May 2024 - Kernel - mailweb.openeuler.org

[PATCH OLK-5.10] ima: fix deadlock when traversing "ima_default_rules".
by GUO Zihua 07 May '24

07 May '24

From: liqiong <liqiong(a)nfschina.com> mainline inclusion from mainline-v5.16-rc1 commit eb0782bbdfd0d7c4786216659277c3fd585afc0e category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I9AAM6 CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- The current IMA ruleset is identified by the variable "ima_rules" that default to "&ima_default_rules". When loading a custom policy for the first time, the variable is updated to "&ima_policy_rules" instead. That update isn't RCU-safe, and deadlocks are possible. Indeed, some functions like ima_match_policy() may loop indefinitely when traversing "ima_default_rules" with list_for_each_entry_rcu(). When iterating over the default ruleset back to head, if the list head is "ima_default_rules", and "ima_rules" have been updated to "&ima_policy_rules", the loop condition (&entry->list != ima_rules) stays always true, traversing won't terminate, causing a soft lockup and RCU stalls. Introduce a temporary value for "ima_rules" when iterating over the ruleset to avoid the deadlocks. Signed-off-by: liqiong <liqiong(a)nfschina.com> Reviewed-by: THOBY Simon <Simon.THOBY(a)viveris.fr> Fixes: 38d859f991f3 ("IMA: policy can now be updated multiple times") Reported-by: kernel test robot <lkp(a)intel.com> (Fix sparse: incompatible types in comparison expression.) Signed-off-by: Mimi Zohar <zohar(a)linux.ibm.com> Conflicts: security/integrity/ima/ima_policy.c [Context conflicts. Besides an additional pair of rcu_read_lock and unlock has been added to ima_update_policy_flag to mitigate a suspicious RCU usage warning. This pair of RCU lock was added with commit 4f2946aa0c45 ("IMA: introduce a new policy option func=SETXATTR_CHECK") on mainstream.] Signed-off-by: GUO Zihua <guozihua(a)huawei.com> --- security/integrity/ima/ima_policy.c | 29 ++++++++++++++++++++--------- 1 file changed, 20 insertions(+), 9 deletions(-) diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c index fa1543cdca70..43a5c4754a66 100644 --- a/security/integrity/ima/ima_policy.c +++ b/security/integrity/ima/ima_policy.c @@ -245,7 +245,7 @@ static struct ima_rule_entry *arch_policy_entry __ro_after_init; static LIST_HEAD(ima_default_rules); static LIST_HEAD(ima_policy_rules); static LIST_HEAD(ima_temp_rules); -static struct list_head *ima_rules = &ima_default_rules; +static struct list_head __rcu *ima_rules = (struct list_head __rcu *)(&ima_default_rules); static int ima_policy __initdata; @@ -702,12 +702,14 @@ int ima_match_policy(struct inode *inode, const struct cred *cred, u32 secid, { struct ima_rule_entry *entry; int action = 0, actmask = flags | (flags << 1); + struct list_head *ima_rules_tmp; if (template_desc) *template_desc = ima_template_desc_current(); rcu_read_lock(); - list_for_each_entry_rcu(entry, ima_rules, list) { + ima_rules_tmp = rcu_dereference(ima_rules); + list_for_each_entry_rcu(entry, ima_rules_tmp, list) { if (!(entry->action & actmask)) continue; @@ -755,11 +757,15 @@ int ima_match_policy(struct inode *inode, const struct cred *cred, u32 secid, void ima_update_policy_flag(void) { struct ima_rule_entry *entry; + struct list_head *ima_rules_tmp; - list_for_each_entry(entry, ima_rules, list) { + rcu_read_lock(); + ima_rules_tmp = rcu_dereference(ima_rules); + list_for_each_entry_rcu(entry, ima_rules_tmp, list) { if (entry->action & IMA_DO_MASK) ima_policy_flag |= entry->action; } + rcu_read_unlock(); ima_appraise |= (build_ima_appraise | temp_ima_appraise); if (!ima_appraise) @@ -1019,10 +1025,10 @@ void ima_update_policy(void) list_splice_tail_init_rcu(&ima_temp_rules, policy, synchronize_rcu); - if (ima_rules != policy) { + if (ima_rules != (struct list_head __rcu *)policy) { ima_policy_flag = 0; - ima_rules = policy; + rcu_assign_pointer(ima_rules, policy); /* * IMA architecture specific policy rules are specified * as strings and converted to an array of ima_entry_rules @@ -1117,7 +1123,7 @@ static int ima_lsm_rule_init(struct ima_rule_entry *entry, pr_warn("rule for LSM \'%s\' is undefined\n", entry->lsm[lsm_rule].args_p); - if (ima_rules == &ima_default_rules) { + if (ima_rules == (struct list_head __rcu *)(&ima_default_rules)) { kfree(entry->lsm[lsm_rule].args_p); entry->lsm[lsm_rule].args_p = NULL; result = -EINVAL; @@ -1764,9 +1770,11 @@ void *ima_policy_start(struct seq_file *m, loff_t *pos) { loff_t l = *pos; struct ima_rule_entry *entry; + struct list_head *ima_rules_tmp; rcu_read_lock(); - list_for_each_entry_rcu(entry, ima_rules, list) { + ima_rules_tmp = rcu_dereference(ima_rules); + list_for_each_entry_rcu(entry, ima_rules_tmp, list) { if (!l--) { rcu_read_unlock(); return entry; @@ -1785,7 +1793,8 @@ void *ima_policy_next(struct seq_file *m, void *v, loff_t *pos) rcu_read_unlock(); (*pos)++; - return (&entry->list == ima_rules) ? NULL : entry; + return (&entry->list == &ima_default_rules || + &entry->list == &ima_policy_rules) ? NULL : entry; } void ima_policy_stop(struct seq_file *m, void *v) @@ -1998,6 +2007,7 @@ bool ima_appraise_signature(enum kernel_read_file_id id) struct ima_rule_entry *entry; bool found = false; enum ima_hooks func; + struct list_head *ima_rules_tmp; if (id >= READING_MAX_ID) return false; @@ -2009,7 +2019,8 @@ bool ima_appraise_signature(enum kernel_read_file_id id) func = read_idmap[id] ?: FILE_CHECK; rcu_read_lock(); - list_for_each_entry_rcu(entry, ima_rules, list) { + ima_rules_tmp = rcu_dereference(ima_rules); + list_for_each_entry_rcu(entry, ima_rules_tmp, list) { if (entry->action != APPRAISE) continue; -- 2.34.1

2 1

[PATCH openEuler-1.0-LTS 0/1] cpufreq: brcmstb-avs-cpufreq: add check for cpufreq_cpu_get's return value
by Liao Chen 07 May '24

07 May '24

fix CVE-2024-27051 Anastasia Belova (1): cpufreq: brcmstb-avs-cpufreq: add check for cpufreq_cpu_get's return value drivers/cpufreq/brcmstb-avs-cpufreq.c | 2 ++ 1 file changed, 2 insertions(+) -- 2.34.1

2 2

[PATCH openEuler-1.0-LTS] mm/mmu_gather: limit free batch count and add schedule point in tlb_batch_pages_flush
by Jinjiang Tu 07 May '24

07 May '24

From: Jianxing Wang <wangjianxing(a)loongson.cn> mainline inclusion from mainline-v5.19-rc1 commit b191c9bc334a936775843867485c207e23b30e1b category: bugfix bugzilla: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- free a large list of pages maybe cause rcu_sched starved on non-preemptible kernels. howerver free_unref_page_list maybe can't cond_resched as it maybe called in interrupt or atomic context, especially can't detect atomic context in CONFIG_PREEMPTION=n. The issue is detected in guest with kvm cpu 200% overcommit, however I didn't see the warning in the host with the same application. I'm sure that the patch is needed for guest kernel, but no sure for host. To reproduce, set up two virtual machines in one host machine, per vm has the same number cpu and half memory of host. the run ltpstress.sh in per vm, then will see rcu stall warning.kernel is preempt disabled, append kernel command 'preempt=none' if enable dynamic preempt . It could detected in loongson machine(32 core, 128G mem) and ProLiant DL380 Gen9(x86 E5-2680, 28 core, 64G mem) tlb flush batch count depends on PAGE_SIZE, it's too large if PAGE_SIZE > 4K, here limit free batch count with 512. And add schedule point in tlb_batch_pages_flush. rcu: rcu_sched kthread starved for 5359 jiffies! g454793 f0x0 RCU_GP_WAIT_FQS(5) ->state=0x0 ->cpu=19 [...] Call Trace: free_unref_page_list+0x19c/0x270 release_pages+0x3cc/0x498 tlb_flush_mmu_free+0x44/0x70 zap_pte_range+0x450/0x738 unmap_page_range+0x108/0x240 unmap_vmas+0x74/0xf0 unmap_region+0xb0/0x120 do_munmap+0x264/0x438 vm_munmap+0x58/0xa0 sys_munmap+0x10/0x20 syscall_common+0x24/0x38 Link: https://lkml.kernel.org/r/20220317072857.2635262-1-wangjianxing@loongson.cn Signed-off-by: Jianxing Wang <wangjianxing(a)loongson.cn> Signed-off-by: Peter Zijlstra <peterz(a)infradead.org> Cc: Will Deacon <will(a)kernel.org> Cc: Nicholas Piggin <npiggin(a)gmail.com> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Conflicts: mm/mmu_gather [Context conflicts] Signed-off-by: Jinjiang Tu <tujinjiang(a)huawei.com> --- mm/mmu_gather.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c index a44cf211ffee..2b3f6967176f 100644 --- a/mm/mmu_gather.c +++ b/mm/mmu_gather.c @@ -71,8 +71,20 @@ void tlb_flush_mmu_free(struct mmu_gather *tlb) tlb_table_flush(tlb); #endif for (batch = &tlb->local; batch && batch->nr; batch = batch->next) { - free_pages_and_swap_cache(batch->pages, batch->nr); - batch->nr = 0; + struct page **pages = batch->pages; + + do { + /* + * limit free batch count when PAGE_SIZE > 4K + */ + unsigned int nr = min(512U, batch->nr); + + free_pages_and_swap_cache(pages, nr); + pages += nr; + batch->nr -= nr; + + cond_resched(); + } while (batch->nr); } tlb->active = &tlb->local; } -- 2.25.1

2 1

[PATCH openEuler-1.0-LTS] ima: fix deadlock when traversing "ima_default_rules".
by GUO Zihua 07 May '24

07 May '24

From: liqiong <liqiong(a)nfschina.com> mainline inclusion from mainline-v5.16-rc1 commit eb0782bbdfd0d7c4786216659277c3fd585afc0e category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I9AAM6 CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- The current IMA ruleset is identified by the variable "ima_rules" that default to "&ima_default_rules". When loading a custom policy for the first time, the variable is updated to "&ima_policy_rules" instead. That update isn't RCU-safe, and deadlocks are possible. Indeed, some functions like ima_match_policy() may loop indefinitely when traversing "ima_default_rules" with list_for_each_entry_rcu(). When iterating over the default ruleset back to head, if the list head is "ima_default_rules", and "ima_rules" have been updated to "&ima_policy_rules", the loop condition (&entry->list != ima_rules) stays always true, traversing won't terminate, causing a soft lockup and RCU stalls. Introduce a temporary value for "ima_rules" when iterating over the ruleset to avoid the deadlocks. Signed-off-by: liqiong <liqiong(a)nfschina.com> Reviewed-by: THOBY Simon <Simon.THOBY(a)viveris.fr> Fixes: 38d859f991f3 ("IMA: policy can now be updated multiple times") Reported-by: kernel test robot <lkp(a)intel.com> (Fix sparse: incompatible types in comparison expression.) Signed-off-by: Mimi Zohar <zohar(a)linux.ibm.com> Conflicts: security/integrity/ima/ima_policy.c [Context conflicts. Besides an additional pair of rcu_read_lock and unlock has been added to ima_update_policy_flag to mitigate a suspicious RCU usage warning. This pair of RCU lock was added with commit 4f2946aa0c45 ("IMA: introduce a new policy option func=SETXATTR_CHECK") on mainstream.] Signed-off-by: GUO Zihua <guozihua(a)huawei.com> --- security/integrity/ima/ima_policy.c | 25 +++++++++++++++++-------- 1 file changed, 17 insertions(+), 8 deletions(-) diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c index 08eae4df759e..3098894ea026 100644 --- a/security/integrity/ima/ima_policy.c +++ b/security/integrity/ima/ima_policy.c @@ -196,7 +196,7 @@ static struct ima_rule_entry secure_boot_rules[] __ro_after_init = { static LIST_HEAD(ima_default_rules); static LIST_HEAD(ima_policy_rules); static LIST_HEAD(ima_temp_rules); -static struct list_head *ima_rules = &ima_default_rules; +static struct list_head __rcu *ima_rules = (struct list_head __rcu *)(&ima_default_rules); static int ima_policy __initdata; @@ -515,9 +515,11 @@ int ima_match_policy(struct inode *inode, const struct cred *cred, u32 secid, { struct ima_rule_entry *entry; int action = 0, actmask = flags | (flags << 1); + struct list_head *ima_rules_tmp; rcu_read_lock(); - list_for_each_entry_rcu(entry, ima_rules, list) { + ima_rules_tmp = rcu_dereference(ima_rules); + list_for_each_entry_rcu(entry, ima_rules_tmp, list) { if (!(entry->action & actmask)) continue; @@ -560,11 +562,15 @@ int ima_match_policy(struct inode *inode, const struct cred *cred, u32 secid, void ima_update_policy_flag(void) { struct ima_rule_entry *entry; + struct list_head *ima_rules_tmp; - list_for_each_entry(entry, ima_rules, list) { + rcu_read_lock(); + ima_rules_tmp = rcu_dereference(ima_rules); + list_for_each_entry_rcu(entry, ima_rules_tmp, list) { if (entry->action & IMA_DO_MASK) ima_policy_flag |= entry->action; } + rcu_read_unlock(); ima_appraise |= (build_ima_appraise | temp_ima_appraise); if (!ima_appraise) @@ -683,9 +689,9 @@ void ima_update_policy(void) list_splice_tail_init_rcu(&ima_temp_rules, policy, synchronize_rcu); - if (ima_rules != policy) { + if (ima_rules != (struct list_head __rcu *)policy) { ima_policy_flag = 0; - ima_rules = policy; + rcu_assign_pointer(ima_rules, policy); } ima_update_policy_flag(); } @@ -760,7 +766,7 @@ static int ima_lsm_rule_init(struct ima_rule_entry *entry, pr_warn("rule for LSM \'%s\' is undefined\n", (char *)entry->lsm[lsm_rule].args_p); - if (ima_rules == &ima_default_rules) { + if (ima_rules == (struct list_head __rcu *)(&ima_default_rules)) { kfree(entry->lsm[lsm_rule].args_p); entry->lsm[lsm_rule].args_p = NULL; result = -EINVAL; @@ -1188,9 +1194,11 @@ void *ima_policy_start(struct seq_file *m, loff_t *pos) { loff_t l = *pos; struct ima_rule_entry *entry; + struct list_head *ima_rules_tmp; rcu_read_lock(); - list_for_each_entry_rcu(entry, ima_rules, list) { + ima_rules_tmp = rcu_dereference(ima_rules); + list_for_each_entry_rcu(entry, ima_rules_tmp, list) { if (!l--) { rcu_read_unlock(); return entry; @@ -1209,7 +1217,8 @@ void *ima_policy_next(struct seq_file *m, void *v, loff_t *pos) rcu_read_unlock(); (*pos)++; - return (&entry->list == ima_rules) ? NULL : entry; + return (&entry->list == &ima_default_rules || + &entry->list == &ima_policy_rules) ? NULL : entry; } void ima_policy_stop(struct seq_file *m, void *v) -- 2.34.1

2 1

[PATCH v2 openEuler-1.0-LTS 0/2] Fix CVE-2022-48693
by Li Huafei 07 May '24

07 May '24

Liang He (1): soc: brcmstb: pm-arm: Fix refcount leak and __iomem leak bugs Miaoqian Lin (1): soc: bcm: brcmstb: pm: pm-arm: Fix refcount leak in brcmstb_pm_probe drivers/soc/bcm/brcmstb/pm/pm-arm.c | 51 ++++++++++++++++++++++------- 1 file changed, 40 insertions(+), 11 deletions(-) -- 2.25.1

2 3

[PATCH openEuler-1.0-LTS] Bluetooth: Fix TOCTOU in HCI debugfs implementation
by Wang Hai 07 May '24

07 May '24

From: Bastien Nocera <hadess(a)hadess.net> mainline inclusion from mainline-v6.9-rc3 commit 7835fcfd132eb88b87e8eb901f88436f63ab60f7 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I917NR CVE: CVE-2024-24858 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- struct hci_dev members conn_info_max_age, conn_info_min_age, le_conn_max_interval, le_conn_min_interval, le_adv_max_interval, and le_adv_min_interval can be modified from the HCI core code, as well through debugfs. The debugfs implementation, that's only available to privileged users, will check for boundaries, making sure that the minimum value being set is strictly above the maximum value that already exists, and vice-versa. However, as both minimum and maximum values can be changed concurrently to us modifying them, we need to make sure that the value we check is the value we end up using. For example, with ->conn_info_max_age set to 10, conn_info_min_age_set() gets called from vfs handlers to set conn_info_min_age to 8. In conn_info_min_age_set(), this goes through: if (val == 0 || val > hdev->conn_info_max_age) return -EINVAL; Concurrently, conn_info_max_age_set() gets called to set to set the conn_info_max_age to 7: if (val == 0 || val > hdev->conn_info_max_age) return -EINVAL; That check will also pass because we used the old value (10) for conn_info_max_age. After those checks that both passed, the struct hci_dev access is mutex-locked, disabling concurrent access, but that does not matter because the invalid value checks both passed, and we'll end up with conn_info_min_age = 8 and conn_info_max_age = 7 To fix this problem, we need to lock the structure access before so the check and assignment are not interrupted. This fix was originally devised by the BassCheck[1] team, and considered the problem to be an atomicity one. This isn't the case as there aren't any concerns about the variable changing while we check it, but rather after we check it parallel to another change. This patch fixes CVE-2024-24858 and CVE-2024-24857. [1] https://sites.google.com/view/basscheck/ Co-developed-by: Gui-Dong Han <2045gemini(a)gmail.com> Signed-off-by: Gui-Dong Han <2045gemini(a)gmail.com> Link: https://lore.kernel.org/linux-bluetooth/20231222161317.6255-1-2045gemini@gm… Link: https://nvd.nist.gov/vuln/detail/CVE-2024-24858 Link: https://lore.kernel.org/linux-bluetooth/20231222162931.6553-1-2045gemini@gm… Link: https://lore.kernel.org/linux-bluetooth/20231222162310.6461-1-2045gemini@gm… Link: https://nvd.nist.gov/vuln/detail/CVE-2024-24857 Fixes: 31ad169148df ("Bluetooth: Add conn info lifetime parameters to debugfs") Fixes: 729a1051da6f ("Bluetooth: Expose default LE advertising interval via debugfs") Fixes: 71c3b60ec6d2 ("Bluetooth: Move BR/EDR debugfs file creation into hci_debugfs.c") Signed-off-by: Bastien Nocera <hadess(a)hadess.net> Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz(a)intel.com> Signed-off-by: Wang Hai <wanghai38(a)huawei.com> --- net/bluetooth/hci_debugfs.c | 48 ++++++++++++++++++++++++------------- 1 file changed, 32 insertions(+), 16 deletions(-) diff --git a/net/bluetooth/hci_debugfs.c b/net/bluetooth/hci_debugfs.c index 18683a76cf25..150edcb1da09 100644 --- a/net/bluetooth/hci_debugfs.c +++ b/net/bluetooth/hci_debugfs.c @@ -201,10 +201,12 @@ static int conn_info_min_age_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val == 0 || val > hdev->conn_info_max_age) + hci_dev_lock(hdev); + if (val == 0 || val > hdev->conn_info_max_age) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->conn_info_min_age = val; hci_dev_unlock(hdev); @@ -229,10 +231,12 @@ static int conn_info_max_age_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val == 0 || val < hdev->conn_info_min_age) + hci_dev_lock(hdev); + if (val == 0 || val < hdev->conn_info_min_age) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->conn_info_max_age = val; hci_dev_unlock(hdev); @@ -480,10 +484,12 @@ static int sniff_min_interval_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val == 0 || val % 2 || val > hdev->sniff_max_interval) + hci_dev_lock(hdev); + if (val == 0 || val % 2 || val > hdev->sniff_max_interval) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->sniff_min_interval = val; hci_dev_unlock(hdev); @@ -508,10 +514,12 @@ static int sniff_max_interval_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val == 0 || val % 2 || val < hdev->sniff_min_interval) + hci_dev_lock(hdev); + if (val == 0 || val % 2 || val < hdev->sniff_min_interval) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->sniff_max_interval = val; hci_dev_unlock(hdev); @@ -750,10 +758,12 @@ static int conn_min_interval_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val < 0x0006 || val > 0x0c80 || val > hdev->le_conn_max_interval) + hci_dev_lock(hdev); + if (val < 0x0006 || val > 0x0c80 || val > hdev->le_conn_max_interval) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->le_conn_min_interval = val; hci_dev_unlock(hdev); @@ -778,10 +788,12 @@ static int conn_max_interval_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val < 0x0006 || val > 0x0c80 || val < hdev->le_conn_min_interval) + hci_dev_lock(hdev); + if (val < 0x0006 || val > 0x0c80 || val < hdev->le_conn_min_interval) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->le_conn_max_interval = val; hci_dev_unlock(hdev); @@ -890,10 +902,12 @@ static int adv_min_interval_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val < 0x0020 || val > 0x4000 || val > hdev->le_adv_max_interval) + hci_dev_lock(hdev); + if (val < 0x0020 || val > 0x4000 || val > hdev->le_adv_max_interval) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->le_adv_min_interval = val; hci_dev_unlock(hdev); @@ -918,10 +932,12 @@ static int adv_max_interval_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val < 0x0020 || val > 0x4000 || val < hdev->le_adv_min_interval) + hci_dev_lock(hdev); + if (val < 0x0020 || val > 0x4000 || val < hdev->le_adv_min_interval) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->le_adv_max_interval = val; hci_dev_unlock(hdev); -- 2.17.1

2 1

[PATCH OLK-5.10] f2fs: compress: fix to guarantee persisting compressed blocks by CP
by Zizhi Wo 07 May '24

07 May '24

From: Chao Yu <chao(a)kernel.org> stable inclusion from stable-v6.1.83 commit e54cce8137258a550b49cae45d09e024821fb28d category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I9L9OE CVE: CVE-2024-27035 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 8a430dd49e9cb021372b0ad91e60aeef9c6ced00 ] If data block in compressed cluster is not persisted with metadata during checkpoint, after SPOR, the data may be corrupted, let's guarantee to write compressed page by checkpoint. Fixes: 4c8ff7095bef ("f2fs: support data compression") Reviewed-by: Daeho Jeong <daehojeong(a)google.com> Signed-off-by: Chao Yu <chao(a)kernel.org> Signed-off-by: Jaegeuk Kim <jaegeuk(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Conflicts: fs/f2fs/data.c fs/f2fs/f2fs.h [Due to the large number of patch modifications and conflicts, patch adaptation is performed in the original contexts, related to f2fs compression] Signed-off-by: Zizhi Wo <wozizhi(a)huawei.com> --- fs/f2fs/compress.c | 4 +++- fs/f2fs/data.c | 18 +++++++++--------- fs/f2fs/f2fs.h | 4 +++- 3 files changed, 15 insertions(+), 11 deletions(-) diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c index a94e102d1586..c99f1cc5c449 100644 --- a/fs/f2fs/compress.c +++ b/fs/f2fs/compress.c @@ -1333,6 +1333,8 @@ void f2fs_compress_write_end_io(struct bio *bio, struct page *page) struct f2fs_sb_info *sbi = bio->bi_private; struct compress_io_ctx *cic = (struct compress_io_ctx *)page_private(page); + enum count_type type = WB_DATA_TYPE(page, + f2fs_is_compressed_page(page)); int i; if (unlikely(bio->bi_status)) @@ -1340,7 +1342,7 @@ void f2fs_compress_write_end_io(struct bio *bio, struct page *page) f2fs_compress_free_page(page); - dec_page_count(sbi, F2FS_WB_DATA); + dec_page_count(sbi, type); if (atomic_dec_return(&cic->pending_pages)) return; diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 28beb7d7c7e1..c0c30a32fd59 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -71,7 +71,7 @@ struct bio *f2fs_bio_alloc(struct f2fs_sb_info *sbi, int npages, bool noio) return __f2fs_bio_alloc(GFP_KERNEL, npages); } -static bool __is_cp_guaranteed(struct page *page) +bool f2fs_is_cp_guaranteed(struct page *page) { struct address_space *mapping = page->mapping; struct inode *inode; @@ -80,9 +80,6 @@ static bool __is_cp_guaranteed(struct page *page) if (!mapping) return false; - if (f2fs_is_compressed_page(page)) - return false; - inode = mapping->host; sbi = F2FS_I_SB(inode); @@ -347,7 +344,7 @@ static void f2fs_write_end_io(struct bio *bio) bio_for_each_segment_all(bvec, bio, iter_all) { struct page *page = bvec->bv_page; - enum count_type type = WB_DATA_TYPE(page); + enum count_type type = WB_DATA_TYPE(page, false); if (IS_DUMMY_WRITTEN_PAGE(page)) { set_page_private(page, (unsigned long)NULL); @@ -727,7 +724,7 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio) bio_set_op_attrs(bio, fio->op, fio->op_flags); inc_page_count(fio->sbi, is_read_io(fio->op) ? - __read_io_type(page): WB_DATA_TYPE(fio->page)); + __read_io_type(page) : WB_DATA_TYPE(fio->page, false)); __submit_bio(fio->sbi, bio, fio->type); return 0; @@ -933,7 +930,7 @@ int f2fs_merge_page_bio(struct f2fs_io_info *fio) if (fio->io_wbc) wbc_account_cgroup_owner(fio->io_wbc, fio->page, PAGE_SIZE); - inc_page_count(fio->sbi, WB_DATA_TYPE(page)); + inc_page_count(fio->sbi, WB_DATA_TYPE(page, false)); *fio->last_block = fio->new_blkaddr; *fio->bio = bio; @@ -947,6 +944,7 @@ void f2fs_submit_page_write(struct f2fs_io_info *fio) enum page_type btype = PAGE_TYPE_OF_BIO(fio->type); struct f2fs_bio_info *io = sbi->write_io[btype] + fio->temp; struct page *bio_page; + enum count_type type; f2fs_bug_on(sbi, is_read_io(fio->op)); @@ -976,7 +974,8 @@ void f2fs_submit_page_write(struct f2fs_io_info *fio) /* set submitted = true as a return value */ fio->submitted = true; - inc_page_count(sbi, WB_DATA_TYPE(bio_page)); + type = WB_DATA_TYPE(bio_page, fio->compressed_page); + inc_page_count(sbi, type); if (io->bio && (!io_is_mergeable(sbi, io->bio, io, fio, io->last_block_in_bio, @@ -989,7 +988,8 @@ void f2fs_submit_page_write(struct f2fs_io_info *fio) if (F2FS_IO_ALIGNED(sbi) && (fio->type == DATA || fio->type == NODE) && fio->new_blkaddr & F2FS_IO_SIZE_MASK(sbi)) { - dec_page_count(sbi, WB_DATA_TYPE(bio_page)); + dec_page_count(sbi, WB_DATA_TYPE(bio_page, + fio->compressed_page)); fio->retry = true; goto skip; } diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index a174736931d1..154d6fa2f4c0 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -994,7 +994,8 @@ struct f2fs_sm_info { * f2fs monitors the number of several block types such as on-writeback, * dirty dentry blocks, dirty node blocks, and dirty meta blocks. */ -#define WB_DATA_TYPE(p) (__is_cp_guaranteed(p) ? F2FS_WB_CP_DATA : F2FS_WB_DATA) +#define WB_DATA_TYPE(p, f) \ + (f || f2fs_is_cp_guaranteed(p) ? F2FS_WB_CP_DATA : F2FS_WB_DATA) enum count_type { F2FS_DIRTY_DENTS, F2FS_DIRTY_DATA, @@ -3415,6 +3416,7 @@ void f2fs_destroy_checkpoint_caches(void); */ int __init f2fs_init_bioset(void); void f2fs_destroy_bioset(void); +bool f2fs_is_cp_guaranteed(struct page *page); struct bio *f2fs_bio_alloc(struct f2fs_sb_info *sbi, int npages, bool noio); int f2fs_init_bio_entry_cache(void); void f2fs_destroy_bio_entry_cache(void); -- 2.39.2

2 1

[PATCH openEuler-1.0-LTS v4 0/2] CVE-2024-26846
by Li Lingfeng 07 May '24

07 May '24

v1->v2: Apply patch to remove nvme_fc_wq. v2->v3: Correct commit id. v3->v4: Adjust the format of conflict information according to the new requirements. Daniel Wagner (1): nvme-fc: do not wait in vain when unloading module James Smart (1): nvme-fc: remove err_work work item drivers/nvme/host/fc.c | 87 ++++++++---------------------------------- 1 file changed, 16 insertions(+), 71 deletions(-) -- 2.31.1

2 3

[PATCH openEuler-1.0-LTS] media: go7007: fix a memleak in go7007_load_encoder
by Guo Mengqi 07 May '24

07 May '24

From: Zhipeng Lu <alexious(a)zju.edu.cn> stable inclusion from stable-v4.19.311 commit 7f11dd3d165b178e738fe73dfeea513e383bedb5 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I9L9IB CVE: CVE-2024-27074 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit b9b683844b01d171a72b9c0419a2d760d946ee12 ] In go7007_load_encoder, bounce(i.e. go->boot_fw), is allocated without a deallocation thereafter. After the following call chain: saa7134_go7007_init |-> go7007_boot_encoder |-> go7007_load_encoder |-> kfree(go) go is freed and thus bounce is leaked. Fixes: 95ef39403f89 ("[media] go7007: remember boot firmware") Signed-off-by: Zhipeng Lu <alexious(a)zju.edu.cn> Signed-off-by: Hans Verkuil <hverkuil-cisco(a)xs4all.nl> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Guo Mengqi <guomengqi3(a)huawei.com> --- drivers/media/usb/go7007/go7007-driver.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/media/usb/go7007/go7007-driver.c b/drivers/media/usb/go7007/go7007-driver.c index 62aeebcdd7f7..89eb65624054 100644 --- a/drivers/media/usb/go7007/go7007-driver.c +++ b/drivers/media/usb/go7007/go7007-driver.c @@ -88,7 +88,7 @@ static int go7007_load_encoder(struct go7007 *go) const struct firmware *fw_entry; char fw_name[] = "go7007/go7007fw.bin"; void *bounce; - int fw_len, rv = 0; + int fw_len; u16 intr_val, intr_data; if (go->boot_fw == NULL) { @@ -117,9 +117,11 @@ static int go7007_load_encoder(struct go7007 *go) go7007_read_interrupt(go, &intr_val, &intr_data) < 0 || (intr_val & ~0x1) != 0x5a5a) { v4l2_err(go, "error transferring firmware\n"); - rv = -1; + kfree(go->boot_fw); + go->boot_fw = NULL; + return -1; } - return rv; + return 0; } MODULE_FIRMWARE("go7007/go7007fw.bin"); -- 2.17.1

2 1

[PATCH OLK-5.10] net/smc: Fix possible access to freed memory in link clear
by Zhengchao Shao 07 May '24

07 May '24

From: Yacan Liu <liuyacan(a)corp.netease.com> mainline inclusion from mainline-v6.0-rc5 commit e9b1a4f867ae9c1dbd1d71cd09cbdb3239fb4968 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I9LK4T CVE: CVE-2022-48673 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- After modifying the QP to the Error state, all RX WR would be completed with WC in IB_WC_WR_FLUSH_ERR status. Current implementation does not wait for it is done, but destroy the QP and free the link group directly. So there is a risk that accessing the freed memory in tasklet context. Here is a crash example: BUG: unable to handle page fault for address: ffffffff8f220860 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page PGD f7300e067 P4D f7300e067 PUD f7300f063 PMD 8c4e45063 PTE 800ffff08c9df060 Oops: 0002 [#1] SMP PTI CPU: 1 PID: 0 Comm: swapper/1 Kdump: loaded Tainted: G S OE 5.10.0-0607+ #23 Hardware name: Inspur NF5280M4/YZMB-00689-101, BIOS 4.1.20 07/09/2018 RIP: 0010:native_queued_spin_lock_slowpath+0x176/0x1b0 Code: f3 90 48 8b 32 48 85 f6 74 f6 eb d5 c1 ee 12 83 e0 03 83 ee 01 48 c1 e0 05 48 63 f6 48 05 00 c8 02 00 48 03 04 f5 00 09 98 8e <48> 89 10 8b 42 08 85 c0 75 09 f3 90 8b 42 08 85 c0 74 f7 48 8b 32 RSP: 0018:ffffb3b6c001ebd8 EFLAGS: 00010086 RAX: ffffffff8f220860 RBX: 0000000000000246 RCX: 0000000000080000 RDX: ffff91db1f86c800 RSI: 000000000000173c RDI: ffff91db62bace00 RBP: ffff91db62bacc00 R08: 0000000000000000 R09: c00000010000028b R10: 0000000000055198 R11: ffffb3b6c001ea58 R12: ffff91db80e05010 R13: 000000000000000a R14: 0000000000000006 R15: 0000000000000040 FS: 0000000000000000(0000) GS:ffff91db1f840000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffffff8f220860 CR3: 00000001f9580004 CR4: 00000000003706e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <IRQ> _raw_spin_lock_irqsave+0x30/0x40 mlx5_ib_poll_cq+0x4c/0xc50 [mlx5_ib] smc_wr_rx_tasklet_fn+0x56/0xa0 [smc] tasklet_action_common.isra.21+0x66/0x100 __do_softirq+0xd5/0x29c asm_call_irq_on_stack+0x12/0x20 </IRQ> do_softirq_own_stack+0x37/0x40 irq_exit_rcu+0x9d/0xa0 sysvec_call_function_single+0x34/0x80 asm_sysvec_call_function_single+0x12/0x20 Fixes: bd4ad57718cc ("smc: initialize IB transport incl. PD, MR, QP, CQ, event, WR") Signed-off-by: Yacan Liu <liuyacan(a)corp.netease.com> Reviewed-by: Tony Lu <tonylu(a)linux.alibaba.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Conflicts: net/smc/smc_core.c net/smc/smc_core.h [This is a conflict caused by commit 61f434b0280e("net/smc: Resolve the race between link group access and termination") and 8799e310fb3f(" net/smc: add v2 support to the work request layer") those are not merged.] Signed-off-by: Zhengchao Shao <shaozhengchao(a)huawei.com> --- net/smc/smc_core.c | 1 + net/smc/smc_core.h | 2 ++ net/smc/smc_wr.c | 5 +++++ net/smc/smc_wr.h | 5 +++++ 4 files changed, 13 insertions(+) diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 2283cbf6b8ab..5312ca02a3e4 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -703,6 +703,7 @@ int smcr_link_init(struct smc_link_group *lgr, struct smc_link *lnk, lnk->lgr = lgr; smc_lgr_hold(lgr); /* lgr_put in smcr_link_clear() */ lnk->link_idx = link_idx; + lnk->wr_rx_id_compl = 0; lnk->smcibdev = ini->ib_dev; lnk->ibport = ini->ib_port; smc_ibdev_cnt_inc(lnk); diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index 739ead4360b0..16c286360d36 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -105,8 +105,10 @@ struct smc_link { /* above three vectors have wr_rx_cnt elements and use the same index */ dma_addr_t wr_rx_dma_addr; /* DMA address of wr_rx_bufs */ u64 wr_rx_id; /* seq # of last recv WR */ + u64 wr_rx_id_compl; /* seq # of last completed WR */ u32 wr_rx_cnt; /* number of WR recv buffers */ unsigned long wr_rx_tstamp; /* jiffies when last buf rx */ + wait_queue_head_t wr_rx_empty_wait; /* wait for RQ empty */ struct ib_reg_wr wr_reg; /* WR register memory region */ wait_queue_head_t wr_reg_wait; /* wait for wr_reg result */ diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c index d6a4d8b9d446..64c455abf861 100644 --- a/net/smc/smc_wr.c +++ b/net/smc/smc_wr.c @@ -388,6 +388,7 @@ static inline void smc_wr_rx_process_cqes(struct ib_wc wc[], int num) for (i = 0; i < num; i++) { link = wc[i].qp->qp_context; + link->wr_rx_id_compl = wc[i].wr_id; if (wc[i].status == IB_WC_SUCCESS) { link->wr_rx_tstamp = jiffies; smc_wr_rx_demultiplex(&wc[i]); @@ -399,6 +400,8 @@ static inline void smc_wr_rx_process_cqes(struct ib_wc wc[], int num) case IB_WC_RNR_RETRY_EXC_ERR: case IB_WC_WR_FLUSH_ERR: smcr_link_down_cond_sched(link); + if (link->wr_rx_id_compl == link->wr_rx_id) + wake_up(&link->wr_rx_empty_wait); break; default: smc_wr_rx_post(link); /* refill WR RX */ @@ -542,6 +545,7 @@ void smc_wr_free_link(struct smc_link *lnk) return; ibdev = lnk->smcibdev->ibdev; + smc_wr_drain_cq(lnk); smc_wr_wakeup_reg_wait(lnk); smc_wr_wakeup_tx_wait(lnk); @@ -711,6 +715,7 @@ int smc_wr_create_link(struct smc_link *lnk) atomic_set(&lnk->wr_tx_refcnt, 0); init_waitqueue_head(&lnk->wr_reg_wait); atomic_set(&lnk->wr_reg_refcnt, 0); + init_waitqueue_head(&lnk->wr_rx_empty_wait); return rc; dma_unmap: diff --git a/net/smc/smc_wr.h b/net/smc/smc_wr.h index cb58e60078f5..4fbd0ef26f00 100644 --- a/net/smc/smc_wr.h +++ b/net/smc/smc_wr.h @@ -73,6 +73,11 @@ static inline void smc_wr_tx_link_put(struct smc_link *link) wake_up_all(&link->wr_tx_wait); } +static inline void smc_wr_drain_cq(struct smc_link *lnk) +{ + wait_event(lnk->wr_rx_empty_wait, lnk->wr_rx_id_compl == lnk->wr_rx_id); +} + static inline void smc_wr_wakeup_tx_wait(struct smc_link *lnk) { wake_up_all(&lnk->wr_tx_wait); -- 2.34.1

2 1