to be hitting. Note that I've seen one "msdu_done" bit not set warning also with this patch so whether it helps with that at all remains to be seen. I'm CCing Jens and Steev that see these warnings frequently and that may be able to help out with testing. Johan drivers/net/wireless/ath/ath11k/dp_rx.c | 25 ++++++++++++++++--------- 1 file changed, 16 insertions(+), 9 deletions(-) diff --git a/drivers/net/wireless/ath/ath11k/dp_rx.c b/drivers/net/wireless/ath/ath11k/dp_rx.c index 029ecf51c9ef..0a57b337e4c6 100644 --- a/drivers/net/wireless/ath/ath11k/dp_rx.c +++ b/drivers/net/wireless/ath/ath11k/dp_rx.c @@ -2646,7 +2646,7 @@ int ath11k_dp_process_rx(struct ath11k_base *ab, int ring_id, struct ath11k *ar; struct hal_reo_dest_ring *desc; enum hal_reo_dest_ring_push_reason push_reason; - u32 cookie; + u32 cookie, info0, rx_msdu_info0, rx_mpdu_info0; int i; for (i = 0; i < MAX_RADIOS; i++) @@ -2659,11 +2659,14 @@ int ath11k_dp_process_rx(struct ath11k_base *ab, int ring_id, try_again: ath11k_hal_srng_access_begin(ab, srng); + /* Make sure descriptor is read after the head pointer. */ + dma_rmb(); + while (likely(desc = (struct hal_reo_dest_ring *)ath11k_hal_srng_dst_get_next_entry(ab, srng))) { cookie = FIELD_GET(BUFFER_ADDR_INFO1_SW_COOKIE, - desc->buf_addr_info.info1); + READ_ONCE(desc->buf_addr_info.info1)); buf_id = FIELD_GET(DP_RXDMA_BUF_COOKIE_BUF_ID, cookie); mac_id = FIELD_GET(DP_RXDMA_BUF_COOKIE_PDEV_ID, cookie); @@ -2692,8 +2695,9 @@ int ath11k_dp_process_rx(struct ath11k_base *ab, int ring_id, num_buffs_reaped[mac_id]++; + info0 = READ_ONCE(desc->info0); push_reason = FIELD_GET(HAL_REO_DEST_RING_INFO0_PUSH_REASON, - desc->info0); + info0); if (unlikely(push_reason != HAL_REO_DEST_RING_PUSH_REASON_ROUTING_INSTRUCTION)) { dev_kfree_skb_any(msdu); @@ -2701,18 +2705,21 @@ int ath11k_dp_process_rx(struct ath11k_base *ab, int ring_id, continue; } - rxcb->is_first_msdu = !!(desc->rx_msdu_info.info0 & + rx_msdu_info0 = READ_ONCE(desc->rx_msdu_info.info0); + rx_mpdu_info0 = READ_ONCE(desc->rx_mpdu_info.info0); + + rxcb->is_first_msdu = !!(rx_msdu_info0 & RX_MSDU_DESC_INFO0_FIRST_MSDU_IN_MPDU); - rxcb->is_last_msdu = !!(desc->rx_msdu_info.info0 & + rxcb->is_last_msdu = !!(rx_msdu_info0 & RX_MSDU_DESC_INFO0_LAST_MSDU_IN_MPDU); - rxcb->is_continuation = !!(desc->rx_msdu_info.info0 & + rxcb->is_continuation = !!(rx_msdu_info0 & RX_MSDU_DESC_INFO0_MSDU_CONTINUATION); rxcb->peer_id = FIELD_GET(RX_MPDU_DESC_META_DATA_PEER_ID, - desc->rx_mpdu_info.meta_data); + READ_ONCE(desc->rx_mpdu_info.meta_data)); rxcb->seq_no = FIELD_GET(RX_MPDU_DESC_INFO0_SEQ_NUM, - desc->rx_mpdu_info.info0); + rx_mpdu_info0); rxcb->tid = FIELD_GET(HAL_REO_DEST_RING_INFO0_RX_QUEUE_NUM, - desc->info0); + info0); rxcb->mac_id = mac_id; __skb_queue_tail(&msdu_list[mac_id], msdu); -- 2.48.1

3 months, 3 weeks

5
7
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror May 2025