April 2025 - Kernel - mailweb.openeuler.org

[PATCH openEuler-1.0-LTS V1] ALSA: jack: Access input_dev under mutex
by Cheng Yu 02 Apr '25

02 Apr '25

From: Amadeusz Sławiński <amadeuszx.slawinski(a)linux.intel.com> stable inclusion from stable-v4.19.247 commit c093b62c40027c21d649c5534ad7aa3605a99b00 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBP3KT CVE: CVE-2022-49538 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 1b6a6fc5280e97559287b61eade2d4b363e836f2 ] It is possible when using ASoC that input_dev is unregistered while calling snd_jack_report, which causes NULL pointer dereference. In order to prevent this serialize access to input_dev using mutex lock. Signed-off-by: Amadeusz Sławiński <amadeuszx.slawinski(a)linux.intel.com> Reviewed-by: Cezary Rojewski <cezary.rojewski(a)intel.com> Link: https://lore.kernel.org/r/20220412091628.3056922-1-amadeuszx.slawinski@linu… Signed-off-by: Takashi Iwai <tiwai(a)suse.de> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Conflicts: sound/core/jack.c [Context conflicts.] Signed-off-by: Cheng Yu <serein.chengyu(a)huawei.com> --- include/sound/jack.h | 1 + sound/core/jack.c | 34 +++++++++++++++++++++++++++------- 2 files changed, 28 insertions(+), 7 deletions(-) diff --git a/include/sound/jack.h b/include/sound/jack.h index 1e84bfb553cf..4742f842b457 100644 --- a/include/sound/jack.h +++ b/include/sound/jack.h @@ -77,6 +77,7 @@ struct snd_jack { const char *id; #ifdef CONFIG_SND_JACK_INPUT_DEV struct input_dev *input_dev; + struct mutex input_dev_lock; int registered; int type; char name[100]; diff --git a/sound/core/jack.c b/sound/core/jack.c index 84c2a17c56ee..2f43fe667759 100644 --- a/sound/core/jack.c +++ b/sound/core/jack.c @@ -48,8 +48,11 @@ static int snd_jack_dev_disconnect(struct snd_device *device) #ifdef CONFIG_SND_JACK_INPUT_DEV struct snd_jack *jack = device->device_data; - if (!jack->input_dev) + mutex_lock(&jack->input_dev_lock); + if (!jack->input_dev) { + mutex_unlock(&jack->input_dev_lock); return 0; + } /* If the input device is registered with the input subsystem * then we need to use a different deallocator. */ @@ -58,6 +61,7 @@ static int snd_jack_dev_disconnect(struct snd_device *device) else input_free_device(jack->input_dev); jack->input_dev = NULL; + mutex_unlock(&jack->input_dev_lock); #endif /* CONFIG_SND_JACK_INPUT_DEV */ return 0; } @@ -93,8 +97,11 @@ static int snd_jack_dev_register(struct snd_device *device) snprintf(jack->name, sizeof(jack->name), "%s %s", card->shortname, jack->id); - if (!jack->input_dev) + mutex_lock(&jack->input_dev_lock); + if (!jack->input_dev) { + mutex_unlock(&jack->input_dev_lock); return 0; + } jack->input_dev->name = jack->name; @@ -119,6 +126,7 @@ static int snd_jack_dev_register(struct snd_device *device) if (err == 0) jack->registered = 1; + mutex_unlock(&jack->input_dev_lock); return err; } #endif /* CONFIG_SND_JACK_INPUT_DEV */ @@ -235,9 +243,11 @@ int snd_jack_new(struct snd_card *card, const char *id, int type, jack->id = kstrdup(id, GFP_KERNEL); - /* don't creat input device for phantom jack */ - if (!phantom_jack) { #ifdef CONFIG_SND_JACK_INPUT_DEV + mutex_init(&jack->input_dev_lock); + + /* don't create input device for phantom jack */ + if (!phantom_jack) { int i; jack->input_dev = input_allocate_device(); @@ -255,8 +265,8 @@ int snd_jack_new(struct snd_card *card, const char *id, int type, input_set_capability(jack->input_dev, EV_SW, jack_switch_types[i]); -#endif /* CONFIG_SND_JACK_INPUT_DEV */ } +#endif /* CONFIG_SND_JACK_INPUT_DEV */ err = snd_device_new(card, SNDRV_DEV_JACK, jack, &ops); if (err < 0) @@ -296,10 +306,14 @@ EXPORT_SYMBOL(snd_jack_new); void snd_jack_set_parent(struct snd_jack *jack, struct device *parent) { WARN_ON(jack->registered); - if (!jack->input_dev) + mutex_lock(&jack->input_dev_lock); + if (!jack->input_dev) { + mutex_unlock(&jack->input_dev_lock); return; + } jack->input_dev->dev.parent = parent; + mutex_unlock(&jack->input_dev_lock); } EXPORT_SYMBOL(snd_jack_set_parent); @@ -347,6 +361,8 @@ EXPORT_SYMBOL(snd_jack_set_key); /** * snd_jack_report - Report the current status of a jack + * Note: This function uses mutexes and should be called from a + * context which can sleep (such as a workqueue). * * @jack: The jack to report status for * @status: The current status of the jack @@ -366,8 +382,11 @@ void snd_jack_report(struct snd_jack *jack, int status) status & jack_kctl->mask_bits); #ifdef CONFIG_SND_JACK_INPUT_DEV - if (!jack->input_dev) + mutex_lock(&jack->input_dev_lock); + if (!jack->input_dev) { + mutex_unlock(&jack->input_dev_lock); return; + } for (i = 0; i < ARRAY_SIZE(jack->key); i++) { int testbit = SND_JACK_BTN_0 >> i; @@ -386,6 +405,7 @@ void snd_jack_report(struct snd_jack *jack, int status) } input_sync(jack->input_dev); + mutex_unlock(&jack->input_dev_lock); #endif /* CONFIG_SND_JACK_INPUT_DEV */ } EXPORT_SYMBOL(snd_jack_report); -- 2.25.1

2 1

[PATCH OLK-6.6] uprobes: Reject the shared zeropage in uprobe_write_opcode()
by Chen Zhongjin 02 Apr '25

02 Apr '25

From: Tong Tiangen <tongtiangen(a)huawei.com> stable inclusion from stable-v6.6.81 commit 0b6f19714588cf2366b0364234f97ba963688f63 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBWVTY CVE: CVE-2025-21881 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- [ Upstream commit bddf10d26e6e5114e7415a0e442ec6f51a559468 ] We triggered the following crash in syzkaller tests: BUG: Bad page state in process syz.7.38 pfn:1eff3 page: refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x1eff3 flags: 0x3fffff00004004(referenced|reserved|node=0|zone=1|lastcpupid=0x1fffff) raw: 003fffff00004004 ffffe6c6c07bfcc8 ffffe6c6c07bfcc8 0000000000000000 raw: 0000000000000000 0000000000000000 00000000fffffffe 0000000000000000 page dumped because: PAGE_FLAGS_CHECK_AT_FREE flag(s) set Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1ubuntu1.1 04/01/2014 Call Trace: <TASK> dump_stack_lvl+0x32/0x50 bad_page+0x69/0xf0 free_unref_page_prepare+0x401/0x500 free_unref_page+0x6d/0x1b0 uprobe_write_opcode+0x460/0x8e0 install_breakpoint.part.0+0x51/0x80 register_for_each_vma+0x1d9/0x2b0 __uprobe_register+0x245/0x300 bpf_uprobe_multi_link_attach+0x29b/0x4f0 link_create+0x1e2/0x280 __sys_bpf+0x75f/0xac0 __x64_sys_bpf+0x1a/0x30 do_syscall_64+0x56/0x100 entry_SYSCALL_64_after_hwframe+0x78/0xe2 BUG: Bad rss-counter state mm:00000000452453e0 type:MM_FILEPAGES val:-1 The following syzkaller test case can be used to reproduce: r2 = creat(&(0x7f0000000000)='./file0\x00', 0x8) write$nbd(r2, &(0x7f0000000580)=ANY=[], 0x10) r4 = openat(0xffffffffffffff9c, &(0x7f0000000040)='./file0\x00', 0x42, 0x0) mmap$IORING_OFF_SQ_RING(&(0x7f0000ffd000/0x3000)=nil, 0x3000, 0x0, 0x12, r4, 0x0) r5 = userfaultfd(0x80801) ioctl$UFFDIO_API(r5, 0xc018aa3f, &(0x7f0000000040)={0xaa, 0x20}) r6 = userfaultfd(0x80801) ioctl$UFFDIO_API(r6, 0xc018aa3f, &(0x7f0000000140)) ioctl$UFFDIO_REGISTER(r6, 0xc020aa00, &(0x7f0000000100)={{&(0x7f0000ffc000/0x4000)=nil, 0x4000}, 0x2}) ioctl$UFFDIO_ZEROPAGE(r5, 0xc020aa04, &(0x7f0000000000)={{&(0x7f0000ffd000/0x1000)=nil, 0x1000}}) r7 = bpf$PROG_LOAD(0x5, &(0x7f0000000140)={0x2, 0x3, &(0x7f0000000200)=ANY=[@ANYBLOB="1800000000120000000000000000000095"], &(0x7f0000000000)='GPL\x00', 0x7, 0x0, 0x0, 0x0, 0x0, '\x00', 0x0, @fallback=0x30, 0xffffffffffffffff, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x10, 0x0, @void, @value}, 0x94) bpf$BPF_LINK_CREATE_XDP(0x1c, &(0x7f0000000040)={r7, 0x0, 0x30, 0x1e, @val=@uprobe_multi={&(0x7f0000000080)='./file0\x00', &(0x7f0000000100)=[0x2], 0x0, 0x0, 0x1}}, 0x40) The cause is that zero pfn is set to the PTE without increasing the RSS count in mfill_atomic_pte_zeropage() and the refcount of zero folio does not increase accordingly. Then, the operation on the same pfn is performed in uprobe_write_opcode()->__replace_page() to unconditional decrease the RSS count and old_folio's refcount. Therefore, two bugs are introduced: 1. The RSS count is incorrect, when process exit, the check_mm() report error "Bad rss-count". 2. The reserved folio (zero folio) is freed when folio->refcount is zero, then free_pages_prepare->free_page_is_bad() report error "Bad page state". There is more, the following warning could also theoretically be triggered: __replace_page() -> ... -> folio_remove_rmap_pte() -> VM_WARN_ON_FOLIO(is_zero_folio(folio), folio) Considering that uprobe hit on the zero folio is a very rare case, just reject zero old folio immediately after get_user_page_vma_remote(). [ mingo: Cleaned up the changelog ] Fixes: 7396fa818d62 ("uprobes/core: Make background page replacement logic account for rss_stat counters") Fixes: 2b1444983508 ("uprobes, mm, x86: Add the ability to install and remove uprobes breakpoints") Signed-off-by: Tong Tiangen <tongtiangen(a)huawei.com> Signed-off-by: Ingo Molnar <mingo(a)kernel.org> Reviewed-by: David Hildenbrand <david(a)redhat.com> Reviewed-by: Oleg Nesterov <oleg(a)redhat.com> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Masami Hiramatsu <mhiramat(a)kernel.org> Link: https://lore.kernel.org/r/20250224031149.1598949-1-tongtiangen@huawei.com Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Chen Zhongjin <chenzhongjin(a)huawei.com> --- kernel/events/uprobes.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index a14b0059f177..c135c9704deb 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -483,6 +483,11 @@ int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm, if (ret <= 0) goto put_old; + if (is_zero_page(old_page)) { + ret = -EINVAL; + goto put_old; + } + if (WARN(!is_register && PageCompound(old_page), "uprobe unregister should never work on compound page\n")) { ret = -EINVAL; -- 2.25.1

2 1

[PATCH openEuler-1.0-LTS V1] ALSA: jack: Fix mutex call in snd_jack_report()
by Cheng Yu 02 Apr '25

02 Apr '25

From: Takashi Iwai <tiwai(a)suse.de> stable inclusion from stable-v4.19.291 commit 839f4e860eb6aff659ad05900963cf0410063eda category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBP3KT CVE: CVE-2022-49538 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 89dbb335cb6a627a4067bc42caa09c8bc3326d40 ] snd_jack_report() is supposed to be callable from an IRQ context, too, and it's indeed used in that way from virtsnd driver. The fix for input_dev race in commit 1b6a6fc5280e ("ALSA: jack: Access input_dev under mutex"), however, introduced a mutex lock in snd_jack_report(), and this resulted in a potential sleep-in-atomic. For addressing that problem, this patch changes the relevant code to use the object get/put and removes the mutex usage. That is, snd_jack_report(), it takes input_get_device() and leaves with input_put_device() for assuring the input_dev being assigned. Although the whole mutex could be reduced, we keep it because it can be still a protection for potential races between creation and deletion. Fixes: 1b6a6fc5280e ("ALSA: jack: Access input_dev under mutex") Reported-by: Dan Carpenter <dan.carpenter(a)linaro.org> Closes: https://lore.kernel.org/r/cf95f7fe-a748-4990-8378-000491b40329@moroto.mount… Tested-by: Amadeusz Sławiński <amadeuszx.slawinski(a)linux.intel.com> Cc: <stable(a)vger.kernel.org> Link: https://lore.kernel.org/r/20230706155357.3470-1-tiwai@suse.de Signed-off-by: Takashi Iwai <tiwai(a)suse.de> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Cheng Yu <serein.chengyu(a)huawei.com> --- sound/core/jack.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) diff --git a/sound/core/jack.c b/sound/core/jack.c index 2f43fe667759..0e26488d8db2 100644 --- a/sound/core/jack.c +++ b/sound/core/jack.c @@ -371,6 +371,7 @@ void snd_jack_report(struct snd_jack *jack, int status) { struct snd_jack_kctl *jack_kctl; #ifdef CONFIG_SND_JACK_INPUT_DEV + struct input_dev *idev; int i; #endif @@ -382,30 +383,28 @@ void snd_jack_report(struct snd_jack *jack, int status) status & jack_kctl->mask_bits); #ifdef CONFIG_SND_JACK_INPUT_DEV - mutex_lock(&jack->input_dev_lock); - if (!jack->input_dev) { - mutex_unlock(&jack->input_dev_lock); + idev = input_get_device(jack->input_dev); + if (!idev) return; - } for (i = 0; i < ARRAY_SIZE(jack->key); i++) { int testbit = SND_JACK_BTN_0 >> i; if (jack->type & testbit) - input_report_key(jack->input_dev, jack->key[i], + input_report_key(idev, jack->key[i], status & testbit); } for (i = 0; i < ARRAY_SIZE(jack_switch_types); i++) { int testbit = 1 << i; if (jack->type & testbit) - input_report_switch(jack->input_dev, + input_report_switch(idev, jack_switch_types[i], status & testbit); } - input_sync(jack->input_dev); - mutex_unlock(&jack->input_dev_lock); + input_sync(idev); + input_put_device(idev); #endif /* CONFIG_SND_JACK_INPUT_DEV */ } EXPORT_SYMBOL(snd_jack_report); -- 2.25.1

2 1

[PATCH OLK-5.10] uprobes: Reject the shared zeropage in uprobe_write_opcode()
by Chen Zhongjin 02 Apr '25

02 Apr '25

From: Tong Tiangen <tongtiangen(a)huawei.com> mainline inclusion from mainline-v6.14-rc5 commit bddf10d26e6e5114e7415a0e442ec6f51a559468 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBWVTY CVE: CVE-2025-21881 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- We triggered the following crash in syzkaller tests: BUG: Bad page state in process syz.7.38 pfn:1eff3 page: refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x1eff3 flags: 0x3fffff00004004(referenced|reserved|node=0|zone=1|lastcpupid=0x1fffff) raw: 003fffff00004004 ffffe6c6c07bfcc8 ffffe6c6c07bfcc8 0000000000000000 raw: 0000000000000000 0000000000000000 00000000fffffffe 0000000000000000 page dumped because: PAGE_FLAGS_CHECK_AT_FREE flag(s) set Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1ubuntu1.1 04/01/2014 Call Trace: <TASK> dump_stack_lvl+0x32/0x50 bad_page+0x69/0xf0 free_unref_page_prepare+0x401/0x500 free_unref_page+0x6d/0x1b0 uprobe_write_opcode+0x460/0x8e0 install_breakpoint.part.0+0x51/0x80 register_for_each_vma+0x1d9/0x2b0 __uprobe_register+0x245/0x300 bpf_uprobe_multi_link_attach+0x29b/0x4f0 link_create+0x1e2/0x280 __sys_bpf+0x75f/0xac0 __x64_sys_bpf+0x1a/0x30 do_syscall_64+0x56/0x100 entry_SYSCALL_64_after_hwframe+0x78/0xe2 BUG: Bad rss-counter state mm:00000000452453e0 type:MM_FILEPAGES val:-1 The following syzkaller test case can be used to reproduce: r2 = creat(&(0x7f0000000000)='./file0\x00', 0x8) write$nbd(r2, &(0x7f0000000580)=ANY=[], 0x10) r4 = openat(0xffffffffffffff9c, &(0x7f0000000040)='./file0\x00', 0x42, 0x0) mmap$IORING_OFF_SQ_RING(&(0x7f0000ffd000/0x3000)=nil, 0x3000, 0x0, 0x12, r4, 0x0) r5 = userfaultfd(0x80801) ioctl$UFFDIO_API(r5, 0xc018aa3f, &(0x7f0000000040)={0xaa, 0x20}) r6 = userfaultfd(0x80801) ioctl$UFFDIO_API(r6, 0xc018aa3f, &(0x7f0000000140)) ioctl$UFFDIO_REGISTER(r6, 0xc020aa00, &(0x7f0000000100)={{&(0x7f0000ffc000/0x4000)=nil, 0x4000}, 0x2}) ioctl$UFFDIO_ZEROPAGE(r5, 0xc020aa04, &(0x7f0000000000)={{&(0x7f0000ffd000/0x1000)=nil, 0x1000}}) r7 = bpf$PROG_LOAD(0x5, &(0x7f0000000140)={0x2, 0x3, &(0x7f0000000200)=ANY=[@ANYBLOB="1800000000120000000000000000000095"], &(0x7f0000000000)='GPL\x00', 0x7, 0x0, 0x0, 0x0, 0x0, '\x00', 0x0, @fallback=0x30, 0xffffffffffffffff, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x10, 0x0, @void, @value}, 0x94) bpf$BPF_LINK_CREATE_XDP(0x1c, &(0x7f0000000040)={r7, 0x0, 0x30, 0x1e, @val=@uprobe_multi={&(0x7f0000000080)='./file0\x00', &(0x7f0000000100)=[0x2], 0x0, 0x0, 0x1}}, 0x40) The cause is that zero pfn is set to the PTE without increasing the RSS count in mfill_atomic_pte_zeropage() and the refcount of zero folio does not increase accordingly. Then, the operation on the same pfn is performed in uprobe_write_opcode()->__replace_page() to unconditional decrease the RSS count and old_folio's refcount. Therefore, two bugs are introduced: 1. The RSS count is incorrect, when process exit, the check_mm() report error "Bad rss-count". 2. The reserved folio (zero folio) is freed when folio->refcount is zero, then free_pages_prepare->free_page_is_bad() report error "Bad page state". There is more, the following warning could also theoretically be triggered: __replace_page() -> ... -> folio_remove_rmap_pte() -> VM_WARN_ON_FOLIO(is_zero_folio(folio), folio) Considering that uprobe hit on the zero folio is a very rare case, just reject zero old folio immediately after get_user_page_vma_remote(). [ mingo: Cleaned up the changelog ] Fixes: 7396fa818d62 ("uprobes/core: Make background page replacement logic account for rss_stat counters") Fixes: 2b1444983508 ("uprobes, mm, x86: Add the ability to install and remove uprobes breakpoints") Signed-off-by: Tong Tiangen <tongtiangen(a)huawei.com> Signed-off-by: Ingo Molnar <mingo(a)kernel.org> Reviewed-by: David Hildenbrand <david(a)redhat.com> Reviewed-by: Oleg Nesterov <oleg(a)redhat.com> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Masami Hiramatsu <mhiramat(a)kernel.org> Link: https://lore.kernel.org/r/20250224031149.1598949-1-tongtiangen@huawei.com Signed-off-by: Chen Zhongjin <chenzhongjin(a)huawei.com> --- kernel/events/uprobes.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index e045b12662f1..424b24dd029e 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -488,6 +488,11 @@ int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm, if (ret <= 0) goto put_old; + if (is_zero_page(old_page)) { + ret = -EINVAL; + goto put_old; + } + if (WARN(!is_register && PageCompound(old_page), "uprobe unregister should never work on compound page\n")) { ret = -EINVAL; -- 2.25.1

2 1

[PATCH v2 OLK-6.6 0/5] Support the FEAT_HDBSS introduced in Armv9.5
by Zhenyu Ye 02 Apr '25

02 Apr '25

From: eillon <yezhenyu2(a)huawei.com> hulk inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/IB103D CVE: NA ---------------------------------------------------------------------- This series of patches add support to the Hardware Dirty state tracking Structure(HDBSS) feature, which is introduced by the ARM architecture in the DDI0601(ID121123) version. The HDBSS feature is an extension to the architecture that enhances tracking translation table descriptors' dirty state, identified as FEAT_HDBSS. The goal of this feature is to reduce the cost of surveying for dirtied granules, with minimal effect on recording when a granule has been dirtied. The purpose of this feature is to make the execution overhead of live migration lower to both the guest and the host, compared to existing approaches (write-protect or search stage 2 tables). After these patches, users(such as qemu) can use the KVM_CAP_ARM_HW_DIRTY_STATE_TRACK ioctl to enable or disable the HDBSS feature before and after the live migration. Changes in v2: - adapt the commit format See patches for details, Thanks. eillon (5): arm64/sysreg: add HDBSS related register information arm64/kvm: support set the DBM attr during memory abort arm64/kvm: using ioctl to enable/disable the HDBSS feature arm64/kvm: support to handle the HDBSSF event arm64/config: add config to control whether enable HDBSS feature arch/arm64/Kconfig | 12 ++++ arch/arm64/configs/openeuler_defconfig | 6 ++ arch/arm64/include/asm/cpufeature.h | 14 ++++ arch/arm64/include/asm/esr.h | 2 + arch/arm64/include/asm/kvm_arm.h | 1 + arch/arm64/include/asm/kvm_host.h | 8 +++ arch/arm64/include/asm/kvm_mmu.h | 14 ++++ arch/arm64/include/asm/kvm_pgtable.h | 1 + arch/arm64/include/asm/sysreg.h | 14 ++++ arch/arm64/kvm/arm.c | 88 ++++++++++++++++++++++++++ arch/arm64/kvm/handle_exit.c | 50 +++++++++++++++ arch/arm64/kvm/hyp/pgtable.c | 12 ++++ arch/arm64/kvm/hyp/vhe/switch.c | 3 + arch/arm64/kvm/hyp/vhe/sysreg-sr.c | 4 ++ arch/arm64/kvm/mmu.c | 17 ++++- arch/arm64/kvm/reset.c | 9 +++ arch/arm64/tools/sysreg | 28 ++++++++ include/linux/kvm_host.h | 3 + include/uapi/linux/kvm.h | 2 + tools/include/uapi/linux/kvm.h | 2 + 20 files changed, 289 insertions(+), 1 deletion(-) -- 2.39.3

2 6

[PATCH openEuler-1.0-LTS] ftrace: Avoid potential division by zero in function_stat_show()
by Pu Lehui 02 Apr '25

02 Apr '25

From: Nikolay Kuratov <kniv(a)yandex-team.ru> mainline inclusion from mainline-v6.14-rc5 commit a1a7eb89ca0b89dc1c326eeee2596f263291aca3 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IBY5DV Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Check whether denominator expression x * (x - 1) * 1000 mod {2^32, 2^64} produce zero and skip stddev computation in that case. For now don't care about rec->counter * rec->counter overflow because rec->time * rec->time overflow will likely happen earlier. Cc: stable(a)vger.kernel.org Cc: Wen Yang <wenyang(a)linux.alibaba.com> Cc: Mark Rutland <mark.rutland(a)arm.com> Cc: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> Link: https://lore.kernel.org/20250206090156.1561783-1-kniv@yandex-team.ru Fixes: e31f7939c1c27 ("ftrace: Avoid potential division by zero in function profiler") Signed-off-by: Nikolay Kuratov <kniv(a)yandex-team.ru> Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> Conflicts: kernel/trace/ftrace.c [The conflicts were due to some minor issue] Signed-off-by: Pu Lehui <pulehui(a)huawei.com> --- kernel/trace/ftrace.c | 27 ++++++++++++--------------- 1 file changed, 12 insertions(+), 15 deletions(-) diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 36de4ab34431..8199571d9ab3 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -544,6 +544,7 @@ static int function_stat_show(struct seq_file *m, void *v) static struct trace_seq s; unsigned long long avg; unsigned long long stddev; + unsigned long long stddev_denom; #endif mutex_lock(&ftrace_profile_lock); @@ -565,23 +566,19 @@ static int function_stat_show(struct seq_file *m, void *v) #ifdef CONFIG_FUNCTION_GRAPH_TRACER seq_puts(m, " "); - /* Sample standard deviation (s^2) */ - if (rec->counter <= 1) - stddev = 0; - else { - /* - * Apply Welford's method: - * s^2 = 1 / (n * (n-1)) * (n * \Sum (x_i)^2 - (\Sum x_i)^2) - */ + /* + * Variance formula: + * s^2 = 1 / (n * (n-1)) * (n * \Sum (x_i)^2 - (\Sum x_i)^2) + * Maybe Welford's method is better here? + * Divide only by 1000 for ns^2 -> us^2 conversion. + * trace_print_graph_duration will divide by 1000 again. + */ + stddev = 0; + stddev_denom = rec->counter * (rec->counter - 1) * 1000; + if (stddev_denom) { stddev = rec->counter * rec->time_squared - rec->time * rec->time; - - /* - * Divide only 1000 for ns^2 -> us^2 conversion. - * trace_print_graph_duration will divide 1000 again. - */ - stddev = div64_ul(stddev, - rec->counter * (rec->counter - 1) * 1000); + stddev = div64_ul(stddev, stddev_denom); } trace_seq_init(&s); -- 2.34.1

2 1

[PATCH OLK-6.6] ftrace: Avoid potential division by zero in function_stat_show()
by Pu Lehui 02 Apr '25

02 Apr '25

From: Nikolay Kuratov <kniv(a)yandex-team.ru> stable inclusion from stable-v6.6.81 commit f58a3f8e284d0bdf94164a8e61cd4e70d337a1a3 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IBY5DV Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit a1a7eb89ca0b89dc1c326eeee2596f263291aca3 upstream. Check whether denominator expression x * (x - 1) * 1000 mod {2^32, 2^64} produce zero and skip stddev computation in that case. For now don't care about rec->counter * rec->counter overflow because rec->time * rec->time overflow will likely happen earlier. Cc: stable(a)vger.kernel.org Cc: Wen Yang <wenyang(a)linux.alibaba.com> Cc: Mark Rutland <mark.rutland(a)arm.com> Cc: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> Link: https://lore.kernel.org/20250206090156.1561783-1-kniv@yandex-team.ru Fixes: e31f7939c1c27 ("ftrace: Avoid potential division by zero in function profiler") Signed-off-by: Nikolay Kuratov <kniv(a)yandex-team.ru> Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Pu Lehui <pulehui(a)huawei.com> --- kernel/trace/ftrace.c | 27 ++++++++++++--------------- 1 file changed, 12 insertions(+), 15 deletions(-) diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 1043936b352d..fe26b58e753f 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -538,6 +538,7 @@ static int function_stat_show(struct seq_file *m, void *v) static struct trace_seq s; unsigned long long avg; unsigned long long stddev; + unsigned long long stddev_denom; #endif mutex_lock(&ftrace_profile_lock); @@ -559,23 +560,19 @@ static int function_stat_show(struct seq_file *m, void *v) #ifdef CONFIG_FUNCTION_GRAPH_TRACER seq_puts(m, " "); - /* Sample standard deviation (s^2) */ - if (rec->counter <= 1) - stddev = 0; - else { - /* - * Apply Welford's method: - * s^2 = 1 / (n * (n-1)) * (n * \Sum (x_i)^2 - (\Sum x_i)^2) - */ + /* + * Variance formula: + * s^2 = 1 / (n * (n-1)) * (n * \Sum (x_i)^2 - (\Sum x_i)^2) + * Maybe Welford's method is better here? + * Divide only by 1000 for ns^2 -> us^2 conversion. + * trace_print_graph_duration will divide by 1000 again. + */ + stddev = 0; + stddev_denom = rec->counter * (rec->counter - 1) * 1000; + if (stddev_denom) { stddev = rec->counter * rec->time_squared - rec->time * rec->time; - - /* - * Divide only 1000 for ns^2 -> us^2 conversion. - * trace_print_graph_duration will divide 1000 again. - */ - stddev = div64_ul(stddev, - rec->counter * (rec->counter - 1) * 1000); + stddev = div64_ul(stddev, stddev_denom); } trace_seq_init(&s); -- 2.34.1

2 1

[PATCH OLK-6.6] bpf: Add tracepoints with null-able arguments
by Pu Lehui 02 Apr '25

02 Apr '25

From: Jiri Olsa <jolsa(a)kernel.org> mainline inclusion from mainline-v6.15-rc1 commit c83e2d970bae8616b94c40caa43d85f2f2c7d81e category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IBY5DV Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Some of the tracepoints slipped when we did the first scan, adding them now. Fixes: 838a10bd2ebf ("bpf: Augment raw_tp arguments with PTR_MAYBE_NULL") Signed-off-by: Jiri Olsa <jolsa(a)kernel.org> Link: https://lore.kernel.org/r/20250210175913.2893549-1-jolsa@kernel.org Signed-off-by: Alexei Starovoitov <ast(a)kernel.org> Signed-off-by: Pu Lehui <pulehui(a)huawei.com> --- kernel/bpf/btf.c | 99 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 99 insertions(+) diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index bbc99401b4e7..39fc33e6368f 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -5997,6 +5997,8 @@ static const struct bpf_raw_tp_null_args raw_tp_null_args[] = { /* rxrpc */ { "rxrpc_recvdata", 0x1 }, { "rxrpc_resend", 0x10 }, + { "rxrpc_tq", 0x10 }, + { "rxrpc_client", 0x1 }, /* sunrpc */ { "xs_stream_read_data", 0x1 }, /* ... from xprt_cong_event event class */ @@ -6017,6 +6019,103 @@ static const struct bpf_raw_tp_null_args raw_tp_null_args[] = { { "mr_integ_alloc", 0x2000 }, /* bpf_testmod */ { "bpf_testmod_test_read", 0x0 }, + /* amdgpu */ + { "amdgpu_vm_bo_map", 0x1 }, + { "amdgpu_vm_bo_unmap", 0x1 }, + /* netfs */ + { "netfs_folioq", 0x1 }, + /* xfs from xfs_defer_pending_class */ + { "xfs_defer_create_intent", 0x1 }, + { "xfs_defer_cancel_list", 0x1 }, + { "xfs_defer_pending_finish", 0x1 }, + { "xfs_defer_pending_abort", 0x1 }, + { "xfs_defer_relog_intent", 0x1 }, + { "xfs_defer_isolate_paused", 0x1 }, + { "xfs_defer_item_pause", 0x1 }, + { "xfs_defer_item_unpause", 0x1 }, + /* xfs from xfs_defer_pending_item_class */ + { "xfs_defer_add_item", 0x1 }, + { "xfs_defer_cancel_item", 0x1 }, + { "xfs_defer_finish_item", 0x1 }, + /* xfs from xfs_icwalk_class */ + { "xfs_ioc_free_eofblocks", 0x10 }, + { "xfs_blockgc_free_space", 0x10 }, + /* xfs from xfs_btree_cur_class */ + { "xfs_btree_updkeys", 0x100 }, + { "xfs_btree_overlapped_query_range", 0x100 }, + /* xfs from xfs_imap_class*/ + { "xfs_map_blocks_found", 0x10000 }, + { "xfs_map_blocks_alloc", 0x10000 }, + { "xfs_iomap_alloc", 0x1000 }, + { "xfs_iomap_found", 0x1000 }, + /* xfs from xfs_fs_class */ + { "xfs_inodegc_flush", 0x1 }, + { "xfs_inodegc_push", 0x1 }, + { "xfs_inodegc_start", 0x1 }, + { "xfs_inodegc_stop", 0x1 }, + { "xfs_inodegc_queue", 0x1 }, + { "xfs_inodegc_throttle", 0x1 }, + { "xfs_fs_sync_fs", 0x1 }, + { "xfs_blockgc_start", 0x1 }, + { "xfs_blockgc_stop", 0x1 }, + { "xfs_blockgc_worker", 0x1 }, + { "xfs_blockgc_flush_all", 0x1 }, + /* xfs_scrub */ + { "xchk_nlinks_live_update", 0x10 }, + /* xfs_scrub from xchk_metapath_class */ + { "xchk_metapath_lookup", 0x100 }, + /* nfsd */ + { "nfsd_dirent", 0x1 }, + { "nfsd_file_acquire", 0x1001 }, + { "nfsd_file_insert_err", 0x1 }, + { "nfsd_file_cons_err", 0x1 }, + /* nfs4 */ + { "nfs4_setup_sequence", 0x1 }, + { "pnfs_update_layout", 0x10000 }, + { "nfs4_inode_callback_event", 0x200 }, + { "nfs4_inode_stateid_callback_event", 0x200 }, + /* nfs from pnfs_layout_event */ + { "pnfs_mds_fallback_pg_init_read", 0x10000 }, + { "pnfs_mds_fallback_pg_init_write", 0x10000 }, + { "pnfs_mds_fallback_pg_get_mirror_count", 0x10000 }, + { "pnfs_mds_fallback_read_done", 0x10000 }, + { "pnfs_mds_fallback_write_done", 0x10000 }, + { "pnfs_mds_fallback_read_pagelist", 0x10000 }, + { "pnfs_mds_fallback_write_pagelist", 0x10000 }, + /* coda */ + { "coda_dec_pic_run", 0x10 }, + { "coda_dec_pic_done", 0x10 }, + /* cfg80211 */ + { "cfg80211_scan_done", 0x11 }, + { "rdev_set_coalesce", 0x10 }, + { "cfg80211_report_wowlan_wakeup", 0x100 }, + { "cfg80211_inform_bss_frame", 0x100 }, + { "cfg80211_michael_mic_failure", 0x10000 }, + /* cfg80211 from wiphy_work_event */ + { "wiphy_work_queue", 0x10 }, + { "wiphy_work_run", 0x10 }, + { "wiphy_work_cancel", 0x10 }, + { "wiphy_work_flush", 0x10 }, + /* hugetlbfs */ + { "hugetlbfs_alloc_inode", 0x10 }, + /* spufs */ + { "spufs_context", 0x10 }, + /* kvm_hv */ + { "kvm_page_fault_enter", 0x100 }, + /* dpu */ + { "dpu_crtc_setup_mixer", 0x100 }, + /* binder */ + { "binder_transaction", 0x100 }, + /* bcachefs */ + { "btree_path_free", 0x100 }, + /* hfi1_tx */ + { "hfi1_sdma_progress", 0x1000 }, + /* iptfs */ + { "iptfs_ingress_postq_event", 0x1000 }, + /* neigh */ + { "neigh_update", 0x10 }, + /* snd_firewire_lib */ + { "amdtp_packet", 0x100 }, }; bool btf_ctx_access(int off, int size, enum bpf_access_type type, -- 2.34.1

2 1

[openeuler:OLK-5.10 2830/2830] fs/xfs/libxfs/xfs_da_btree.o: warning: objtool: xfs_da3_split()+0x787: unreachable instruction
by kernel test robot 02 Apr '25

02 Apr '25

tree: https://gitee.com/openeuler/kernel.git OLK-5.10 head: 411f2e6e24ad11083d85f2ab7324b1f77ad0d371 commit: f2c902d8c653f8021f9761092a27f7b9db42b662 [2830/2830] tracing: Make tracepoint lockdep check actually test something config: x86_64-buildonly-randconfig-004-20250331 (https://download.01.org/0day-ci/archive/20250402/202504021010.h7TdpCwx-lkp@…) compiler: clang version 20.1.1 (https://github.com/llvm/llvm-project 424c2d9b7e4de40d0804dd374721e6411c27d1d1) reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20250402/202504021010.h7TdpCwx-lkp@…) If you fix the issue in a separate patch/commit (i.e. not just a new version of the same patch/commit), kindly add following tags | Reported-by: kernel test robot <lkp(a)intel.com> | Closes: https://lore.kernel.org/oe-kbuild-all/202504021010.h7TdpCwx-lkp@intel.com/ All warnings (new ones prefixed by >>): >> fs/xfs/libxfs/xfs_da_btree.o: warning: objtool: xfs_da3_split()+0x787: unreachable instruction -- >> fs/xfs/libxfs/xfs_attr_leaf.o: warning: objtool: xfs_attr3_leaf_split()+0x2da: unreachable instruction -- 0-DAY CI Kernel Test Service https://github.com/intel/lkp-tests/wiki

1 0

[PATCH openEuler-1.0-LTS] dmaengine: Fix double increment of client_count in dma_chan_get()
by Xiaomeng Zhang 02 Apr '25

02 Apr '25

From: Koba Ko <koba.ko(a)canonical.com> stable inclusion from stable-v4.19.272 commit c6221afe573413fd2981e291f7df4a58283e0654 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IBWVX7 CVE: CVE-2022-49753 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit f3dc1b3b4750851a94212dba249703dd0e50bb20 ] The first time dma_chan_get() is called for a channel the channel client_count is incorrectly incremented twice for public channels, first in balance_ref_count(), and again prior to returning. This results in an incorrect client count which will lead to the channel resources not being freed when they should be. A simple test of repeated module load and unload of async_tx on a Dell Power Edge R7425 also shows this resulting in a kref underflow warning. [ 124.329662] async_tx: api initialized (async) [ 129.000627] async_tx: api initialized (async) [ 130.047839] ------------[ cut here ]------------ [ 130.052472] refcount_t: underflow; use-after-free. [ 130.057279] WARNING: CPU: 3 PID: 19364 at lib/refcount.c:28 refcount_warn_saturate+0xba/0x110 [ 130.065811] Modules linked in: async_tx(-) rfkill intel_rapl_msr intel_rapl_common amd64_edac edac_mce_amd ipmi_ssif kvm_amd dcdbas kvm mgag200 drm_shmem_helper acpi_ipmi irqbypass drm_kms_helper ipmi_si syscopyarea sysfillrect rapl pcspkr ipmi_devintf sysimgblt fb_sys_fops k10temp i2c_piix4 ipmi_msghandler acpi_power_meter acpi_cpufreq vfat fat drm fuse xfs libcrc32c sd_mod t10_pi sg ahci crct10dif_pclmul libahci crc32_pclmul crc32c_intel ghash_clmulni_intel igb megaraid_sas i40e libata i2c_algo_bit ccp sp5100_tco dca dm_mirror dm_region_hash dm_log dm_mod [last unloaded: async_tx] [ 130.117361] CPU: 3 PID: 19364 Comm: modprobe Kdump: loaded Not tainted 5.14.0-185.el9.x86_64 #1 [ 130.126091] Hardware name: Dell Inc. PowerEdge R7425/02MJ3T, BIOS 1.18.0 01/17/2022 [ 130.133806] RIP: 0010:refcount_warn_saturate+0xba/0x110 [ 130.139041] Code: 01 01 e8 6d bd 55 00 0f 0b e9 72 9d 8a 00 80 3d 26 18 9c 01 00 75 85 48 c7 c7 f8 a3 03 9d c6 05 16 18 9c 01 01 e8 4a bd 55 00 <0f> 0b e9 4f 9d 8a 00 80 3d 01 18 9c 01 00 0f 85 5e ff ff ff 48 c7 [ 130.157807] RSP: 0018:ffffbf98898afe68 EFLAGS: 00010286 [ 130.163036] RAX: 0000000000000000 RBX: ffff9da06028e598 RCX: 0000000000000000 [ 130.170172] RDX: ffff9daf9de26480 RSI: ffff9daf9de198a0 RDI: ffff9daf9de198a0 [ 130.177316] RBP: ffff9da7cddf3970 R08: 0000000000000000 R09: 00000000ffff7fff [ 130.184459] R10: ffffbf98898afd00 R11: ffffffff9d9e8c28 R12: ffff9da7cddf1970 [ 130.191596] R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 [ 130.198739] FS: 00007f646435c740(0000) GS:ffff9daf9de00000(0000) knlGS:0000000000000000 [ 130.206832] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 130.212586] CR2: 00007f6463b214f0 CR3: 00000008ab98c000 CR4: 00000000003506e0 [ 130.219729] Call Trace: [ 130.222192] <TASK> [ 130.224305] dma_chan_put+0x10d/0x110 [ 130.227988] dmaengine_put+0x7a/0xa0 [ 130.231575] __do_sys_delete_module.constprop.0+0x178/0x280 [ 130.237157] ? syscall_trace_enter.constprop.0+0x145/0x1d0 [ 130.242652] do_syscall_64+0x5c/0x90 [ 130.246240] ? exc_page_fault+0x62/0x150 [ 130.250178] entry_SYSCALL_64_after_hwframe+0x63/0xcd [ 130.255243] RIP: 0033:0x7f6463a3f5ab [ 130.258830] Code: 73 01 c3 48 8b 0d 75 a8 1b 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa b8 b0 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 45 a8 1b 00 f7 d8 64 89 01 48 [ 130.277591] RSP: 002b:00007fff22f972c8 EFLAGS: 00000206 ORIG_RAX: 00000000000000b0 [ 130.285164] RAX: ffffffffffffffda RBX: 000055b6786edd40 RCX: 00007f6463a3f5ab [ 130.292303] RDX: 0000000000000000 RSI: 0000000000000800 RDI: 000055b6786edda8 [ 130.299443] RBP: 000055b6786edd40 R08: 0000000000000000 R09: 0000000000000000 [ 130.306584] R10: 00007f6463b9eac0 R11: 0000000000000206 R12: 000055b6786edda8 [ 130.313731] R13: 0000000000000000 R14: 000055b6786edda8 R15: 00007fff22f995f8 [ 130.320875] </TASK> [ 130.323081] ---[ end trace eff7156d56b5cf25 ]--- cat /sys/class/dma/dma0chan*/in_use would get the wrong result. 2 2 2 Fixes: d2f4f99db3e9 ("dmaengine: Rework dma_chan_get") Signed-off-by: Koba Ko <koba.ko(a)canonical.com> Reviewed-by: Jie Hai <haijie1(a)huawei.com> Test-by: Jie Hai <haijie1(a)huawei.com> Reviewed-by: Jerry Snitselaar <jsnitsel(a)redhat.com> Reviewed-by: Dave Jiang <dave.jiang(a)intel.com> Tested-by: Joel Savitz <jsavitz(a)redhat.com> Link: https://lore.kernel.org/r/20221201030050.978595-1-koba.ko@canonical.com Signed-off-by: Vinod Koul <vkoul(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Wang Hai <wanghai38(a)huawei.com> Signed-off-by: Xiaomeng Zhang <zhangxiaomeng13(a)huawei.com> --- drivers/dma/dmaengine.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c index f1a441ab395d..450b1c4b2129 100644 --- a/drivers/dma/dmaengine.c +++ b/drivers/dma/dmaengine.c @@ -223,7 +223,8 @@ static int dma_chan_get(struct dma_chan *chan) /* The channel is already in use, update client count */ if (chan->client_count) { __module_get(owner); - goto out; + chan->client_count++; + return 0; } if (!try_module_get(owner)) @@ -236,11 +237,11 @@ static int dma_chan_get(struct dma_chan *chan) goto err_out; } + chan->client_count++; + if (!dma_has_cap(DMA_PRIVATE, chan->device->cap_mask)) balance_ref_count(chan); -out: - chan->client_count++; return 0; err_out: -- 2.34.1

2 1