- Kernel - mailweb.openeuler.org

[PATCH OLK-5.10] mm/compaction: fix UBSAN shift-out-of-bounds warning
by Liu Shixin 05 Feb '25

05 Feb '25

mainline inclusion from mainline-v6.14-rc1 commit d1366e74342e75555af2648a2964deb2d5c92200 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IBK36F Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- syzkaller reported a UBSAN shift-out-of-bounds warning of (1UL << order) in isolate_freepages_block(). The bogus compound_order can be any value because it is union with flags. Add back the MAX_PAGE_ORDER check to fix the warning. Link: https://lkml.kernel.org/r/20250123021029.2826736-1-liushixin2@huawei.com Fixes: 3da0272a4c7d ("mm/compaction: correctly return failure with bogus compound_order in strict mode") Signed-off-by: Liu Shixin <liushixin2(a)huawei.com> Reviewed-by: Kemeng Shi <shikemeng(a)huaweicloud.com> Acked-by: David Hildenbrand <david(a)redhat.com> Reviewed-by: Oscar Salvador <osalvador(a)suse.de> Cc: Baolin Wang <baolin.wang(a)linux.alibaba.com> Cc: David Hildenbrand <david(a)redhat.com> Cc: Kemeng Shi <shikemeng(a)huaweicloud.com> Cc: Matthew Wilcox <willy(a)infradead.org> Cc: Mel Gorman <mgorman(a)techsingularity.net> Cc: Nanyong Sun <sunnanyong(a)huawei.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Conflicts: mm/compaction.c [ This is partial revert of commit 5d2cd4265a04. ] Signed-off-by: Liu Shixin <liushixin2(a)huawei.com> --- mm/compaction.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/mm/compaction.c b/mm/compaction.c index 6035aa46c8ac..c0874138ec3a 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -599,7 +599,8 @@ static unsigned long isolate_freepages_block(struct compact_control *cc, if (PageCompound(page)) { const unsigned int order = compound_order(page); - if (blockpfn + (1UL << order) <= end_pfn) { + if (likely(order < MAX_ORDER) && + (blockpfn + (1UL << order) <= end_pfn)) { blockpfn += (1UL << order) - 1; cursor += (1UL << order) - 1; } -- 2.34.1

2 1

[PATCH OLK-6.6] mm/compaction: fix UBSAN shift-out-of-bounds warning
by Liu Shixin 05 Feb '25

05 Feb '25

mainline inclusion from mainline-v6.14-rc1 commit d1366e74342e75555af2648a2964deb2d5c92200 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IBK4CZ Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- syzkaller reported a UBSAN shift-out-of-bounds warning of (1UL << order) in isolate_freepages_block(). The bogus compound_order can be any value because it is union with flags. Add back the MAX_PAGE_ORDER check to fix the warning. Link: https://lkml.kernel.org/r/20250123021029.2826736-1-liushixin2@huawei.com Fixes: 3da0272a4c7d ("mm/compaction: correctly return failure with bogus compound_order in strict mode") Signed-off-by: Liu Shixin <liushixin2(a)huawei.com> Reviewed-by: Kemeng Shi <shikemeng(a)huaweicloud.com> Acked-by: David Hildenbrand <david(a)redhat.com> Reviewed-by: Oscar Salvador <osalvador(a)suse.de> Cc: Baolin Wang <baolin.wang(a)linux.alibaba.com> Cc: David Hildenbrand <david(a)redhat.com> Cc: Kemeng Shi <shikemeng(a)huaweicloud.com> Cc: Matthew Wilcox <willy(a)infradead.org> Cc: Mel Gorman <mgorman(a)techsingularity.net> Cc: Nanyong Sun <sunnanyong(a)huawei.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Liu Shixin <liushixin2(a)huawei.com> --- mm/compaction.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/mm/compaction.c b/mm/compaction.c index e2735752c374..4a3a5c7607f3 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -650,7 +650,8 @@ static unsigned long isolate_freepages_block(struct compact_control *cc, if (PageCompound(page)) { const unsigned int order = compound_order(page); - if (blockpfn + (1UL << order) <= end_pfn) { + if ((order <= MAX_PAGE_ORDER) && + (blockpfn + (1UL << order) <= end_pfn)) { blockpfn += (1UL << order) - 1; page += (1UL << order) - 1; nr_scanned += (1UL << order) - 1; -- 2.34.1

2 1

[PATCH OLK-6.6] arm64: ptrace: fix partial SETREGSET for NT_ARM_TAGGED_ADDR_CTRL
by Liu Mingrui 05 Feb '25

05 Feb '25

From: Mark Rutland <mark.rutland(a)arm.com> stable inclusion from stable-v6.6.66 commit 96035c0093db258975b8887676afe59a64c34a72 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IBH1XN CVE: CVE-2024-57874 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit ca62d90085f4af36de745883faab9f8a7cbb45d3 upstream. Currently tagged_addr_ctrl_set() doesn't initialize the temporary 'ctrl' variable, and a SETREGSET call with a length of zero will leave this uninitialized. Consequently tagged_addr_ctrl_set() will consume an arbitrary value, potentially leaking up to 64 bits of memory from the kernel stack. The read is limited to a specific slot on the stack, and the issue does not provide a write mechanism. As set_tagged_addr_ctrl() only accepts values where bits [63:4] zero and rejects other values, a partial SETREGSET attempt will randomly succeed or fail depending on the value of the uninitialized value, and the exposure is significantly limited. Fix this by initializing the temporary value before copying the regset from userspace, as for other regsets (e.g. NT_PRSTATUS, NT_PRFPREG, NT_ARM_SYSTEM_CALL). In the case of a zero-length write, the existing value of the tagged address ctrl will be retained. The NT_ARM_TAGGED_ADDR_CTRL regset is only visible in the user_aarch64_view used by a native AArch64 task to manipulate another native AArch64 task. As get_tagged_addr_ctrl() only returns an error value when called for a compat task, tagged_addr_ctrl_get() and tagged_addr_ctrl_set() should never observe an error value from get_tagged_addr_ctrl(). Add a WARN_ON_ONCE() to both to indicate that such an error would be unexpected, and error handlnig is not missing in either case. Fixes: 2200aa7154cb ("arm64: mte: ptrace: Add NT_ARM_TAGGED_ADDR_CTRL regset") Cc: <stable(a)vger.kernel.org> # 5.10.x Signed-off-by: Mark Rutland <mark.rutland(a)arm.com> Cc: Will Deacon <will(a)kernel.org> Reviewed-by: Mark Brown <broonie(a)kernel.org> Link: https://lore.kernel.org/r/20241205121655.1824269-2-mark.rutland@arm.com Signed-off-by: Catalin Marinas <catalin.marinas(a)arm.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: ZhangPeng <zhangpeng362(a)huawei.com> Signed-off-by: Liu Mingrui <liumingrui(a)huawei.com> --- arch/arm64/kernel/ptrace.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 28a5ddcf0a1e..d34b57caad49 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -1384,7 +1384,7 @@ static int tagged_addr_ctrl_get(struct task_struct *target, { long ctrl = get_tagged_addr_ctrl(target); - if (IS_ERR_VALUE(ctrl)) + if (WARN_ON_ONCE(IS_ERR_VALUE(ctrl))) return ctrl; return membuf_write(&to, &ctrl, sizeof(ctrl)); @@ -1398,6 +1398,10 @@ static int tagged_addr_ctrl_set(struct task_struct *target, const struct int ret; long ctrl; + ctrl = get_tagged_addr_ctrl(target); + if (WARN_ON_ONCE(IS_ERR_VALUE(ctrl))) + return ctrl; + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &ctrl, 0, -1); if (ret) return ret; -- 2.25.1

2 1

[PATCH openEuler-1.0-LTS] ALSA: seq: oss: Fix races at processing SysEx messages
by Gu Bowen 05 Feb '25

05 Feb '25

From: Takashi Iwai <tiwai(a)suse.de> stable inclusion from stable-v6.6.70 commit d2392b79d8af3714ea8878b71c66dc49d3110f44 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBID2T CVE: CVE-2024-57893 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 0179488ca992d79908b8e26b9213f1554fc5bacc upstream. OSS sequencer handles the SysEx messages split in 6 bytes packets, and ALSA sequencer OSS layer tries to combine those. It stores the data in the internal buffer and this access is racy as of now, which may lead to the out-of-bounds access. As a temporary band-aid fix, introduce a mutex for serializing the process of the SysEx message packets. Reported-by: Kun Hu <huk23(a)m.fudan.edu.cn> Closes: https://lore.kernel.org/2B7E93E4-B13A-4AE4-8E87-306A8EE9BBB7@m.fudan.edu.cn Cc: <stable(a)vger.kernel.org> Link: https://patch.msgid.link/20241230110543.32454-1-tiwai@suse.de Signed-off-by: Takashi Iwai <tiwai(a)suse.de> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Conflicts: sound/core/seq/oss/seq_oss_synth.c [Commit 54da6a092431("locking: Introduce __cleanup() based infrastructure") not merged, The guard() function is not introduced.] Signed-off-by: Gu Bowen <gubowen5(a)huawei.com> --- sound/core/seq/oss/seq_oss_synth.c | 23 +++++++++++++++++------ 1 file changed, 17 insertions(+), 6 deletions(-) diff --git a/sound/core/seq/oss/seq_oss_synth.c b/sound/core/seq/oss/seq_oss_synth.c index c93945917235..33dbe0223326 100644 --- a/sound/core/seq/oss/seq_oss_synth.c +++ b/sound/core/seq/oss/seq_oss_synth.c @@ -79,6 +79,7 @@ static struct seq_oss_synth midi_synth_dev = { }; static DEFINE_SPINLOCK(register_lock); +static DEFINE_MUTEX(sysex_mutex); /* * prototypes @@ -504,16 +505,20 @@ snd_seq_oss_synth_sysex(struct seq_oss_devinfo *dp, int dev, unsigned char *buf, unsigned char *dest; struct seq_oss_synth_sysex *sysex; struct seq_oss_synthinfo *info; + int err = -EINVAL; info = snd_seq_oss_synth_info(dp, dev); if (!info) return -ENXIO; + mutex_lock(&sysex_mutex); sysex = info->sysex; if (sysex == NULL) { sysex = kzalloc(sizeof(*sysex), GFP_KERNEL); - if (sysex == NULL) - return -ENOMEM; + if (sysex == NULL) { + err = -ENOMEM; + goto unlock_sysex; + } info->sysex = sysex; } @@ -538,19 +543,25 @@ snd_seq_oss_synth_sysex(struct seq_oss_devinfo *dp, int dev, unsigned char *buf, if (sysex->skip) { sysex->skip = 0; sysex->len = 0; - return -EINVAL; /* skip */ + err = -EINVAL; /* skip */ + goto unlock_sysex; } /* copy the data to event record and send it */ ev->flags = SNDRV_SEQ_EVENT_LENGTH_VARIABLE; - if (snd_seq_oss_synth_addr(dp, dev, ev)) - return -EINVAL; + if (snd_seq_oss_synth_addr(dp, dev, ev)) { + err = -EINVAL; + goto unlock_sysex; + } ev->data.ext.len = sysex->len; ev->data.ext.ptr = sysex->buf; sysex->len = 0; + mutex_unlock(&sysex_mutex); return 0; } - return -EINVAL; /* skip */ +unlock_sysex: + mutex_unlock(&sysex_mutex); + return err; /* skip */ } /* -- 2.25.1

2 1

[PATCH OLK-5.10] usb: typec: fix potential array underflow in ucsi_ccg_sync_control()
by GONG Ruiqi 05 Feb '25

05 Feb '25

From: Dan Carpenter <dan.carpenter(a)linaro.org> mainline inclusion from mainline-v6.13-rc1 commit e56aac6e5a25630645607b6856d4b2a17b2311a5 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBEAFV CVE: CVE-2024-53203 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- The "command" variable can be controlled by the user via debugfs. The worry is that if con_index is zero then "&uc->ucsi->connector[con_index - 1]" would be an array underflow. Fixes: 170a6726d0e2 ("usb: typec: ucsi: add support for separate DP altmode devices") Signed-off-by: Dan Carpenter <dan.carpenter(a)linaro.org> Reviewed-by: Heikki Krogerus <heikki.krogerus(a)linux.intel.com> Link: https://lore.kernel.org/r/c69ef0b3-61b0-4dde-98dd-97b97f81d912@stanley.moun… Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Conflicts: drivers/usb/typec/ucsi/ucsi_ccg.c [It comes from two reasons: 1. the lack of commit 13f2ec3115c8, which refactors ucsi_ccg_sync_write() to ucsi_ccg_sync_control(); 2. a possible error within the original upstream patch, causing the imbalance of pm_runtime_{get,put}_sync().] Signed-off-by: GONG Ruiqi <gongruiqi1(a)huawei.com> --- drivers/usb/typec/ucsi/ucsi_ccg.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/usb/typec/ucsi/ucsi_ccg.c b/drivers/usb/typec/ucsi/ucsi_ccg.c index 6db7c8ddd51c..2f2cb3fc8581 100644 --- a/drivers/usb/typec/ucsi/ucsi_ccg.c +++ b/drivers/usb/typec/ucsi/ucsi_ccg.c @@ -571,6 +571,10 @@ static int ucsi_ccg_sync_write(struct ucsi *ucsi, unsigned int offset, uc->has_multiple_dp) { con_index = (uc->last_cmd_sent >> 16) & UCSI_CMD_CONNECTOR_MASK; + if (con_index == 0) { + ret = -EINVAL; + goto err_clear_bit; + } con = &uc->ucsi->connector[con_index - 1]; ucsi_ccg_update_set_new_cam_cmd(uc, con, (u64 *)val); } -- 2.25.1

2 1

[PATCH OLK-6.6 0/3] mainline patches
by Chen Ridong 05 Feb '25

05 Feb '25

mainline patches Chen Ridong (2): Revert "cgroup: Fix memory leak caused by missing cgroup_bpf_offline" cgroup/bpf: only cgroup v2 can be attached by bpf programs Waiman Long (1): cgroup/cpuset: Prevent leakage of isolated CPUs into sched domains kernel/cgroup/cgroup.c | 21 ++++++++++++--------- kernel/cgroup/cpuset.c | 10 +++++++++- 2 files changed, 21 insertions(+), 10 deletions(-) -- 2.34.1

2 4

[PATCH OLK-6.6] [Backport] ksmbd: fix a missing return value check bug
by Yongjian Sun 05 Feb '25

05 Feb '25

From: Wentao Liang <liangwentao(a)iscas.ac.cn> mainline inclusion from mainline-v6.12-rc3 commit 4c16e1cadcbcaf3c82d5fc310fbd34d0f5d0db7c category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBIQXA CVE: CVE-2024-57925 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- In the smb2_send_interim_resp(), if ksmbd_alloc_work_struct() fails to allocate a node, it returns a NULL pointer to the in_work pointer. This can lead to an illegal memory write of in_work->response_buf when allocate_interim_rsp_buf() attempts to perform a kzalloc() on it. To address this issue, incorporating a check for the return value of ksmbd_alloc_work_struct() ensures that the function returns immediately upon allocation failure, thereby preventing the aforementioned illegal memory access. Fixes: 041bba4414cd ("ksmbd: fix wrong interim response on compound") Signed-off-by: Wentao Liang <liangwentao(a)iscas.ac.cn> Acked-by: Namjae Jeon <linkinjeon(a)kernel.org> Signed-off-by: Steve French <stfrench(a)microsoft.com> Signed-off-by: Yongjian Sun <sunyongjian1(a)huawei.com> --- fs/smb/server/smb2pdu.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 27a61cb8b487..ceb10a346a72 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -689,6 +689,9 @@ void smb2_send_interim_resp(struct ksmbd_work *work, __le32 status) struct smb2_hdr *rsp_hdr; struct ksmbd_work *in_work = ksmbd_alloc_work_struct(); + if (!in_work) + return; + if (allocate_interim_rsp_buf(in_work)) { pr_err("smb_allocate_rsp_buf failed!\n"); ksmbd_free_work_struct(in_work); -- 2.39.2

2 1

[PATCH OLK-6.6] net/smc: check v2_ext_offset/eid_cnt/ism_gid_cnt when receiving proposal msg
by Zeng Heng 05 Feb '25

05 Feb '25

From: Guangguan Wang <guangguan.wang(a)linux.alibaba.com> stable inclusion from stable-v6.6.68 commit 295a92e3df32e72aff0f4bc25c310e349d07ffbf category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBJCCV CVE: CVE-2024-49568 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 7863c9f3d24ba49dbead7e03dfbe40deb5888fdf ] When receiving proposal msg in server, the fields v2_ext_offset/ eid_cnt/ism_gid_cnt in proposal msg are from the remote client and can not be fully trusted. Especially the field v2_ext_offset, once exceed the max value, there has the chance to access wrong address, and crash may happen. This patch checks the fields v2_ext_offset/eid_cnt/ism_gid_cnt before using them. Fixes: 8c3dca341aea ("net/smc: build and send V2 CLC proposal") Signed-off-by: Guangguan Wang <guangguan.wang(a)linux.alibaba.com> Reviewed-by: Wen Gu <guwen(a)linux.alibaba.com> Reviewed-by: D. Wythe <alibuda(a)linux.alibaba.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Conflicts: net/smc/smc_clc.c [Fix context conflict.] Signed-off-by: Zeng Heng <zengheng4(a)huawei.com> --- net/smc/af_smc.c | 3 ++- net/smc/smc_clc.c | 8 +++++++- net/smc/smc_clc.h | 8 +++++++- 3 files changed, 16 insertions(+), 3 deletions(-) diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 6881fd03ef25..1ad7b05893af 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -2280,7 +2280,8 @@ static void smc_find_rdma_v2_device_serv(struct smc_sock *new_smc, goto not_found; smc_v2_ext = smc_get_clc_v2_ext(pclc); - if (!smc_clc_match_eid(ini->negotiated_eid, smc_v2_ext, NULL, NULL)) + if (!smc_v2_ext || + !smc_clc_match_eid(ini->negotiated_eid, smc_v2_ext, NULL, NULL)) goto not_found; /* prepare RDMA check */ diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index d96ad04e7dcf..3d0139250cc8 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -352,7 +352,6 @@ static bool smc_clc_msg_prop_valid(struct smc_clc_msg_proposal *pclc) struct smc_clc_msg_hdr *hdr = &pclc->hdr; struct smc_clc_v2_extension *v2_ext; - v2_ext = smc_get_clc_v2_ext(pclc); pclc_prfx = smc_clc_proposal_get_prefix(pclc); if (hdr->version == SMC_V1) { if (hdr->typev1 == SMC_TYPE_N) @@ -365,6 +364,13 @@ static bool smc_clc_msg_prop_valid(struct smc_clc_msg_proposal *pclc) sizeof(struct smc_clc_msg_trail)) return false; } else { + v2_ext = smc_get_clc_v2_ext(pclc); + if ((hdr->typev2 != SMC_TYPE_N && + (!v2_ext || v2_ext->hdr.eid_cnt > SMC_CLC_MAX_UEID)) || + (smcd_indicated(hdr->typev2) && + v2_ext->hdr.ism_gid_cnt > SMCD_CLC_MAX_V2_GID_ENTRIES)) + return false; + if (ntohs(hdr->length) != sizeof(*pclc) + sizeof(struct smc_clc_msg_smcd) + diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h index 58777b6a0dfe..0ddf0f5307a7 100644 --- a/net/smc/smc_clc.h +++ b/net/smc/smc_clc.h @@ -366,8 +366,14 @@ static inline struct smc_clc_v2_extension * smc_get_clc_v2_ext(struct smc_clc_msg_proposal *prop) { struct smc_clc_msg_smcd *prop_smcd = smc_get_clc_msg_smcd(prop); + u16 max_offset; - if (!prop_smcd || !ntohs(prop_smcd->v2_ext_offset)) + max_offset = offsetof(struct smc_clc_msg_proposal_area, pclc_v2_ext) - + offsetof(struct smc_clc_msg_proposal_area, pclc_smcd) - + offsetofend(struct smc_clc_msg_smcd, v2_ext_offset); + + if (!prop_smcd || !ntohs(prop_smcd->v2_ext_offset) || + ntohs(prop_smcd->v2_ext_offset) > max_offset) return NULL; return (struct smc_clc_v2_extension *) -- 2.25.1

2 1

[PATCH OLK-6.6] workqueue: Do not warn when cancelling WQ_MEM_RECLAIM work from !WQ_MEM_RECLAIM worker
by Zeng Heng 05 Feb '25

05 Feb '25

From: Tvrtko Ursulin <tvrtko.ursulin(a)igalia.com> stable inclusion from stable-v6.6.72 commit 1fd2a57dcb4de3cb40844a29c71b5d7b46a84334 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBID2Z CVE: CVE-2024-57888 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit de35994ecd2dd6148ab5a6c5050a1670a04dec77 ] After commit 746ae46c1113 ("drm/sched: Mark scheduler work queues with WQ_MEM_RECLAIM") amdgpu started seeing the following warning: [ ] workqueue: WQ_MEM_RECLAIM sdma0:drm_sched_run_job_work [gpu_sched] is flushing !WQ_MEM_RECLAIM events:amdgpu_device_delay_enable_gfx_off [amdgpu] ... [ ] Workqueue: sdma0 drm_sched_run_job_work [gpu_sched] ... [ ] Call Trace: [ ] <TASK> ... [ ] ? check_flush_dependency+0xf5/0x110 ... [ ] cancel_delayed_work_sync+0x6e/0x80 [ ] amdgpu_gfx_off_ctrl+0xab/0x140 [amdgpu] [ ] amdgpu_ring_alloc+0x40/0x50 [amdgpu] [ ] amdgpu_ib_schedule+0xf4/0x810 [amdgpu] [ ] ? drm_sched_run_job_work+0x22c/0x430 [gpu_sched] [ ] amdgpu_job_run+0xaa/0x1f0 [amdgpu] [ ] drm_sched_run_job_work+0x257/0x430 [gpu_sched] [ ] process_one_work+0x217/0x720 ... [ ] </TASK> The intent of the verifcation done in check_flush_depedency is to ensure forward progress during memory reclaim, by flagging cases when either a memory reclaim process, or a memory reclaim work item is flushed from a context not marked as memory reclaim safe. This is correct when flushing, but when called from the cancel(_delayed)_work_sync() paths it is a false positive because work is either already running, or will not be running at all. Therefore cancelling it is safe and we can relax the warning criteria by letting the helper know of the calling context. Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin(a)igalia.com> Fixes: fca839c00a12 ("workqueue: warn if memory reclaim tries to flush !WQ_MEM_RECLAIM workqueue") References: 746ae46c1113 ("drm/sched: Mark scheduler work queues with WQ_MEM_RECLAIM") Cc: Tejun Heo <tj(a)kernel.org> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Lai Jiangshan <jiangshanlai(a)gmail.com> Cc: Alex Deucher <alexander.deucher(a)amd.com> Cc: Christian König <christian.koenig(a)amd.com Cc: Matthew Brost <matthew.brost(a)intel.com> Cc: <stable(a)vger.kernel.org> # v4.5+ Signed-off-by: Tejun Heo <tj(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Conflicts: kernel/workqueue.c [Fix context conflict.] Signed-off-by: Zeng Heng <zengheng4(a)huawei.com> --- kernel/workqueue.c | 22 +++++++++++++--------- 1 file changed, 13 insertions(+), 9 deletions(-) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 5bb2fba9cb8a..db78a74f5455 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -2940,23 +2940,27 @@ static int rescuer_thread(void *__rescuer) * check_flush_dependency - check for flush dependency sanity * @target_wq: workqueue being flushed * @target_work: work item being flushed (NULL for workqueue flushes) + * @from_cancel: are we called from the work cancel path * * %current is trying to flush the whole @target_wq or @target_work on it. - * If @target_wq doesn't have %WQ_MEM_RECLAIM, verify that %current is not - * reclaiming memory or running on a workqueue which doesn't have - * %WQ_MEM_RECLAIM as that can break forward-progress guarantee leading to - * a deadlock. + * If this is not the cancel path (which implies work being flushed is either + * already running, or will not be at all), check if @target_wq doesn't have + * %WQ_MEM_RECLAIM and verify that %current is not reclaiming memory or running + * on a workqueue which doesn't have %WQ_MEM_RECLAIM as that can break forward- + * progress guarantee leading to a deadlock. */ static void check_flush_dependency(struct workqueue_struct *target_wq, - struct work_struct *target_work) + struct work_struct *target_work, + bool from_cancel) { - work_func_t target_func = target_work ? target_work->func : NULL; + work_func_t target_func; struct worker *worker; - if (target_wq->flags & WQ_MEM_RECLAIM) + if (from_cancel || target_wq->flags & WQ_MEM_RECLAIM) return; worker = current_wq_worker(); + target_func = target_work ? target_work->func : NULL; WARN_ONCE(current->flags & PF_MEMALLOC, "workqueue: PF_MEMALLOC task %d(%s) is flushing !WQ_MEM_RECLAIM %s:%ps", @@ -3189,7 +3193,7 @@ void __flush_workqueue(struct workqueue_struct *wq) list_add_tail(&this_flusher.list, &wq->flusher_overflow); } - check_flush_dependency(wq, NULL); + check_flush_dependency(wq, NULL, false); mutex_unlock(&wq->mutex); @@ -3364,7 +3368,7 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr, pwq = worker->current_pwq; } - check_flush_dependency(pwq->wq, work); + check_flush_dependency(pwq->wq, work, from_cancel); insert_wq_barrier(pwq, barr, work, worker); raw_spin_unlock_irq(&pool->lock); -- 2.25.1

2 1

[PATCH OLK-6.6] net/smc: check v2_ext_offset/eid_cnt/ism_gid_cnt when receiving proposal msg
by Zeng Heng 05 Feb '25

05 Feb '25

From: Guangguan Wang <guangguan.wang(a)linux.alibaba.com> stable inclusion from stable-v6.6.68 commit 295a92e3df32e72aff0f4bc25c310e349d07ffbf category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IBH1XN Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 7863c9f3d24ba49dbead7e03dfbe40deb5888fdf ] When receiving proposal msg in server, the fields v2_ext_offset/ eid_cnt/ism_gid_cnt in proposal msg are from the remote client and can not be fully trusted. Especially the field v2_ext_offset, once exceed the max value, there has the chance to access wrong address, and crash may happen. This patch checks the fields v2_ext_offset/eid_cnt/ism_gid_cnt before using them. Fixes: 8c3dca341aea ("net/smc: build and send V2 CLC proposal") Signed-off-by: Guangguan Wang <guangguan.wang(a)linux.alibaba.com> Reviewed-by: Wen Gu <guwen(a)linux.alibaba.com> Reviewed-by: D. Wythe <alibuda(a)linux.alibaba.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Conflicts: net/smc/smc_clc.c [Fix context conflict.] Signed-off-by: Zeng Heng <zengheng4(a)huawei.com> --- net/smc/af_smc.c | 3 ++- net/smc/smc_clc.c | 8 +++++++- net/smc/smc_clc.h | 8 +++++++- 3 files changed, 16 insertions(+), 3 deletions(-) diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 6881fd03ef25..1ad7b05893af 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -2280,7 +2280,8 @@ static void smc_find_rdma_v2_device_serv(struct smc_sock *new_smc, goto not_found; smc_v2_ext = smc_get_clc_v2_ext(pclc); - if (!smc_clc_match_eid(ini->negotiated_eid, smc_v2_ext, NULL, NULL)) + if (!smc_v2_ext || + !smc_clc_match_eid(ini->negotiated_eid, smc_v2_ext, NULL, NULL)) goto not_found; /* prepare RDMA check */ diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index d96ad04e7dcf..3d0139250cc8 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -352,7 +352,6 @@ static bool smc_clc_msg_prop_valid(struct smc_clc_msg_proposal *pclc) struct smc_clc_msg_hdr *hdr = &pclc->hdr; struct smc_clc_v2_extension *v2_ext; - v2_ext = smc_get_clc_v2_ext(pclc); pclc_prfx = smc_clc_proposal_get_prefix(pclc); if (hdr->version == SMC_V1) { if (hdr->typev1 == SMC_TYPE_N) @@ -365,6 +364,13 @@ static bool smc_clc_msg_prop_valid(struct smc_clc_msg_proposal *pclc) sizeof(struct smc_clc_msg_trail)) return false; } else { + v2_ext = smc_get_clc_v2_ext(pclc); + if ((hdr->typev2 != SMC_TYPE_N && + (!v2_ext || v2_ext->hdr.eid_cnt > SMC_CLC_MAX_UEID)) || + (smcd_indicated(hdr->typev2) && + v2_ext->hdr.ism_gid_cnt > SMCD_CLC_MAX_V2_GID_ENTRIES)) + return false; + if (ntohs(hdr->length) != sizeof(*pclc) + sizeof(struct smc_clc_msg_smcd) + diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h index 58777b6a0dfe..0ddf0f5307a7 100644 --- a/net/smc/smc_clc.h +++ b/net/smc/smc_clc.h @@ -366,8 +366,14 @@ static inline struct smc_clc_v2_extension * smc_get_clc_v2_ext(struct smc_clc_msg_proposal *prop) { struct smc_clc_msg_smcd *prop_smcd = smc_get_clc_msg_smcd(prop); + u16 max_offset; - if (!prop_smcd || !ntohs(prop_smcd->v2_ext_offset)) + max_offset = offsetof(struct smc_clc_msg_proposal_area, pclc_v2_ext) - + offsetof(struct smc_clc_msg_proposal_area, pclc_smcd) - + offsetofend(struct smc_clc_msg_smcd, v2_ext_offset); + + if (!prop_smcd || !ntohs(prop_smcd->v2_ext_offset) || + ntohs(prop_smcd->v2_ext_offset) > max_offset) return NULL; return (struct smc_clc_v2_extension *) -- 2.25.1

2 1