February 2025 - Linux-stable-mirror

[PATCH 5.15.y] nfsd: release svc_expkey/svc_export with rcu_work

by lanbincn＠qq.com

From: Yang Erkun <yangerkun(a)huawei.com> commit f8c989a0c89a75d30f899a7cabdc14d72522bb8d upstream. The last reference for `cache_head` can be reduced to zero in `c_show` and `e_show`(using `rcu_read_lock` and `rcu_read_unlock`). Consequently, `svc_export_put` and `expkey_put` will be invoked, leading to two issues: 1. The `svc_export_put` will directly free ex_uuid. However, `e_show`/`c_show` will access `ex_uuid` after `cache_put`, which can trigger a use-after-free issue, shown below. ================================================================== BUG: KASAN: slab-use-after-free in svc_export_show+0x362/0x430 [nfsd] Read of size 1 at addr ff11000010fdc120 by task cat/870 CPU: 1 UID: 0 PID: 870 Comm: cat Not tainted 6.12.0-rc3+ #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.1-2.fc37 04/01/2014 Call Trace: <TASK> dump_stack_lvl+0x53/0x70 print_address_description.constprop.0+0x2c/0x3a0 print_report+0xb9/0x280 kasan_report+0xae/0xe0 svc_export_show+0x362/0x430 [nfsd] c_show+0x161/0x390 [sunrpc] seq_read_iter+0x589/0x770 seq_read+0x1e5/0x270 proc_reg_read+0xe1/0x140 vfs_read+0x125/0x530 ksys_read+0xc1/0x160 do_syscall_64+0x5f/0x170 entry_SYSCALL_64_after_hwframe+0x76/0x7e Allocated by task 830: kasan_save_stack+0x20/0x40 kasan_save_track+0x14/0x30 __kasan_kmalloc+0x8f/0xa0 __kmalloc_node_track_caller_noprof+0x1bc/0x400 kmemdup_noprof+0x22/0x50 svc_export_parse+0x8a9/0xb80 [nfsd] cache_do_downcall+0x71/0xa0 [sunrpc] cache_write_procfs+0x8e/0xd0 [sunrpc] proc_reg_write+0xe1/0x140 vfs_write+0x1a5/0x6d0 ksys_write+0xc1/0x160 do_syscall_64+0x5f/0x170 entry_SYSCALL_64_after_hwframe+0x76/0x7e Freed by task 868: kasan_save_stack+0x20/0x40 kasan_save_track+0x14/0x30 kasan_save_free_info+0x3b/0x60 __kasan_slab_free+0x37/0x50 kfree+0xf3/0x3e0 svc_export_put+0x87/0xb0 [nfsd] cache_purge+0x17f/0x1f0 [sunrpc] nfsd_destroy_serv+0x226/0x2d0 [nfsd] nfsd_svc+0x125/0x1e0 [nfsd] write_threads+0x16a/0x2a0 [nfsd] nfsctl_transaction_write+0x74/0xa0 [nfsd] vfs_write+0x1a5/0x6d0 ksys_write+0xc1/0x160 do_syscall_64+0x5f/0x170 entry_SYSCALL_64_after_hwframe+0x76/0x7e 2. We cannot sleep while using `rcu_read_lock`/`rcu_read_unlock`. However, `svc_export_put`/`expkey_put` will call path_put, which subsequently triggers a sleeping operation due to the following `dput`. ============================= WARNING: suspicious RCU usage 5.10.0-dirty #141 Not tainted ----------------------------- ... Call Trace: dump_stack+0x9a/0xd0 ___might_sleep+0x231/0x240 dput+0x39/0x600 path_put+0x1b/0x30 svc_export_put+0x17/0x80 e_show+0x1c9/0x200 seq_read_iter+0x63f/0x7c0 seq_read+0x226/0x2d0 vfs_read+0x113/0x2c0 ksys_read+0xc9/0x170 do_syscall_64+0x33/0x40 entry_SYSCALL_64_after_hwframe+0x67/0xd1 Fix these issues by using `rcu_work` to help release `svc_expkey`/`svc_export`. This approach allows for an asynchronous context to invoke `path_put` and also facilitates the freeing of `uuid/exp/key` after an RCU grace period. Fixes: 9ceddd9da134 ("knfsd: Allow lockless lookups of the exports") Signed-off-by: Yang Erkun <yangerkun(a)huawei.com> Reviewed-by: Jeff Layton <jlayton(a)kernel.org> Signed-off-by: Chuck Lever <chuck.lever(a)oracle.com> Signed-off-by: Bin Lan <lanbincn(a)qq.com> --- fs/nfsd/export.c | 31 +++++++++++++++++++++++++------ fs/nfsd/export.h | 4 ++-- 2 files changed, 27 insertions(+), 8 deletions(-) diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index 39228bd7492a..78db46f6cbc6 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -40,15 +40,24 @@ #define EXPKEY_HASHMAX (1 << EXPKEY_HASHBITS) #define EXPKEY_HASHMASK (EXPKEY_HASHMAX -1) -static void expkey_put(struct kref *ref) +static void expkey_put_work(struct work_struct *work) { - struct svc_expkey *key = container_of(ref, struct svc_expkey, h.ref); + struct svc_expkey *key = + container_of(to_rcu_work(work), struct svc_expkey, ek_rcu_work); if (test_bit(CACHE_VALID, &key->h.flags) && !test_bit(CACHE_NEGATIVE, &key->h.flags)) path_put(&key->ek_path); auth_domain_put(key->ek_client); - kfree_rcu(key, ek_rcu); + kfree(key); +} + +static void expkey_put(struct kref *ref) +{ + struct svc_expkey *key = container_of(ref, struct svc_expkey, h.ref); + + INIT_RCU_WORK(&key->ek_rcu_work, expkey_put_work); + queue_rcu_work(system_wq, &key->ek_rcu_work); } static int expkey_upcall(struct cache_detail *cd, struct cache_head *h) @@ -351,16 +360,26 @@ static void export_stats_destroy(struct export_stats *stats) EXP_STATS_COUNTERS_NUM); } -static void svc_export_put(struct kref *ref) +static void svc_export_put_work(struct work_struct *work) { - struct svc_export *exp = container_of(ref, struct svc_export, h.ref); + struct svc_export *exp = + container_of(to_rcu_work(work), struct svc_export, ex_rcu_work); + path_put(&exp->ex_path); auth_domain_put(exp->ex_client); nfsd4_fslocs_free(&exp->ex_fslocs); export_stats_destroy(exp->ex_stats); kfree(exp->ex_stats); kfree(exp->ex_uuid); - kfree_rcu(exp, ex_rcu); + kfree(exp); +} + +static void svc_export_put(struct kref *ref) +{ + struct svc_export *exp = container_of(ref, struct svc_export, h.ref); + + INIT_RCU_WORK(&exp->ex_rcu_work, svc_export_put_work); + queue_rcu_work(system_wq, &exp->ex_rcu_work); } static int svc_export_upcall(struct cache_detail *cd, struct cache_head *h) diff --git a/fs/nfsd/export.h b/fs/nfsd/export.h index f73e23bb24a1..fa545d8dcc36 100644 --- a/fs/nfsd/export.h +++ b/fs/nfsd/export.h @@ -75,7 +75,7 @@ struct svc_export { u32 ex_layout_types; struct nfsd4_deviceid_map *ex_devid_map; struct cache_detail *cd; - struct rcu_head ex_rcu; + struct rcu_work ex_rcu_work; struct export_stats *ex_stats; }; @@ -91,7 +91,7 @@ struct svc_expkey { u32 ek_fsid[6]; struct path ek_path; - struct rcu_head ek_rcu; + struct rcu_work ek_rcu_work; }; #define EX_ISSYNC(exp) (!((exp)->ex_flags & NFSEXP_ASYNC)) -- 2.43.0

6 months

3
2
0 0

+ dma-kmsan-export-kmsan_handle_dma-for-modules.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: dma: kmsan: export kmsan_handle_dma() for modules has been added to the -mm mm-hotfixes-unstable branch. Its filename is dma-kmsan-export-kmsan_handle_dma-for-modules.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: Sebastian Andrzej Siewior <bigeasy(a)linutronix.de> Subject: dma: kmsan: export kmsan_handle_dma() for modules Date: Tue, 18 Feb 2025 10:14:11 +0100 kmsan_handle_dma() is used by virtio_ring() which can be built as a module. kmsan_handle_dma() needs to be exported otherwise building the virtio_ring fails. Export kmsan_handle_dma for modules. Link: https://lkml.kernel.org/r/20250218091411.MMS3wBN9@linutronix.de Reported-by: kernel test robot <lkp(a)intel.com> Closes: https://lore.kernel.org/oe-kbuild-all/202502150634.qjxwSeJR-lkp@intel.com/ Fixes: 7ade4f10779cb ("dma: kmsan: unpoison DMA mappings") Signed-off-by: Sebastian Andrzej Siewior <bigeasy(a)linutronix.de> Cc: Alexander Potapenko <glider(a)google.com> Cc: Dmitriy Vyukov <dvyukov(a)google.com> Cc: Macro Elver <elver(a)google.com> Cc: Peter Zijlstra (Intel) <peterz(a)infradead.org> Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/kmsan/hooks.c | 1 + 1 file changed, 1 insertion(+) --- a/mm/kmsan/hooks.c~dma-kmsan-export-kmsan_handle_dma-for-modules +++ a/mm/kmsan/hooks.c @@ -357,6 +357,7 @@ void kmsan_handle_dma(struct page *page, size -= to_go; } } +EXPORT_SYMBOL_GPL(kmsan_handle_dma); void kmsan_handle_dma_sg(struct scatterlist *sg, int nents, enum dma_data_direction dir) _ Patches currently in -mm which might be from bigeasy(a)linutronix.de are dma-kmsan-export-kmsan_handle_dma-for-modules.patch rcu-provide-a-static-initializer-for-hlist_nulls_head.patch ucount-replace-get_ucounts_or_wrap-with-atomic_inc_not_zero.patch ucount-use-rcu-for-ucounts-lookups.patch ucount-use-rcuref_t-for-reference-counting.patch

6 months

1
0
0 0

+ mm-hugetlb-wait-for-hugetlb-folios-to-be-freed.patch added to mm-unstable branch

by Andrew Morton

The patch titled Subject: mm/hugetlb: wait for hugetlb folios to be freed has been added to the -mm mm-unstable branch. Its filename is mm-hugetlb-wait-for-hugetlb-folios-to-be-freed.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-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: Ge Yang <yangge1116(a)126.com> Subject: mm/hugetlb: wait for hugetlb folios to be freed Date: Tue, 18 Feb 2025 19:40:28 +0800 Since the introduction of commit c77c0a8ac4c52 ("mm/hugetlb: defer freeing of huge pages if in non-task context"), which supports deferring the freeing of hugetlb pages, the allocation of contiguous memory through cma_alloc() may fail probabilistically. In the CMA allocation process, if it is found that the CMA area is occupied by in-use hugetlb folios, these in-use hugetlb folios need to be migrated to another location. When there are no available hugetlb folios in the free hugetlb pool during the migration of in-use hugetlb folios, new folios are allocated from the buddy system. A temporary state is set on the newly allocated folio. Upon completion of the hugetlb folio migration, the temporary state is transferred from the new folios to the old folios. Normally, when the old folios with the temporary state are freed, it is directly released back to the buddy system. However, due to the deferred freeing of hugetlb pages, the PageBuddy() check fails, ultimately leading to the failure of cma_alloc(). Here is a simplified call trace illustrating the process: cma_alloc() ->__alloc_contig_migrate_range() // Migrate in-use hugetlb folios ->unmap_and_move_huge_page() ->folio_putback_hugetlb() // Free old folios ->test_pages_isolated() ->__test_page_isolated_in_pageblock() ->PageBuddy(page) // Check if the page is in buddy To resolve this issue, we have implemented a function named wait_for_freed_hugetlb_folios(). This function ensures that the hugetlb folios are properly released back to the buddy system after their migration is completed. By invoking wait_for_freed_hugetlb_folios() before calling PageBuddy(), we ensure that PageBuddy() will succeed. Link: https://lkml.kernel.org/r/1739878828-9960-1-git-send-email-yangge1116@126.c… Fixes: c77c0a8ac4c52 ("mm/hugetlb: defer freeing of huge pages if in non-task context") Signed-off-by: Ge Yang <yangge1116(a)126.com> Acked-by: David Hildenbrand <david(a)redhat.com> Cc: Baolin Wang <baolin.wang(a)linux.alibaba.com> Cc: Barry Song <21cnbao(a)gmail.com> Cc: Muchun Song <muchun.song(a)linux.dev> Cc: Oscar Salvador <osalvador(a)suse.de> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- include/linux/hugetlb.h | 5 +++++ mm/hugetlb.c | 5 +++++ mm/page_isolation.c | 10 ++++++++++ 3 files changed, 20 insertions(+) --- a/include/linux/hugetlb.h~mm-hugetlb-wait-for-hugetlb-folios-to-be-freed +++ a/include/linux/hugetlb.h @@ -697,6 +697,7 @@ bool hugetlb_bootmem_page_zones_valid(in int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list); int replace_free_hugepage_folios(unsigned long start_pfn, unsigned long end_pfn); +void wait_for_freed_hugetlb_folios(void); struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, unsigned long addr, bool cow_from_owner); struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid, @@ -1092,6 +1093,10 @@ static inline int replace_free_hugepage_ return 0; } +static inline void wait_for_freed_hugetlb_folios(void) +{ +} + static inline struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, unsigned long addr, bool cow_from_owner) --- a/mm/hugetlb.c~mm-hugetlb-wait-for-hugetlb-folios-to-be-freed +++ a/mm/hugetlb.c @@ -2955,6 +2955,11 @@ int replace_free_hugepage_folios(unsigne return ret; } +void wait_for_freed_hugetlb_folios(void) +{ + flush_work(&free_hpage_work); +} + typedef enum { /* * For either 0/1: we checked the per-vma resv map, and one resv --- a/mm/page_isolation.c~mm-hugetlb-wait-for-hugetlb-folios-to-be-freed +++ a/mm/page_isolation.c @@ -615,6 +615,16 @@ int test_pages_isolated(unsigned long st int ret; /* + * Due to the deferred freeing of hugetlb folios, the hugepage folios may + * not immediately release to the buddy system. This can cause PageBuddy() + * to fail in __test_page_isolated_in_pageblock(). To ensure that the + * hugetlb folios are properly released back to the buddy system, we + * invoke the wait_for_freed_hugetlb_folios() function to wait for the + * release to complete. + */ + wait_for_freed_hugetlb_folios(); + + /* * Note: pageblock_nr_pages != MAX_PAGE_ORDER. Then, chunks of free * pages are not aligned to pageblock_nr_pages. * Then we just check migratetype first. _ Patches currently in -mm which might be from yangge1116(a)126.com are mm-hugetlb-wait-for-hugepage-folios-to-be-freed.patch mm-hugetlb-wait-for-hugetlb-folios-to-be-freed.patch

6 months

1
0
0 0

Re: [REGRESSION] xfs kernel panic

by Lorenz Brun

Am Mo., 17. Feb. 2025 um 16:00 Uhr schrieb Lorenz Brun <lorenz(a)monogon.tech>: > > Hi everyone, > > Linux 6.12.14 (released today) contains a regression for XFS, causing > a kernel panic after just a few seconds of working with a > freshly-created (xfsprogs 6.9) XFS filesystem. I have not yet bisected > this because I wanted to get this report out ASAP but I'm going to do > that now. There are multiple associated stack traces, but all of them > have xfs_buf_offset as the faulting function. > > Example backtrace: > [ 31.745932] BUG: kernel NULL pointer dereference, address: 0000000000000098 > [ 31.746590] #PF: supervisor read access in kernel mode > [ 31.747072] #PF: error_code(0x0000) - not-present page > [ 31.747537] PGD 5bee067 P4D 5bee067 PUD 5bef067 PMD 0 > [ 31.748016] Oops: Oops: 0000 [#1] PREEMPT SMP NOPTI > [ 31.748459] CPU: 0 UID: 0 PID: 116 Comm: xfsaild/vda4 Not tainted > 6.12.14-metropolis #1 9b2470be3d7713b818a3236e4a2804dd9cbef735 > [ 31.749490] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), > BIOS 0.0.0 02/06/2015 > [ 31.750340] RIP: 0010:xfs_buf_offset+0x9/0x50 > [ 31.750823] Code: 08 5b e9 8a 2c c4 00 66 2e 0f 1f 84 00 00 00 00 > 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 66 0f 1f 00 0f 1f > 44 00 00 <48> 8b 87 98 00 00 00 48 85 c0 75 2e 48 8b 87 00 01 00 00 48 > 89 f2 > [ 31.752775] RSP: 0018:ffffbf50c07abdb8 EFLAGS: 00010246 > [ 31.753343] RAX: 0000000000000002 RBX: ffff9c0985817d58 RCX: 0000000000000016 > [ 31.754103] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 > [ 31.754734] RBP: 0000000000000000 R08: ffff9c09fb704000 R09: 00000000e0be9fc4 > [ 31.755396] R10: 0000000000000000 R11: ffff9c0985827df8 R12: ffff9c09fb57ff58 > [ 31.756078] R13: ffff9c0985817eb0 R14: ffff9c09fb704000 R15: ffff9c0985817f00 > [ 31.756764] FS: 0000000000000000(0000) GS:ffff9c09fc000000(0000) > knlGS:0000000000000000 > [ 31.757529] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 > [ 31.758041] CR2: 0000000000000098 CR3: 0000000005b70000 CR4: 0000000000350ef0 > [ 31.758696] Call Trace: > [ 31.758940] <TASK> > [ 31.759172] ? __die+0x56/0x97 > [ 31.759473] ? page_fault_oops+0x15c/0x2d0 > [ 31.759853] ? exc_page_fault+0x4c5/0x790 > [ 31.760237] ? asm_exc_page_fault+0x26/0x30 > [ 31.760637] ? xfs_buf_offset+0x9/0x50 > [ 31.761002] ? srso_return_thunk+0x5/0x5f > [ 31.761409] xfs_qm_dqflush+0xd0/0x350 > [ 31.761799] xfs_qm_dquot_logitem_push+0xe9/0x140 > [ 31.762253] xfsaild+0x347/0xa10 > [ 31.762567] ? srso_return_thunk+0x5/0x5f > [ 31.762952] ? srso_return_thunk+0x5/0x5f > [ 31.763325] ? __pfx_xfsaild+0x10/0x10 > [ 31.763665] kthread+0xd2/0x100 > [ 31.763985] ? __pfx_kthread+0x10/0x10 > [ 31.764342] ret_from_fork+0x34/0x50 > [ 31.764675] ? __pfx_kthread+0x10/0x10 > [ 31.765029] ret_from_fork_asm+0x1a/0x30 > [ 31.765408] </TASK> > [ 31.765618] Modules linked in: kvm_amd > [ 31.765978] CR2: 0000000000000098 > [ 31.766297] ---[ end trace 0000000000000000 ]--- > [ 32.371004] RIP: 0010:xfs_buf_offset+0x9/0x50 > [ 32.371453] Code: 08 5b e9 8a 2c c4 00 66 2e 0f 1f 84 00 00 00 00 > 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 66 0f 1f 00 0f 1f > 44 00 00 <48> 8b 87 98 00 00 00 48 85 c0 75 2e 48 8b 87 00 01 00 00 48 > 89 f2 > [ 32.373133] RSP: 0018:ffffbf50c07abdb8 EFLAGS: 00010246 > [ 32.373611] RAX: 0000000000000002 RBX: ffff9c0985817d58 RCX: 0000000000000016 > [ 32.374275] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 > [ 32.374921] RBP: 0000000000000000 R08: ffff9c09fb704000 R09: 00000000e0be9fc4 > [ 32.375720] R10: 0000000000000000 R11: ffff9c0985827df8 R12: ffff9c09fb57ff58 > [ 32.376376] R13: ffff9c0985817eb0 R14: ffff9c09fb704000 R15: ffff9c0985817f00 > [ 32.377027] FS: 0000000000000000(0000) GS:ffff9c09fc000000(0000) > knlGS:0000000000000000 > [ 32.377761] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 > [ 32.378292] CR2: 0000000000000098 CR3: 0000000005b70000 CR4: 0000000000350ef0 > [ 32.378940] Kernel panic - not syncing: Fatal exception > [ 32.379492] Kernel Offset: 0x2a600000 from 0xffffffff81000000 > (relocation range: 0xffffffff80000000-0xffffffffbfffffff) > > #regzbot introduced: v6.12.13..v6.12.14 > > Regards, > Lorenz Hi everyone, I root-caused this to 5808d420 ("xfs: attach dquot buffer to dquot log item buffer"), but needs reverting of the 3 follow-up commits (d331fc15, ee6984a2 and 84307caf) as well as they depend on the broken one. With that 6.12.14 passes our test suite again. Reproduction should be rather easy by just creating a fresh filesystem, mounting with "prjquota" and performing I/O. Regards, Lorenz

6 months

3
4
0 0

[PATCH AUTOSEL 5.4 1/3] HID: intel-ish-hid: fix the length of MNG_SYNC_FW_CLOCK in doorbell

by Sasha Levin

From: Zhang Lixu <lixu.zhang(a)intel.com> [ Upstream commit 4b54ae69197b9f416baa0fceadff7e89075f8454 ] The timestamps in the Firmware log and HID sensor samples are incorrect. They show 1970-01-01 because the current IPC driver only uses the first 8 bytes of bootup time when synchronizing time with the firmware. The firmware converts the bootup time to UTC time, which results in the display of 1970-01-01. In write_ipc_from_queue(), when sending the MNG_SYNC_FW_CLOCK message, the clock is updated according to the definition of ipc_time_update_msg. However, in _ish_sync_fw_clock(), the message length is specified as the size of uint64_t when building the doorbell. As a result, the firmware only receives the first 8 bytes of struct ipc_time_update_msg. This patch corrects the length in the doorbell to ensure the entire ipc_time_update_msg is sent, fixing the timestamp issue. Signed-off-by: Zhang Lixu <lixu.zhang(a)intel.com> Acked-by: Srinivas Pandruvada <srinivas.pandruvada(a)linux.intel.com> Signed-off-by: Jiri Kosina <jkosina(a)suse.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- drivers/hid/intel-ish-hid/ipc/ipc.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/hid/intel-ish-hid/ipc/ipc.c b/drivers/hid/intel-ish-hid/ipc/ipc.c index 8f8dfdf64833e..871f043eeba1e 100644 --- a/drivers/hid/intel-ish-hid/ipc/ipc.c +++ b/drivers/hid/intel-ish-hid/ipc/ipc.c @@ -549,14 +549,14 @@ static void fw_reset_work_fn(struct work_struct *unused) static void _ish_sync_fw_clock(struct ishtp_device *dev) { static unsigned long prev_sync; - uint64_t usec; + struct ipc_time_update_msg time = {}; if (prev_sync && jiffies - prev_sync < 20 * HZ) return; prev_sync = jiffies; - usec = ktime_to_us(ktime_get_boottime()); - ipc_send_mng_msg(dev, MNG_SYNC_FW_CLOCK, &usec, sizeof(uint64_t)); + /* The fields of time would be updated while sending message */ + ipc_send_mng_msg(dev, MNG_SYNC_FW_CLOCK, &time, sizeof(time)); } /** -- 2.39.5

6 months

1
2
0 0

[PATCH AUTOSEL 5.10 1/4] HID: intel-ish-hid: fix the length of MNG_SYNC_FW_CLOCK in doorbell

by Sasha Levin

From: Zhang Lixu <lixu.zhang(a)intel.com> [ Upstream commit 4b54ae69197b9f416baa0fceadff7e89075f8454 ] The timestamps in the Firmware log and HID sensor samples are incorrect. They show 1970-01-01 because the current IPC driver only uses the first 8 bytes of bootup time when synchronizing time with the firmware. The firmware converts the bootup time to UTC time, which results in the display of 1970-01-01. In write_ipc_from_queue(), when sending the MNG_SYNC_FW_CLOCK message, the clock is updated according to the definition of ipc_time_update_msg. However, in _ish_sync_fw_clock(), the message length is specified as the size of uint64_t when building the doorbell. As a result, the firmware only receives the first 8 bytes of struct ipc_time_update_msg. This patch corrects the length in the doorbell to ensure the entire ipc_time_update_msg is sent, fixing the timestamp issue. Signed-off-by: Zhang Lixu <lixu.zhang(a)intel.com> Acked-by: Srinivas Pandruvada <srinivas.pandruvada(a)linux.intel.com> Signed-off-by: Jiri Kosina <jkosina(a)suse.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- drivers/hid/intel-ish-hid/ipc/ipc.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/hid/intel-ish-hid/ipc/ipc.c b/drivers/hid/intel-ish-hid/ipc/ipc.c index a45ac7fa417b9..da896f5c74424 100644 --- a/drivers/hid/intel-ish-hid/ipc/ipc.c +++ b/drivers/hid/intel-ish-hid/ipc/ipc.c @@ -549,14 +549,14 @@ static void fw_reset_work_fn(struct work_struct *unused) static void _ish_sync_fw_clock(struct ishtp_device *dev) { static unsigned long prev_sync; - uint64_t usec; + struct ipc_time_update_msg time = {}; if (prev_sync && jiffies - prev_sync < 20 * HZ) return; prev_sync = jiffies; - usec = ktime_to_us(ktime_get_boottime()); - ipc_send_mng_msg(dev, MNG_SYNC_FW_CLOCK, &usec, sizeof(uint64_t)); + /* The fields of time would be updated while sending message */ + ipc_send_mng_msg(dev, MNG_SYNC_FW_CLOCK, &time, sizeof(time)); } /** -- 2.39.5

6 months

1
3
0 0

[PATCH AUTOSEL 5.15 1/6] HID: intel-ish-hid: fix the length of MNG_SYNC_FW_CLOCK in doorbell

by Sasha Levin

From: Zhang Lixu <lixu.zhang(a)intel.com> [ Upstream commit 4b54ae69197b9f416baa0fceadff7e89075f8454 ] The timestamps in the Firmware log and HID sensor samples are incorrect. They show 1970-01-01 because the current IPC driver only uses the first 8 bytes of bootup time when synchronizing time with the firmware. The firmware converts the bootup time to UTC time, which results in the display of 1970-01-01. In write_ipc_from_queue(), when sending the MNG_SYNC_FW_CLOCK message, the clock is updated according to the definition of ipc_time_update_msg. However, in _ish_sync_fw_clock(), the message length is specified as the size of uint64_t when building the doorbell. As a result, the firmware only receives the first 8 bytes of struct ipc_time_update_msg. This patch corrects the length in the doorbell to ensure the entire ipc_time_update_msg is sent, fixing the timestamp issue. Signed-off-by: Zhang Lixu <lixu.zhang(a)intel.com> Acked-by: Srinivas Pandruvada <srinivas.pandruvada(a)linux.intel.com> Signed-off-by: Jiri Kosina <jkosina(a)suse.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- drivers/hid/intel-ish-hid/ipc/ipc.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/hid/intel-ish-hid/ipc/ipc.c b/drivers/hid/intel-ish-hid/ipc/ipc.c index ba45605fc6b52..a48f7cd514b0f 100644 --- a/drivers/hid/intel-ish-hid/ipc/ipc.c +++ b/drivers/hid/intel-ish-hid/ipc/ipc.c @@ -577,14 +577,14 @@ static void fw_reset_work_fn(struct work_struct *unused) static void _ish_sync_fw_clock(struct ishtp_device *dev) { static unsigned long prev_sync; - uint64_t usec; + struct ipc_time_update_msg time = {}; if (prev_sync && jiffies - prev_sync < 20 * HZ) return; prev_sync = jiffies; - usec = ktime_to_us(ktime_get_boottime()); - ipc_send_mng_msg(dev, MNG_SYNC_FW_CLOCK, &usec, sizeof(uint64_t)); + /* The fields of time would be updated while sending message */ + ipc_send_mng_msg(dev, MNG_SYNC_FW_CLOCK, &time, sizeof(time)); } /** -- 2.39.5

6 months

1
5
0 0

[PATCH AUTOSEL 6.1 01/13] HID: intel-ish-hid: fix the length of MNG_SYNC_FW_CLOCK in doorbell

by Sasha Levin

From: Zhang Lixu <lixu.zhang(a)intel.com> [ Upstream commit 4b54ae69197b9f416baa0fceadff7e89075f8454 ] The timestamps in the Firmware log and HID sensor samples are incorrect. They show 1970-01-01 because the current IPC driver only uses the first 8 bytes of bootup time when synchronizing time with the firmware. The firmware converts the bootup time to UTC time, which results in the display of 1970-01-01. In write_ipc_from_queue(), when sending the MNG_SYNC_FW_CLOCK message, the clock is updated according to the definition of ipc_time_update_msg. However, in _ish_sync_fw_clock(), the message length is specified as the size of uint64_t when building the doorbell. As a result, the firmware only receives the first 8 bytes of struct ipc_time_update_msg. This patch corrects the length in the doorbell to ensure the entire ipc_time_update_msg is sent, fixing the timestamp issue. Signed-off-by: Zhang Lixu <lixu.zhang(a)intel.com> Acked-by: Srinivas Pandruvada <srinivas.pandruvada(a)linux.intel.com> Signed-off-by: Jiri Kosina <jkosina(a)suse.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- drivers/hid/intel-ish-hid/ipc/ipc.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/hid/intel-ish-hid/ipc/ipc.c b/drivers/hid/intel-ish-hid/ipc/ipc.c index dd5fc60874ba1..b1a41c90c5741 100644 --- a/drivers/hid/intel-ish-hid/ipc/ipc.c +++ b/drivers/hid/intel-ish-hid/ipc/ipc.c @@ -577,14 +577,14 @@ static void fw_reset_work_fn(struct work_struct *unused) static void _ish_sync_fw_clock(struct ishtp_device *dev) { static unsigned long prev_sync; - uint64_t usec; + struct ipc_time_update_msg time = {}; if (prev_sync && time_before(jiffies, prev_sync + 20 * HZ)) return; prev_sync = jiffies; - usec = ktime_to_us(ktime_get_boottime()); - ipc_send_mng_msg(dev, MNG_SYNC_FW_CLOCK, &usec, sizeof(uint64_t)); + /* The fields of time would be updated while sending message */ + ipc_send_mng_msg(dev, MNG_SYNC_FW_CLOCK, &time, sizeof(time)); } /** -- 2.39.5

6 months

1
12
0 0

[PATCH AUTOSEL 6.12 01/31] sched_ext: selftests/dsp_local_on: Fix sporadic failures

by Sasha Levin

From: Tejun Heo <tj(a)kernel.org> [ Upstream commit e9fe182772dcb2630964724fd93e9c90b68ea0fd ] dsp_local_on has several incorrect assumptions, one of which is that p->nr_cpus_allowed always tracks p->cpus_ptr. This is not true when a task is scheduled out while migration is disabled - p->cpus_ptr is temporarily overridden to the previous CPU while p->nr_cpus_allowed remains unchanged. This led to sporadic test faliures when dsp_local_on_dispatch() tries to put a migration disabled task to a different CPU. Fix it by keeping the previous CPU when migration is disabled. There are SCX schedulers that make use of p->nr_cpus_allowed. They should also implement explicit handling for p->migration_disabled. Signed-off-by: Tejun Heo <tj(a)kernel.org> Reported-by: Ihor Solodrai <ihor.solodrai(a)pm.me> Cc: Andrea Righi <arighi(a)nvidia.com> Cc: Changwoo Min <changwoo(a)igalia.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- tools/testing/selftests/sched_ext/dsp_local_on.bpf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c b/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c index c9a2da0575a0f..eea06decb6f59 100644 --- a/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c +++ b/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c @@ -43,7 +43,7 @@ void BPF_STRUCT_OPS(dsp_local_on_dispatch, s32 cpu, struct task_struct *prev) if (!p) return; - if (p->nr_cpus_allowed == nr_cpus) + if (p->nr_cpus_allowed == nr_cpus && !p->migration_disabled) target = bpf_get_prandom_u32() % nr_cpus; else target = scx_bpf_task_cpu(p); -- 2.39.5

6 months

1
30
0 0

[PATCH AUTOSEL 6.13 01/31] sched_ext: selftests/dsp_local_on: Fix sporadic failures

by Sasha Levin

From: Tejun Heo <tj(a)kernel.org> [ Upstream commit e9fe182772dcb2630964724fd93e9c90b68ea0fd ] dsp_local_on has several incorrect assumptions, one of which is that p->nr_cpus_allowed always tracks p->cpus_ptr. This is not true when a task is scheduled out while migration is disabled - p->cpus_ptr is temporarily overridden to the previous CPU while p->nr_cpus_allowed remains unchanged. This led to sporadic test faliures when dsp_local_on_dispatch() tries to put a migration disabled task to a different CPU. Fix it by keeping the previous CPU when migration is disabled. There are SCX schedulers that make use of p->nr_cpus_allowed. They should also implement explicit handling for p->migration_disabled. Signed-off-by: Tejun Heo <tj(a)kernel.org> Reported-by: Ihor Solodrai <ihor.solodrai(a)pm.me> Cc: Andrea Righi <arighi(a)nvidia.com> Cc: Changwoo Min <changwoo(a)igalia.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- tools/testing/selftests/sched_ext/dsp_local_on.bpf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c b/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c index fbda6bf546712..758b479bd1ee1 100644 --- a/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c +++ b/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c @@ -43,7 +43,7 @@ void BPF_STRUCT_OPS(dsp_local_on_dispatch, s32 cpu, struct task_struct *prev) if (!p) return; - if (p->nr_cpus_allowed == nr_cpus) + if (p->nr_cpus_allowed == nr_cpus && !p->migration_disabled) target = bpf_get_prandom_u32() % nr_cpus; else target = scx_bpf_task_cpu(p); -- 2.39.5

6 months

1
30
0 0

[PATCH v3] HID: corsair-void: Update power supply values with a unified work handler

by Stuart Hayhurst

corsair_void_process_receiver can be called from an interrupt context, locking battery_mutex in it was causing a kernel panic. Fix it by moving the critical section into its own work, sharing this work with battery_add_work and battery_remove_work to remove the need for any locking Closes: https://bugzilla.suse.com/show_bug.cgi?id=1236843 Fixes: 6ea2a6fd3872 ("HID: corsair-void: Add Corsair Void headset family driver") Cc: stable(a)vger.kernel.org Signed-off-by: Stuart Hayhurst <stuart.a.hayhurst(a)gmail.com> --- v2 -> v3: - Use an enum instead of a define for battery flag values - Use an integer instead of BIT() for the bit index - Drop unhelpful comments - Simplify corsair_void_battery_work_handler logic - Remove extra newline in commit message v1 -> v2: - Actually remove the mutex --- drivers/hid/hid-corsair-void.c | 83 ++++++++++++++++++---------------- 1 file changed, 43 insertions(+), 40 deletions(-) diff --git a/drivers/hid/hid-corsair-void.c b/drivers/hid/hid-corsair-void.c index 56e858066c3c..afbd67aa9719 100644 --- a/drivers/hid/hid-corsair-void.c +++ b/drivers/hid/hid-corsair-void.c @@ -71,11 +71,9 @@ #include <linux/bitfield.h> #include <linux/bitops.h> -#include <linux/cleanup.h> #include <linux/device.h> #include <linux/hid.h> #include <linux/module.h> -#include <linux/mutex.h> #include <linux/power_supply.h> #include <linux/usb.h> #include <linux/workqueue.h> @@ -120,6 +118,12 @@ enum { CORSAIR_VOID_BATTERY_CHARGING = 5, }; +enum { + CORSAIR_VOID_ADD_BATTERY = 0, + CORSAIR_VOID_REMOVE_BATTERY = 1, + CORSAIR_VOID_UPDATE_BATTERY = 2, +}; + static enum power_supply_property corsair_void_battery_props[] = { POWER_SUPPLY_PROP_STATUS, POWER_SUPPLY_PROP_PRESENT, @@ -155,12 +159,12 @@ struct corsair_void_drvdata { struct power_supply *battery; struct power_supply_desc battery_desc; - struct mutex battery_mutex; struct delayed_work delayed_status_work; struct delayed_work delayed_firmware_work; - struct work_struct battery_remove_work; - struct work_struct battery_add_work; + + unsigned long battery_work_flags; + struct work_struct battery_work; }; /* @@ -260,11 +264,9 @@ static void corsair_void_process_receiver(struct corsair_void_drvdata *drvdata, /* Inform power supply if battery values changed */ if (memcmp(&orig_battery_data, battery_data, sizeof(*battery_data))) { - scoped_guard(mutex, &drvdata->battery_mutex) { - if (drvdata->battery) { - power_supply_changed(drvdata->battery); - } - } + set_bit(CORSAIR_VOID_UPDATE_BATTERY, + &drvdata->battery_work_flags); + schedule_work(&drvdata->battery_work); } } @@ -536,29 +538,11 @@ static void corsair_void_firmware_work_handler(struct work_struct *work) } -static void corsair_void_battery_remove_work_handler(struct work_struct *work) -{ - struct corsair_void_drvdata *drvdata; - - drvdata = container_of(work, struct corsair_void_drvdata, - battery_remove_work); - scoped_guard(mutex, &drvdata->battery_mutex) { - if (drvdata->battery) { - power_supply_unregister(drvdata->battery); - drvdata->battery = NULL; - } - } -} - -static void corsair_void_battery_add_work_handler(struct work_struct *work) +static void corsair_void_add_battery(struct corsair_void_drvdata *drvdata) { - struct corsair_void_drvdata *drvdata; struct power_supply_config psy_cfg = {}; struct power_supply *new_supply; - drvdata = container_of(work, struct corsair_void_drvdata, - battery_add_work); - guard(mutex)(&drvdata->battery_mutex); if (drvdata->battery) return; @@ -583,16 +567,42 @@ static void corsair_void_battery_add_work_handler(struct work_struct *work) drvdata->battery = new_supply; } +static void corsair_void_battery_work_handler(struct work_struct *work) +{ + struct corsair_void_drvdata *drvdata = container_of(work, + struct corsair_void_drvdata, battery_work); + + bool add_battery = test_and_clear_bit(CORSAIR_VOID_ADD_BATTERY, + &drvdata->battery_work_flags); + bool remove_battery = test_and_clear_bit(CORSAIR_VOID_REMOVE_BATTERY, + &drvdata->battery_work_flags); + bool update_battery = test_and_clear_bit(CORSAIR_VOID_UPDATE_BATTERY, + &drvdata->battery_work_flags); + + if (add_battery && !remove_battery) { + corsair_void_add_battery(drvdata); + } else if (remove_battery && !add_battery && drvdata->battery) { + power_supply_unregister(drvdata->battery); + drvdata->battery = NULL; + } + + if (update_battery && drvdata->battery) + power_supply_changed(drvdata->battery); + +} + static void corsair_void_headset_connected(struct corsair_void_drvdata *drvdata) { - schedule_work(&drvdata->battery_add_work); + set_bit(CORSAIR_VOID_ADD_BATTERY, &drvdata->battery_work_flags); + schedule_work(&drvdata->battery_work); schedule_delayed_work(&drvdata->delayed_firmware_work, msecs_to_jiffies(100)); } static void corsair_void_headset_disconnected(struct corsair_void_drvdata *drvdata) { - schedule_work(&drvdata->battery_remove_work); + set_bit(CORSAIR_VOID_REMOVE_BATTERY, &drvdata->battery_work_flags); + schedule_work(&drvdata->battery_work); corsair_void_set_unknown_wireless_data(drvdata); corsair_void_set_unknown_batt(drvdata); @@ -678,13 +688,7 @@ static int corsair_void_probe(struct hid_device *hid_dev, drvdata->battery_desc.get_property = corsair_void_battery_get_property; drvdata->battery = NULL; - INIT_WORK(&drvdata->battery_remove_work, - corsair_void_battery_remove_work_handler); - INIT_WORK(&drvdata->battery_add_work, - corsair_void_battery_add_work_handler); - ret = devm_mutex_init(drvdata->dev, &drvdata->battery_mutex); - if (ret) - return ret; + INIT_WORK(&drvdata->battery_work, corsair_void_battery_work_handler); ret = sysfs_create_group(&hid_dev->dev.kobj, &corsair_void_attr_group); if (ret) @@ -721,8 +725,7 @@ static void corsair_void_remove(struct hid_device *hid_dev) struct corsair_void_drvdata *drvdata = hid_get_drvdata(hid_dev); hid_hw_stop(hid_dev); - cancel_work_sync(&drvdata->battery_remove_work); - cancel_work_sync(&drvdata->battery_add_work); + cancel_work_sync(&drvdata->battery_work); if (drvdata->battery) power_supply_unregister(drvdata->battery); -- 2.47.2

6 months

4
4
0 0

[PATCH RFC 2/2] usb: typec: ucsi: increase timeout for PPM reset operations

by Fedor Pchelkin

It is observed that on some systems an initial PPM reset during the boot phase can trigger a timeout: [ 6.482546] ucsi_acpi USBC000:00: failed to reset PPM! [ 6.482551] ucsi_acpi USBC000:00: error -ETIMEDOUT: PPM init failed Still, increasing the timeout value, albeit being the most straightforward solution, eliminates the problem: the initial PPM reset may take up to ~8000-10000ms on some Lenovo laptops. When it is reset after the above period of time (or even if ucsi_reset_ppm() is not called overall), UCSI works as expected. Moreover, if the ucsi_acpi module is loaded/unloaded manually after the system has booted, reading the CCI values and resetting the PPM works perfectly, without any timeout. Thus it's only a boot-time issue. The reason for this behavior is not clear but it may be the consequence of some tricks that the firmware performs or be an actual firmware bug. As a workaround, increase the timeout to avoid failing the UCSI initialization prematurely. Fixes: b1b59e16075f ("usb: typec: ucsi: Increase command completion timeout value") Cc: stable(a)vger.kernel.org Signed-off-by: Fedor Pchelkin <boddah8794(a)gmail.com> --- drivers/usb/typec/ucsi/ucsi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c index 0fe1476f4c29..7a56d3f840d7 100644 --- a/drivers/usb/typec/ucsi/ucsi.c +++ b/drivers/usb/typec/ucsi/ucsi.c @@ -25,7 +25,7 @@ * difficult to estimate the time it takes for the system to process the command * before it is actually passed to the PPM. */ -#define UCSI_TIMEOUT_MS 5000 +#define UCSI_TIMEOUT_MS 10000 /* * UCSI_SWAP_TIMEOUT_MS - Timeout for role swap requests -- 2.48.1

6 months

4
5
0 0

[PATCH vhost] vdpa/mlx5: Fix oversized null mkey longer than 32bit

by Dragos Tatulea

From: Si-Wei Liu <si-wei.liu(a)oracle.com> create_user_mr() has correct code to count the number of null keys used to fill in a hole for the memory map. However, fill_indir() does not follow the same to cap the range up to the 1GB limit correspondinly. Fill in more null keys for the gaps in between, so that null keys are correctly populated. Fixes: 94abbccdf291 ("vdpa/mlx5: Add shared memory registration code") Cc: stable(a)vger.kernel.org Signed-off-by: Si-Wei Liu <si-wei.liu(a)oracle.com> Signed-off-by: Dragos Tatulea <dtatulea(a)nvidia.com> --- drivers/vdpa/mlx5/core/mr.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/vdpa/mlx5/core/mr.c b/drivers/vdpa/mlx5/core/mr.c index 8455f08f5d40..61424342c096 100644 --- a/drivers/vdpa/mlx5/core/mr.c +++ b/drivers/vdpa/mlx5/core/mr.c @@ -190,9 +190,12 @@ static void fill_indir(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_mr *mkey, v klm->bcount = cpu_to_be32(klm_bcount(dmr->end - dmr->start)); preve = dmr->end; } else { + u64 bcount = min_t(u64, dmr->start - preve, MAX_KLM_SIZE); + klm->key = cpu_to_be32(mvdev->res.null_mkey); - klm->bcount = cpu_to_be32(klm_bcount(dmr->start - preve)); - preve = dmr->start; + klm->bcount = cpu_to_be32(klm_bcount(bcount)); + preve += bcount; + goto again; } } -- 2.43.0

6 months

2
2
0 0

[REGRESSION] stable-rc/linux-6.1.y: (build) stack frame size (2488) exceeds limit (2048) in 'dml31_ModeSupport...

by KernelCI bot

Hello, New build issue found on stable-rc/linux-6.1.y: --- stack frame size (2488) exceeds limit (2048) in 'dml31_ModeSupportAndSystemConfigurationFull' [-Werror,-Wframe-larger-than] in drivers/gpu/drm/amd/amdgpu/../display/dc/dml/dcn31/display_mode_vba_31.o (drivers/gpu/drm/amd/amdgpu/../display/dc/dml/dcn31/display_mode_vba_31.c) [logspec:kbuild,kbuild.compiler.error] --- - dashboard: https://d.kernelci.org/issue/maestro:bd2798b6baf3af3d8f6fcf670eac9f5235e8b3… - giturl: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git - commit HEAD: c703a7b9b55f8b3d701c14cd8d841ead509baa08 Log excerpt: ===================================================== drivers/gpu/drm/amd/amdgpu/../display/dc/dml/dcn31/display_mode_vba_31.c:3795:6: error: stack frame size (2488) exceeds limit (2048) in 'dml31_ModeSupportAndSystemConfigurationFull' [-Werror,-Wframe-larger-than] 3795 | void dml31_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_lib) | ^ 1 error generated. ===================================================== # Builds where the incident occurred: ## x86_64_defconfig on (x86_64): - compiler: clang-17 - dashboard: https://d.kernelci.org/build/maestro:67b4a3dc50b59caecce1cb05 #kernelci issue maestro:bd2798b6baf3af3d8f6fcf670eac9f5235e8b3a6 Reported-by: kernelci.org bot <bot(a)kernelci.org> -- This is an experimental report format. Please send feedback in! Talk to us at kernelci(a)lists.linux.dev Made with love by the KernelCI team - https://kernelci.org

6 months

1
0
0 0

[PATCH 2/5] ftrace: Do not add duplicate entries in subops manager ops

by Steven Rostedt

From: Steven Rostedt <rostedt(a)goodmis.org> Check if a function is already in the manager ops of a subops. A manager ops contains multiple subops, and if two or more subops are tracing the same function, the manager ops only needs a single entry in its hash. Cc: stable(a)vger.kernel.org Fixes: 4f554e955614f ("ftrace: Add ftrace_set_filter_ips function") Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> --- kernel/trace/ftrace.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 03b35a05808c..189eb0a12f4b 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -5717,6 +5717,9 @@ __ftrace_match_addr(struct ftrace_hash *hash, unsigned long ip, int remove) return -ENOENT; free_hash_entry(hash, entry); return 0; + } else if (__ftrace_lookup_ip(hash, ip) != NULL) { + /* Already exists */ + return 0; } entry = add_hash_entry(hash, ip); -- 2.47.2

6 months

1
0
0 0

[PATCH 1/5] ftrace: Fix accounting of adding subops to a manager ops

by Steven Rostedt

From: Steven Rostedt <rostedt(a)goodmis.org> Function graph uses a subops and manager ops mechanism to attach to ftrace. The manager ops connects to ftrace and the functions it connects to is defined by a list of subops that it manages. The function hash that defines what the above ops attaches to limits the functions to attach if the hash has any content. If the hash is empty, it means to trace all functions. The creation of the manager ops hash is done by iterating over all the subops hashes. If any of the subops hashes is empty, it means that the manager ops hash must trace all functions as well. The issue is in the creation of the manager ops. When a second subops is attached, a new hash is created by starting it as NULL and adding the subops one at a time. But the NULL ops is mistaken as an empty hash, and once an empty hash is found, it stops the loop of subops and just enables all functions. # echo "f:myevent1 kernel_clone" >> /sys/kernel/tracing/dynamic_events # cat /sys/kernel/tracing/enabled_functions kernel_clone (1) tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 # echo "f:myevent2 schedule_timeout" >> /sys/kernel/tracing/dynamic_events # cat /sys/kernel/tracing/enabled_functions trace_initcall_start_cb (1) tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 run_init_process (1) tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 try_to_run_init_process (1) tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 x86_pmu_show_pmu_cap (1) tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 cleanup_rapl_pmus (1) tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 uncore_free_pcibus_map (1) tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 uncore_types_exit (1) tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 uncore_pci_exit.part.0 (1) tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 kvm_shutdown (1) tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 vmx_dump_msrs (1) tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 vmx_cleanup_l1d_flush (1) tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 [..] Fix this by initializing the new hash to NULL and if the hash is NULL do not treat it as an empty hash but instead allocate by copying the content of the first sub ops. Then on subsequent iterations, the new hash will not be NULL, but the content of the previous subops. If that first subops attached to all functions, then new hash may assume that the manager ops also needs to attach to all functions. Cc: stable(a)vger.kernel.org Fixes: 5fccc7552ccbc ("ftrace: Add subops logic to allow one ops to manage many") Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> --- kernel/trace/ftrace.c | 30 ++++++++++++++++++++---------- 1 file changed, 20 insertions(+), 10 deletions(-) diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 728ecda6e8d4..03b35a05808c 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -3220,15 +3220,22 @@ static struct ftrace_hash *copy_hash(struct ftrace_hash *src) * The filter_hash updates uses just the append_hash() function * and the notrace_hash does not. */ -static int append_hash(struct ftrace_hash **hash, struct ftrace_hash *new_hash) +static int append_hash(struct ftrace_hash **hash, struct ftrace_hash *new_hash, + int size_bits) { struct ftrace_func_entry *entry; int size; int i; - /* An empty hash does everything */ - if (ftrace_hash_empty(*hash)) - return 0; + if (*hash) { + /* An empty hash does everything */ + if (ftrace_hash_empty(*hash)) + return 0; + } else { + *hash = alloc_ftrace_hash(size_bits); + if (!*hash) + return -ENOMEM; + } /* If new_hash has everything make hash have everything */ if (ftrace_hash_empty(new_hash)) { @@ -3292,16 +3299,18 @@ static int intersect_hash(struct ftrace_hash **hash, struct ftrace_hash *new_has /* Return a new hash that has a union of all @ops->filter_hash entries */ static struct ftrace_hash *append_hashes(struct ftrace_ops *ops) { - struct ftrace_hash *new_hash; + struct ftrace_hash *new_hash = NULL; struct ftrace_ops *subops; + int size_bits; int ret; - new_hash = alloc_ftrace_hash(ops->func_hash->filter_hash->size_bits); - if (!new_hash) - return NULL; + if (ops->func_hash->filter_hash) + size_bits = ops->func_hash->filter_hash->size_bits; + else + size_bits = FTRACE_HASH_DEFAULT_BITS; list_for_each_entry(subops, &ops->subop_list, list) { - ret = append_hash(&new_hash, subops->func_hash->filter_hash); + ret = append_hash(&new_hash, subops->func_hash->filter_hash, size_bits); if (ret < 0) { free_ftrace_hash(new_hash); return NULL; @@ -3505,7 +3514,8 @@ int ftrace_startup_subops(struct ftrace_ops *ops, struct ftrace_ops *subops, int filter_hash = alloc_and_copy_ftrace_hash(size_bits, ops->func_hash->filter_hash); if (!filter_hash) return -ENOMEM; - ret = append_hash(&filter_hash, subops->func_hash->filter_hash); + ret = append_hash(&filter_hash, subops->func_hash->filter_hash, + size_bits); if (ret < 0) { free_ftrace_hash(filter_hash); return ret; -- 2.47.2

6 months

1
0
0 0

[REGRESSION] stable-rc/linux-5.4.y: (build) ./arch/mips/include/asm/syscall.h:66:28: error: ‘struct pt_regs’ h...

by KernelCI bot

Hello, New build issue found on stable-rc/linux-5.4.y: --- ./arch/mips/include/asm/syscall.h:66:28: error: ‘struct pt_regs’ has no member named ‘args’ in arch/mips/kernel/ptrace.o (arch/mips/kernel/ptrace.c) [logspec:kbuild,kbuild.compiler.error] --- - dashboard: https://d.kernelci.org/issue/maestro:609e973861db59e6d6e75d96a9f0f0a24ba09b… - giturl: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git - commit HEAD: 46b505f46fed8d28d9f0cf8e2aace766b99e48ce Log excerpt: ===================================================== In file included from arch/mips/kernel/ptrace.c:45: ./arch/mips/include/asm/syscall.h: In function ‘mips_get_syscall_arg’: ./arch/mips/include/asm/syscall.h:66:28: error: ‘struct pt_regs’ has no member named ‘args’ 66 | *arg = regs->args[n]; | ^~ ===================================================== # Builds where the incident occurred: ## 32r2el_defconfig on (mips): - compiler: gcc-12 - dashboard: https://d.kernelci.org/build/maestro:67b4a28b50b59caecce1c871 #kernelci issue maestro:609e973861db59e6d6e75d96a9f0f0a24ba09ba0 Reported-by: kernelci.org bot <bot(a)kernelci.org> -- This is an experimental report format. Please send feedback in! Talk to us at kernelci(a)lists.linux.dev Made with love by the KernelCI team - https://kernelci.org

6 months

1
0
0 0

[PATCH v3] ACPI: platform-profile: Fix CFI violation when accessing sysfs files

by Nathan Chancellor

When an attribute group is created with sysfs_create_group(), the ->sysfs_ops() callback is set to kobj_sysfs_ops, which sets the ->show() and ->store() callbacks to kobj_attr_show() and kobj_attr_store() respectively. These functions use container_of() to get the respective callback from the passed attribute, meaning that these callbacks need to be the same type as the callbacks in 'struct kobj_attribute'. However, the platform_profile sysfs functions have the type of the ->show() and ->store() callbacks in 'struct device_attribute', which results a CFI violation when accessing platform_profile or platform_profile_choices under /sys/firmware/acpi because the types do not match: CFI failure at kobj_attr_show+0x19/0x30 (target: platform_profile_choices_show+0x0/0x140; expected type: 0x7a69590c) There is no functional issue from the type mismatch because the layout of 'struct kobj_attribute' and 'struct device_attribute' are the same, so the container_of() cast does not break anything aside from CFI. Change the type of platform_profile_choices_show() and platform_profile_{show,store}() to match the callbacks in 'struct kobj_attribute' and update the attribute variables to match, which resolves the CFI violation. Cc: stable(a)vger.kernel.org Fixes: a2ff95e018f1 ("ACPI: platform: Add platform profile support") Reported-by: John Rowley <lkml(a)johnrowley.me> Closes: https://github.com/ClangBuiltLinux/linux/issues/2047 Tested-by: John Rowley <lkml(a)johnrowley.me> Reviewed-by: Sami Tolvanen <samitolvanen(a)google.com> Signed-off-by: Nathan Chancellor <nathan(a)kernel.org> --- Changes in v3: - Rebase on 6.14-rc1, which includes updates to the driver to address Greg's previous concerns but this change is still needed for the legacy sysfs interface. v2 can be used for the stable backport. - Link to v2: https://lore.kernel.org/r/20241118-acpi-platform_profile-fix-cfi-violation-… Changes in v2: - Rebase on linux-pm/acpi - Pick up Sami's reviewed-by tag - Adjust wording around why there is no functional issue from the mismatched types - Link to v1: https://lore.kernel.org/r/20240819-acpi-platform_profile-fix-cfi-violation-… --- drivers/acpi/platform_profile.c | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-) diff --git a/drivers/acpi/platform_profile.c b/drivers/acpi/platform_profile.c index fc92e43d0fe9..1b6317f759f9 100644 --- a/drivers/acpi/platform_profile.c +++ b/drivers/acpi/platform_profile.c @@ -260,14 +260,14 @@ static int _aggregate_choices(struct device *dev, void *data) /** * platform_profile_choices_show - Show the available profile choices for legacy sysfs interface - * @dev: The device + * @kobj: The kobject * @attr: The attribute * @buf: The buffer to write to * * Return: The number of bytes written */ -static ssize_t platform_profile_choices_show(struct device *dev, - struct device_attribute *attr, +static ssize_t platform_profile_choices_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) { unsigned long aggregate[BITS_TO_LONGS(PLATFORM_PROFILE_LAST)]; @@ -333,14 +333,14 @@ static int _store_and_notify(struct device *dev, void *data) /** * platform_profile_show - Show the current profile for legacy sysfs interface - * @dev: The device + * @kobj: The kobject * @attr: The attribute * @buf: The buffer to write to * * Return: The number of bytes written */ -static ssize_t platform_profile_show(struct device *dev, - struct device_attribute *attr, +static ssize_t platform_profile_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) { enum platform_profile_option profile = PLATFORM_PROFILE_LAST; @@ -362,15 +362,15 @@ static ssize_t platform_profile_show(struct device *dev, /** * platform_profile_store - Set the profile for legacy sysfs interface - * @dev: The device + * @kobj: The kobject * @attr: The attribute * @buf: The buffer to read from * @count: The number of bytes to read * * Return: The number of bytes read */ -static ssize_t platform_profile_store(struct device *dev, - struct device_attribute *attr, +static ssize_t platform_profile_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, size_t count) { unsigned long choices[BITS_TO_LONGS(PLATFORM_PROFILE_LAST)]; @@ -401,12 +401,12 @@ static ssize_t platform_profile_store(struct device *dev, return count; } -static DEVICE_ATTR_RO(platform_profile_choices); -static DEVICE_ATTR_RW(platform_profile); +static struct kobj_attribute attr_platform_profile_choices = __ATTR_RO(platform_profile_choices); +static struct kobj_attribute attr_platform_profile = __ATTR_RW(platform_profile); static struct attribute *platform_profile_attrs[] = { - &dev_attr_platform_profile_choices.attr, - &dev_attr_platform_profile.attr, + &attr_platform_profile_choices.attr, + &attr_platform_profile.attr, NULL }; --- base-commit: 2014c95afecee3e76ca4a56956a936e23283f05b change-id: 20240819-acpi-platform_profile-fix-cfi-violation-de278753bd5f Best regards, -- Nathan Chancellor <nathan(a)kernel.org>

6 months

4
5
0 0

Re: Patch "s390/qeth: move netif_napi_add_tx() and napi_enable() from under BH" has been added to the 6.13-stable tree

by Alexandra Winter

On 18.02.25 13:36, Sasha Levin wrote: > This is a note to let you know that I've just added the patch titled > > s390/qeth: move netif_napi_add_tx() and napi_enable() from under BH > > to the 6.13-stable tree which can be found at: > http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… > > The filename of the patch is: > s390-qeth-move-netif_napi_add_tx-and-napi_enable-fro.patch > and it can be found in the queue-6.13 subdirectory. > > If you, or anyone else, feels it should not be added to the stable tree, > please let <stable(a)vger.kernel.org> know about it. > Hello Sasha, this is a fix for a regression that was introduced with v6.14-rc1. So I do not think it needs to go into 6.13 stable tree. But it does not hurt either. > > > commit 48eda8093b86b426078bd245a9b4fbc5d057c436 > Author: Alexandra Winter <wintera(a)linux.ibm.com> > Date: Wed Feb 12 17:36:59 2025 +0100 > > s390/qeth: move netif_napi_add_tx() and napi_enable() from under BH > > [ Upstream commit 0d0b752f2497471ddd2b32143d167d42e18a8f3c ] > > Like other drivers qeth is calling local_bh_enable() after napi_schedule() > to kick-start softirqs [0]. > Since netif_napi_add_tx() and napi_enable() now take the netdev_lock() > mutex [1], move them out from under the BH protection. Same solution as in > commit a60558644e20 ("wifi: mt76: move napi_enable() from under BH") > > Fixes: 1b23cdbd2bbc ("net: protect netdev->napi_list with netdev_lock()") > Link: https://lore.kernel.org/netdev/20240612181900.4d9d18d0@kernel.org/ [0] > Link: https://lore.kernel.org/netdev/20250115035319.559603-1-kuba@kernel.org/ [1] > Signed-off-by: Alexandra Winter <wintera(a)linux.ibm.com> > Acked-by: Joe Damato <jdamato(a)fastly.com> > Link: https://patch.msgid.link/20250212163659.2287292-1-wintera@linux.ibm.com > Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> > Signed-off-by: Sasha Levin <sashal(a)kernel.org> > > diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c > index a3adaec5504e4..20328d695ef92 100644 > --- a/drivers/s390/net/qeth_core_main.c > +++ b/drivers/s390/net/qeth_core_main.c > @@ -7050,14 +7050,16 @@ int qeth_open(struct net_device *dev) > card->data.state = CH_STATE_UP; > netif_tx_start_all_queues(dev); > > - local_bh_disable(); > qeth_for_each_output_queue(card, queue, i) { > netif_napi_add_tx(dev, &queue->napi, qeth_tx_poll); > napi_enable(&queue->napi); > - napi_schedule(&queue->napi); > } > - > napi_enable(&card->napi); > + > + local_bh_disable(); > + qeth_for_each_output_queue(card, queue, i) { > + napi_schedule(&queue->napi); > + } > napi_schedule(&card->napi); > /* kick-start the NAPI softirq: */ > local_bh_enable();

6 months

2
3
0 0

FAILED: patch "[PATCH] Revert "net: skb: introduce and use a single page frag cache"" 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 011b0335903832facca86cd8ed05d7d8d94c9c76 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025021859-renewal-onto-1877@gregkh' --subject-prefix 'PATCH 6.12.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 011b0335903832facca86cd8ed05d7d8d94c9c76 Mon Sep 17 00:00:00 2001 From: Paolo Abeni <pabeni(a)redhat.com> Date: Thu, 6 Feb 2025 22:28:48 +0100 Subject: [PATCH] Revert "net: skb: introduce and use a single page frag cache" This reverts commit dbae2b062824 ("net: skb: introduce and use a single page frag cache"). The intended goal of such change was to counter a performance regression introduced by commit 3226b158e67c ("net: avoid 32 x truesize under-estimation for tiny skbs"). Unfortunately, the blamed commit introduces another regression for the virtio_net driver. Such a driver calls napi_alloc_skb() with a tiny size, so that the whole head frag could fit a 512-byte block. The single page frag cache uses a 1K fragment for such allocation, and the additional overhead, under small UDP packets flood, makes the page allocator a bottleneck. Thanks to commit bf9f1baa279f ("net: add dedicated kmem_cache for typical/small skb->head"), this revert does not re-introduce the original regression. Actually, in the relevant test on top of this revert, I measure a small but noticeable positive delta, just above noise level. The revert itself required some additional mangling due to the introduction of the SKB_HEAD_ALIGN() helper and local lock infra in the affected code. Suggested-by: Eric Dumazet <edumazet(a)google.com> Fixes: dbae2b062824 ("net: skb: introduce and use a single page frag cache") Signed-off-by: Paolo Abeni <pabeni(a)redhat.com> Link: https://patch.msgid.link/e649212fde9f0fdee23909ca0d14158d32bb7425.173887729… Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index c0a86afb85da..365f0e2098d1 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4115,7 +4115,6 @@ void netif_receive_skb_list(struct list_head *head); gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb); void napi_gro_flush(struct napi_struct *napi, bool flush_old); struct sk_buff *napi_get_frags(struct napi_struct *napi); -void napi_get_frags_check(struct napi_struct *napi); gro_result_t napi_gro_frags(struct napi_struct *napi); static inline void napi_free_frags(struct napi_struct *napi) diff --git a/net/core/dev.c b/net/core/dev.c index b91658e8aedb..55e356a68db6 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6920,6 +6920,23 @@ netif_napi_dev_list_add(struct net_device *dev, struct napi_struct *napi) list_add_rcu(&napi->dev_list, higher); /* adds after higher */ } +/* Double check that napi_get_frags() allocates skbs with + * skb->head being backed by slab, not a page fragment. + * This is to make sure bug fixed in 3226b158e67c + * ("net: avoid 32 x truesize under-estimation for tiny skbs") + * does not accidentally come back. + */ +static void napi_get_frags_check(struct napi_struct *napi) +{ + struct sk_buff *skb; + + local_bh_disable(); + skb = napi_get_frags(napi); + WARN_ON_ONCE(skb && skb->head_frag); + napi_free_frags(napi); + local_bh_enable(); +} + void netif_napi_add_weight_locked(struct net_device *dev, struct napi_struct *napi, int (*poll)(struct napi_struct *, int), diff --git a/net/core/skbuff.c b/net/core/skbuff.c index a441613a1e6c..6a99c453397f 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -220,67 +220,9 @@ static void skb_under_panic(struct sk_buff *skb, unsigned int sz, void *addr) #define NAPI_SKB_CACHE_BULK 16 #define NAPI_SKB_CACHE_HALF (NAPI_SKB_CACHE_SIZE / 2) -#if PAGE_SIZE == SZ_4K - -#define NAPI_HAS_SMALL_PAGE_FRAG 1 -#define NAPI_SMALL_PAGE_PFMEMALLOC(nc) ((nc).pfmemalloc) - -/* specialized page frag allocator using a single order 0 page - * and slicing it into 1K sized fragment. Constrained to systems - * with a very limited amount of 1K fragments fitting a single - * page - to avoid excessive truesize underestimation - */ - -struct page_frag_1k { - void *va; - u16 offset; - bool pfmemalloc; -}; - -static void *page_frag_alloc_1k(struct page_frag_1k *nc, gfp_t gfp) -{ - struct page *page; - int offset; - - offset = nc->offset - SZ_1K; - if (likely(offset >= 0)) - goto use_frag; - - page = alloc_pages_node(NUMA_NO_NODE, gfp, 0); - if (!page) - return NULL; - - nc->va = page_address(page); - nc->pfmemalloc = page_is_pfmemalloc(page); - offset = PAGE_SIZE - SZ_1K; - page_ref_add(page, offset / SZ_1K); - -use_frag: - nc->offset = offset; - return nc->va + offset; -} -#else - -/* the small page is actually unused in this build; add dummy helpers - * to please the compiler and avoid later preprocessor's conditionals - */ -#define NAPI_HAS_SMALL_PAGE_FRAG 0 -#define NAPI_SMALL_PAGE_PFMEMALLOC(nc) false - -struct page_frag_1k { -}; - -static void *page_frag_alloc_1k(struct page_frag_1k *nc, gfp_t gfp_mask) -{ - return NULL; -} - -#endif - struct napi_alloc_cache { local_lock_t bh_lock; struct page_frag_cache page; - struct page_frag_1k page_small; unsigned int skb_count; void *skb_cache[NAPI_SKB_CACHE_SIZE]; }; @@ -290,23 +232,6 @@ static DEFINE_PER_CPU(struct napi_alloc_cache, napi_alloc_cache) = { .bh_lock = INIT_LOCAL_LOCK(bh_lock), }; -/* Double check that napi_get_frags() allocates skbs with - * skb->head being backed by slab, not a page fragment. - * This is to make sure bug fixed in 3226b158e67c - * ("net: avoid 32 x truesize under-estimation for tiny skbs") - * does not accidentally come back. - */ -void napi_get_frags_check(struct napi_struct *napi) -{ - struct sk_buff *skb; - - local_bh_disable(); - skb = napi_get_frags(napi); - WARN_ON_ONCE(!NAPI_HAS_SMALL_PAGE_FRAG && skb && skb->head_frag); - napi_free_frags(napi); - local_bh_enable(); -} - void *__napi_alloc_frag_align(unsigned int fragsz, unsigned int align_mask) { struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); @@ -813,10 +738,8 @@ struct sk_buff *napi_alloc_skb(struct napi_struct *napi, unsigned int len) /* If requested length is either too small or too big, * we use kmalloc() for skb->head allocation. - * When the small frag allocator is available, prefer it over kmalloc - * for small fragments */ - if ((!NAPI_HAS_SMALL_PAGE_FRAG && len <= SKB_WITH_OVERHEAD(1024)) || + if (len <= SKB_WITH_OVERHEAD(1024) || len > SKB_WITH_OVERHEAD(PAGE_SIZE) || (gfp_mask & (__GFP_DIRECT_RECLAIM | GFP_DMA))) { skb = __alloc_skb(len, gfp_mask, SKB_ALLOC_RX | SKB_ALLOC_NAPI, @@ -826,32 +749,16 @@ struct sk_buff *napi_alloc_skb(struct napi_struct *napi, unsigned int len) goto skb_success; } + len = SKB_HEAD_ALIGN(len); + if (sk_memalloc_socks()) gfp_mask |= __GFP_MEMALLOC; local_lock_nested_bh(&napi_alloc_cache.bh_lock); nc = this_cpu_ptr(&napi_alloc_cache); - if (NAPI_HAS_SMALL_PAGE_FRAG && len <= SKB_WITH_OVERHEAD(1024)) { - /* we are artificially inflating the allocation size, but - * that is not as bad as it may look like, as: - * - 'len' less than GRO_MAX_HEAD makes little sense - * - On most systems, larger 'len' values lead to fragment - * size above 512 bytes - * - kmalloc would use the kmalloc-1k slab for such values - * - Builds with smaller GRO_MAX_HEAD will very likely do - * little networking, as that implies no WiFi and no - * tunnels support, and 32 bits arches. - */ - len = SZ_1K; - data = page_frag_alloc_1k(&nc->page_small, gfp_mask); - pfmemalloc = NAPI_SMALL_PAGE_PFMEMALLOC(nc->page_small); - } else { - len = SKB_HEAD_ALIGN(len); - - data = page_frag_alloc(&nc->page, len, gfp_mask); - pfmemalloc = page_frag_cache_is_pfmemalloc(&nc->page); - } + data = page_frag_alloc(&nc->page, len, gfp_mask); + pfmemalloc = page_frag_cache_is_pfmemalloc(&nc->page); local_unlock_nested_bh(&napi_alloc_cache.bh_lock); if (unlikely(!data))

6 months

2
2
0 0

[PATCH 0/2] vsock: fix use-after free and null-ptr-deref

by Luigi Leonardi

Hi all, This series contains two patches that are already available upstream: - The first commit fixes a use-after-free[1], but introduced a null-ptr-deref[2]. - The second commit fixes it. [3] I suggested waiting for both of them to be merged upstream and then applying them togheter to stable[4]. It should be applied to: - 6.13.y - 6.12.y - 6.6.y I will send another series for - 6.1.y - 5.15.y - 5.10.y because of conflicts. [1]https://lore.kernel.org/all/20250128-vsock-transport-vs-autobind-v3-0-1cf… [2]https://lore.kernel.org/all/67a09300.050a0220.d7c5a.008b.GAE@google.com/ [3]https://lore.kernel.org/all/20250210-vsock-linger-nullderef-v3-0-ef6244d0… [4]https://lore.kernel.org/all/2025020644-unwitting-scary-3c0d@gregkh/ Thanks, Luigi --- Michal Luczaj (2): vsock: Keep the binding until socket destruction vsock: Orphan socket after transport release net/vmw_vsock/af_vsock.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) --- base-commit: a1856aaa2ca74c88751f7d255dfa0c8c50fcc1ca change-id: 20250214-linux-rolling-stable-d73f0bed815d Best regards, -- Luigi Leonardi <leonardi(a)redhat.com>

6 months

3
7
0 0

[PATCH 6.6.y] drm/amd/display: Add null check for head_pipe in dcn201_acquire_free_pipe_for_layer

by Xiangyu Chen

From: Srinivasan Shanmugam <srinivasan.shanmugam(a)amd.com> [ Upstream commit f22f4754aaa47d8c59f166ba3042182859e5dff7 ] This commit addresses a potential null pointer dereference issue in the `dcn201_acquire_free_pipe_for_layer` function. The issue could occur when `head_pipe` is null. The fix adds a check to ensure `head_pipe` is not null before asserting it. If `head_pipe` is null, the function returns NULL to prevent a potential null pointer dereference. Reported by smatch: drivers/gpu/drm/amd/amdgpu/../display/dc/resource/dcn201/dcn201_resource.c:1016 dcn201_acquire_free_pipe_for_layer() error: we previously assumed 'head_pipe' could be null (see line 1010) Cc: Tom Chung <chiahsuan.chung(a)amd.com> Cc: Rodrigo Siqueira <Rodrigo.Siqueira(a)amd.com> Cc: Roman Li <roman.li(a)amd.com> Cc: Alex Hung <alex.hung(a)amd.com> Cc: Aurabindo Pillai <aurabindo.pillai(a)amd.com> Cc: Harry Wentland <harry.wentland(a)amd.com> Cc: Hamza Mahfooz <hamza.mahfooz(a)amd.com> Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam(a)amd.com> Reviewed-by: Tom Chung <chiahsuan.chung(a)amd.com> Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com> [dcn201 was moved from drivers/gpu/drm/amd/display/dc to drivers/gpu/drm/amd/display/dc/resource since 8b8eed05a1c6 ("drm/amd/display: Refactor resource into component directory"). The path is changed accordingly to apply the patch on 6.6.y.] Signed-off-by: Xiangyu Chen <xiangyu.chen(a)windriver.com> Signed-off-by: He Zhe <zhe.he(a)windriver.com> --- Verified the build test only due to we don't have DCN201 device. --- drivers/gpu/drm/amd/display/dc/dcn201/dcn201_resource.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn201/dcn201_resource.c b/drivers/gpu/drm/amd/display/dc/dcn201/dcn201_resource.c index 2dc4d2c1410b..8efe3f32a0e7 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn201/dcn201_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn201/dcn201_resource.c @@ -1002,8 +1002,10 @@ static struct pipe_ctx *dcn201_acquire_free_pipe_for_layer( struct pipe_ctx *head_pipe = resource_get_otg_master_for_stream(res_ctx, opp_head_pipe->stream); struct pipe_ctx *idle_pipe = resource_find_free_secondary_pipe_legacy(res_ctx, pool, head_pipe); - if (!head_pipe) + if (!head_pipe) { ASSERT(0); + return NULL; + } if (!idle_pipe) return NULL; -- 2.25.1

6 months

3
2
0 0

Re: Patch "alpha: make stack 16-byte aligned (most cases)" has been added to the 6.6-stable tree

by Ivan Kokshaysky

On Tue, Feb 18, 2025 at 01:55:45PM +0100, gregkh(a)linuxfoundation.org wrote: > > This is a note to let you know that I've just added the patch titled > > alpha: make stack 16-byte aligned (most cases) Hi Greg, thanks for applying this! > Patches currently in stable-queue which might be from ink(a)unseen.parts are > > queue-6.6/alpha-make-stack-16-byte-aligned-most-cases.patch > queue-6.6/alpha-align-stack-for-page-fault-and-user-unaligned-trap-handlers.patch The third one (commit 77b823fa619f97d alpha: replace hardcoded stack offsets with autogenerated ones) is also needed, but it won't apply as-is to 6.6 and older kernels. Do you want me to provide the patches? Ivan.

6 months

2
4
0 0

[PATCH 6.6.y] drm/amd/display: Pass non-null to dcn20_validate_apply_pipe_split_flags

by Xiangyu Chen

From: Alex Hung <alex.hung(a)amd.com> [ upstream commit 5559598742fb4538e4c51c48ef70563c49c2af23 ] [WHAT & HOW] "dcn20_validate_apply_pipe_split_flags" dereferences merge, and thus it cannot be a null pointer. Let's pass a valid pointer to avoid null dereference. This fixes 2 FORWARD_NULL issues reported by Coverity. Reviewed-by: Rodrigo Siqueira <rodrigo.siqueira(a)amd.com> Signed-off-by: Jerry Zuo <jerry.zuo(a)amd.com> Signed-off-by: Alex Hung <alex.hung(a)amd.com> Tested-by: Daniel Wheeler <daniel.wheeler(a)amd.com> Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com> [dcn20 and dcn21 were moved from drivers/gpu/drm/amd/display/dc to drivers/gpu/drm/amd/display/dc/resource since 8b8eed05a1c6 ("drm/amd/display: Refactor resource into component directory"). The path is changed accordingly to apply the patch on 6.6.y.] Signed-off-by: Xiangyu Chen <xiangyu.chen(a)windriver.com> Signed-off-by: He Zhe <zhe.he(a)windriver.com> --- Verified the build test only due to we don't have dcn20/dcn21 device. --- drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c | 3 ++- drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c | 3 ++- 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c index d587f807dfd7..294609557b73 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c @@ -2026,6 +2026,7 @@ bool dcn20_fast_validate_bw( { bool out = false; int split[MAX_PIPES] = { 0 }; + bool merge[MAX_PIPES] = { false }; int pipe_cnt, i, pipe_idx, vlevel; ASSERT(pipes); @@ -2050,7 +2051,7 @@ bool dcn20_fast_validate_bw( if (vlevel > context->bw_ctx.dml.soc.num_states) goto validate_fail; - vlevel = dcn20_validate_apply_pipe_split_flags(dc, context, vlevel, split, NULL); + vlevel = dcn20_validate_apply_pipe_split_flags(dc, context, vlevel, split, merge); /*initialize pipe_just_split_from to invalid idx*/ for (i = 0; i < MAX_PIPES; i++) diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c index 8dffa5b6426e..24105a5b9f2a 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c @@ -800,6 +800,7 @@ bool dcn21_fast_validate_bw(struct dc *dc, { bool out = false; int split[MAX_PIPES] = { 0 }; + bool merge[MAX_PIPES] = { false }; int pipe_cnt, i, pipe_idx, vlevel; ASSERT(pipes); @@ -842,7 +843,7 @@ bool dcn21_fast_validate_bw(struct dc *dc, goto validate_fail; } - vlevel = dcn20_validate_apply_pipe_split_flags(dc, context, vlevel, split, NULL); + vlevel = dcn20_validate_apply_pipe_split_flags(dc, context, vlevel, split, merge); for (i = 0, pipe_idx = 0; i < dc->res_pool->pipe_count; i++) { struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i]; -- 2.25.1

6 months

2
1
0 0

6.12.y stable backport request for bpf selftests fixes

by Alan Maguire

Please backport 42602e3a06f8e5b9a059344e305c9bee2dcc87c8 bpf: handle implicit declaration of function gettid in bpf_iter.c and 4b7c05598a644782b8451e415bb56f31e5c9d3ee selftests/bpf: Fix uprobe consumer test to 6.12.y to fix BPF selftest-related issues (compilation failure and test failure respectively). Both apply to linux-6.12.y cleanly. Thank you! Alan

6 months

2
1
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror February 2025