January 2024 - Kernel - mailweb.openeuler.org

[PATCH OLK-5.10] smb: client: fix OOB in receive_encrypted_standard()
by ZhaoLong Wang 17 Jan '24

17 Jan '24

From: Paulo Alcantara <pc(a)manguebit.com> mainline inclusion from mainline-v6.7-rc6 commit eec04ea119691e65227a97ce53c0da6b9b74b0b7 category: bugfix bugzilla: 189472 CVE: CVE-2024-0565 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Fix potential OOB in receive_encrypted_standard() if server returned a large shdr->NextCommand that would end up writing off the end of @next_buffer. Fixes: b24df3e30cbf ("cifs: update receive_encrypted_standard to handle compounded responses") Cc: stable(a)vger.kernel.org Reported-by: Robert Morris <rtm(a)csail.mit.edu> Signed-off-by: Paulo Alcantara (SUSE) <pc(a)manguebit.com> Signed-off-by: Steve French <stfrench(a)microsoft.com> Conflicts: fs/cifs/smb2ops.c Signed-off-by: ZhaoLong Wang <wangzhaolong1(a)huawei.com> --- fs/cifs/smb2ops.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index b86f559751fd..caee4dedd7dc 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -4886,6 +4886,7 @@ receive_encrypted_standard(struct TCP_Server_Info *server, struct smb2_sync_hdr *shdr; unsigned int pdu_length = server->pdu_size; unsigned int buf_size; + unsigned int next_cmd; struct mid_q_entry *mid_entry; int next_is_large; char *next_buffer = NULL; @@ -4914,14 +4915,15 @@ receive_encrypted_standard(struct TCP_Server_Info *server, next_is_large = server->large_buf; one_more: shdr = (struct smb2_sync_hdr *)buf; - if (shdr->NextCommand) { + next_cmd = le32_to_cpu(shdr->NextCommand); + if (next_cmd) { + if (WARN_ON_ONCE(next_cmd > pdu_length)) + return -1; if (next_is_large) next_buffer = (char *)cifs_buf_get(); else next_buffer = (char *)cifs_small_buf_get(); - memcpy(next_buffer, - buf + le32_to_cpu(shdr->NextCommand), - pdu_length - le32_to_cpu(shdr->NextCommand)); + memcpy(next_buffer, buf + next_cmd, pdu_length - next_cmd); } mid_entry = smb2_find_mid(server, buf); @@ -4945,8 +4947,8 @@ receive_encrypted_standard(struct TCP_Server_Info *server, else ret = cifs_handle_standard(server, mid_entry); - if (ret == 0 && shdr->NextCommand) { - pdu_length -= le32_to_cpu(shdr->NextCommand); + if (ret == 0 && next_cmd) { + pdu_length -= next_cmd; server->large_buf = next_is_large; if (next_is_large) server->bigbuf = buf = next_buffer; -- 2.34.3

2 1

[PATCH openEuler-1.0-LTS] smb: client: fix OOB in receive_encrypted_standard()
by ZhaoLong Wang 17 Jan '24

17 Jan '24

From: Paulo Alcantara <pc(a)manguebit.com> mainline inclusion from mainline-v6.7-rc6 commit eec04ea119691e65227a97ce53c0da6b9b74b0b7 category: bugfix bugzilla: 189472 CVE: CVE-2024-0565 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Fix potential OOB in receive_encrypted_standard() if server returned a large shdr->NextCommand that would end up writing off the end of @next_buffer. Fixes: b24df3e30cbf ("cifs: update receive_encrypted_standard to handle compounded responses") Cc: stable(a)vger.kernel.org Reported-by: Robert Morris <rtm(a)csail.mit.edu> Signed-off-by: Paulo Alcantara (SUSE) <pc(a)manguebit.com> Signed-off-by: Steve French <stfrench(a)microsoft.com> Conflicts: fs/cifs/smb2ops.c Signed-off-by: ZhaoLong Wang <wangzhaolong1(a)huawei.com> --- fs/cifs/smb2ops.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 4f6cc104fdb5..eba4bdfff08a 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -3185,6 +3185,7 @@ receive_encrypted_standard(struct TCP_Server_Info *server, struct smb2_sync_hdr *shdr; unsigned int pdu_length = server->pdu_size; unsigned int buf_size; + unsigned int next_cmd; struct mid_q_entry *mid_entry; int next_is_large; char *next_buffer = NULL; @@ -3213,14 +3214,15 @@ receive_encrypted_standard(struct TCP_Server_Info *server, next_is_large = server->large_buf; one_more: shdr = (struct smb2_sync_hdr *)buf; - if (shdr->NextCommand) { + next_cmd = le32_to_cpu(shdr->NextCommand); + if (next_cmd) { + if (WARN_ON_ONCE(next_cmd > pdu_length)) + return -1; if (next_is_large) next_buffer = (char *)cifs_buf_get(); else next_buffer = (char *)cifs_small_buf_get(); - memcpy(next_buffer, - buf + le32_to_cpu(shdr->NextCommand), - pdu_length - le32_to_cpu(shdr->NextCommand)); + memcpy(next_buffer, buf + next_cmd, pdu_length - next_cmd); } mid_entry = smb2_find_mid(server, buf); @@ -3244,8 +3246,8 @@ receive_encrypted_standard(struct TCP_Server_Info *server, else ret = cifs_handle_standard(server, mid_entry); - if (ret == 0 && shdr->NextCommand) { - pdu_length -= le32_to_cpu(shdr->NextCommand); + if (ret == 0 && next_cmd) { + pdu_length -= next_cmd; server->large_buf = next_is_large; if (next_is_large) server->bigbuf = buf = next_buffer; -- 2.34.3

2 1

[PATCH OLK-6.6 0/6] kabi: net: reserve space for net
by Zhengchao Shao 17 Jan '24

17 Jan '24

Reserve space for net, inheriting the kabi reservation in kernel 5.10. Wang Hai (6): kabi: net: reserve space for net base subsystem related structure kabi: net: reserve space for net bpf subsystem related structure kabi: net: reserve space for net can subsystem related structure kabi: net: reserve space for net netfilter subsystem related structure kabi: net: reserve space for net rdma subsystem related structure kabi: net: reserve space for net sunrpc subsystem related structure include/linux/can/core.h | 4 +++ include/linux/can/dev.h | 6 ++++ include/linux/can/rx-offload.h | 4 +++ include/linux/device.h | 10 ++++++ include/linux/device/class.h | 6 ++++ include/linux/ethtool.h | 6 ++++ include/linux/inetdevice.h | 4 +++ include/linux/ipv6.h | 6 ++++ include/linux/net.h | 6 ++++ include/linux/netdevice.h | 42 ++++++++++++++++++++++++++ include/linux/netfilter.h | 13 ++++++++ include/linux/netfilter/ipset/ip_set.h | 10 ++++++ include/linux/netfilter/nfnetlink.h | 7 +++++ include/linux/netfilter_ipv6.h | 4 +++ include/linux/skbuff.h | 6 ++++ include/linux/skmsg.h | 11 +++++++ include/linux/sunrpc/cache.h | 4 +++ include/linux/sunrpc/clnt.h | 12 ++++++++ include/linux/sunrpc/sched.h | 15 +++++++++ include/linux/sunrpc/stats.h | 7 +++++ include/linux/sunrpc/xprt.h | 17 +++++++++++ include/net/dcbnl.h | 10 ++++++ include/net/dst.h | 10 ++++++ include/net/dst_ops.h | 10 ++++++ include/net/fib_rules.h | 10 ++++++ include/net/flow.h | 7 +++++ include/net/flow_dissector.h | 6 ++++ include/net/genetlink.h | 12 ++++++++ include/net/inet_connection_sock.h | 7 +++++ include/net/ip6_fib.h | 13 ++++++++ include/net/l3mdev.h | 6 ++++ include/net/lwtunnel.h | 7 +++++ include/net/neighbour.h | 11 +++++++ include/net/netdev_rx_queue.h | 5 +++ include/net/netfilter/nf_conntrack.h | 4 +++ include/net/netlink.h | 5 +++ include/net/netns/can.h | 4 +++ include/net/netns/ipv4.h | 8 +++++ include/net/netns/ipv6.h | 4 +++ include/net/netns/netfilter.h | 4 +++ include/net/netns/nftables.h | 4 +++ include/net/netns/xfrm.h | 4 +++ include/net/page_pool/types.h | 4 +++ include/net/rtnetlink.h | 10 ++++++ include/net/sch_generic.h | 11 +++++++ include/net/sock.h | 18 +++++++++++ include/net/switchdev.h | 6 ++++ include/net/tcp.h | 6 ++++ include/net/tls.h | 15 +++++++++ include/net/xdp.h | 6 ++++ include/net/xsk_buff_pool.h | 3 ++ include/rdma/ib_addr.h | 4 +++ include/rdma/rdma_cm.h | 10 ++++++ include/rdma/rdma_counter.h | 4 +++ include/rdma/rdma_netlink.h | 4 +++ include/rdma/rdma_vt.h | 7 +++++ include/rdma/rdmavt_qp.h | 5 +++ net/devlink/devl_internal.h | 5 +++ 58 files changed, 469 insertions(+) -- 2.34.1

2 7

[PATCH OLK-6.6] openeuler_defconfig: Disable new HW_RANDOM support for arm64
by Yi Yang 17 Jan '24

17 Jan '24

hulk inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I8WYFN -------------------------------- New hardware features are disable by default. Disable CONFIG_HW_RANDOM_HISTB,CONFIG_HW_RANDOM_ARM_SMCCC_TRNG, CONFIG_HW_RANDOM_CN10K in openeuler_defconfig on arm64. Signed-off-by: Yi Yang <yiyang13(a)huawei.com> --- arch/arm64/configs/openeuler_defconfig | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/arm64/configs/openeuler_defconfig b/arch/arm64/configs/openeuler_defconfig index 35dd6141f057..87d51893e69e 100644 --- a/arch/arm64/configs/openeuler_defconfig +++ b/arch/arm64/configs/openeuler_defconfig @@ -3568,13 +3568,13 @@ CONFIG_HW_RANDOM_TIMERIOMEM=m # CONFIG_HW_RANDOM_BA431 is not set CONFIG_HW_RANDOM_VIRTIO=m CONFIG_HW_RANDOM_HISI=y -CONFIG_HW_RANDOM_HISTB=y +# CONFIG_HW_RANDOM_HISTB is not set CONFIG_HW_RANDOM_XGENE=y CONFIG_HW_RANDOM_CAVIUM=y # CONFIG_HW_RANDOM_CCTRNG is not set # CONFIG_HW_RANDOM_XIPHERA is not set -CONFIG_HW_RANDOM_ARM_SMCCC_TRNG=y -CONFIG_HW_RANDOM_CN10K=y +# CONFIG_HW_RANDOM_ARM_SMCCC_TRNG is not set +# CONFIG_HW_RANDOM_CN10K is not set # CONFIG_APPLICOM is not set CONFIG_DEVMEM=y # CONFIG_DEVPORT is not set -- 2.25.1

2 1

[PATCH] mm/oom_kill: fix NULL pointer dereference in memcg_print_bad_task()
by Jinjiang Tu 17 Jan '24

17 Jan '24

hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8WVL2 CVE: NA -------------------------------- oc->chosen may be assigned with -1 in oom_evaluate_task(), but memcg_print_bad_task() doesn't check whether oc->chosen is -1 before dereference it. Signed-off-by: Jinjiang Tu <tujinjiang(a)huawei.com> --- mm/memcontrol.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 7ab0eec942ba..8327cef9d53a 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4219,7 +4219,7 @@ void memcg_print_bad_task(struct oom_control *oc) if (memcg_oom_prio_disabled()) return; - if (oc->chosen) { + if (oc->chosen && oc->chosen != (void *)-1UL) { struct mem_cgroup *memcg; rcu_read_lock(); -- 2.25.1

1 0

[PATCH OLK-6.6] mm/oom_kill: fix NULL pointer dereference in memcg_print_bad_task()
by Jinjiang Tu 17 Jan '24

17 Jan '24

hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8WVL2 CVE: NA -------------------------------- oc->chosen may be assigned with -1 in oom_evaluate_task(), but memcg_print_bad_task() doesn't check whether oc->chosen is -1 before dereference it. Signed-off-by: Jinjiang Tu <tujinjiang(a)huawei.com> --- mm/memcontrol.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 7ab0eec942ba..8327cef9d53a 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4219,7 +4219,7 @@ void memcg_print_bad_task(struct oom_control *oc) if (memcg_oom_prio_disabled()) return; - if (oc->chosen) { + if (oc->chosen && oc->chosen != (void *)-1UL) { struct mem_cgroup *memcg; rcu_read_lock(); -- 2.25.1

2 1

[PATCH OLK-6.6 v6 0/8] introduce smart_grid zone
by Yipeng Zou 17 Jan '24

17 Jan '24

The patch sets include two parts: 1. patch 1~3: Rebase smart_grid from OLK-5.10 to OLK-6.6 2. patch 4~8: introduce smart_grid zone qos and cpufreq Since V5: 1. Only modified mm/mempolicy.c review comments Since V4: 1. rebase to OLK-6.6 head Since V3: 1. fix some review comments Since V2: 1. move new sysctl form sysctl.c to fair.c 2. add smart_grid cmdline Since V1: 1. Don't init smart_grid cpufreq with dynamic_affinity disable. 2. Forbid smart_grid cgroup interface with dynamic_affinity disable. Hui Tang (1): sched: Introduce smart grid scheduling strategy for cfs Wang ShaoBo (2): sched: smart grid: init sched_grid_qos structure on QOS purpose config: enable CONFIG_QOS_SCHED_SMART_GRID by default Yipeng Zou (5): sched: introduce smart grid qos zone smart_grid: introduce /proc/pid/smart_grid_level smart_grid: introduce smart_grid_strategy_ctrl sysctl smart_grid: cpufreq: introduce smart_grid cpufreq control smart_grid: introduce smart_grid cmdline arch/arm64/configs/openeuler_defconfig | 1 + arch/x86/configs/openeuler_defconfig | 1 + drivers/cpufreq/cpufreq.c | 244 +++++++++++ fs/proc/array.c | 16 + fs/proc/base.c | 84 ++++ include/linux/cpufreq.h | 11 + include/linux/sched.h | 32 ++ include/linux/sched/grid_qos.h | 135 +++++++ init/Kconfig | 13 + kernel/fork.c | 15 + kernel/sched/Makefile | 1 + kernel/sched/core.c | 181 +++++++++ kernel/sched/fair.c | 537 ++++++++++++++++++++++++- kernel/sched/grid/Makefile | 2 + kernel/sched/grid/internal.h | 6 + kernel/sched/grid/power.c | 27 ++ kernel/sched/grid/qos.c | 279 +++++++++++++ kernel/sched/grid/stat.c | 47 +++ kernel/sched/sched.h | 48 ++- mm/mempolicy.c | 11 +- 20 files changed, 1679 insertions(+), 12 deletions(-) create mode 100644 include/linux/sched/grid_qos.h create mode 100644 kernel/sched/grid/Makefile create mode 100644 kernel/sched/grid/internal.h create mode 100644 kernel/sched/grid/power.c create mode 100644 kernel/sched/grid/qos.c create mode 100644 kernel/sched/grid/stat.c -- 2.34.1

2 9

[PATCH OLK-6.6 0/2] Set CONFIG_NODES_SHIFT to 8
by Liu Shixin 17 Jan '24

17 Jan '24

Patch[1] allow to set NODES_SHIFT between 8 and 10 on MAXSMP. Patch[2] set NODES_SHIFT to 8 for both x86_64 and ARM64 defconfig. Liu Shixin (2): x86/Kconfig: allow NODES_SHIFT to be set on MAXSMP openeuler_defconfig: set CONFIG_NODES_SHIFT to 8 for both x86_64/ARM64 arch/arm64/configs/openeuler_defconfig | 2 +- arch/x86/Kconfig | 3 ++- arch/x86/configs/openeuler_defconfig | 2 +- 3 files changed, 4 insertions(+), 3 deletions(-) -- 2.25.1

2 3

[PATCH OLK-6.6 0/9] Backport etmem feature to OLK 6.6
by Yuchen Tang 17 Jan '24

17 Jan '24

v3 -> v4 - backport only core etmem feature - modify kernel swap enabled toggle implementation v2 -> v3 - fix code style and commit messages v1 -> v2 - make independent patches to export symbols we need - make independent patches for etmem scan and swap config - fix indentation and code style problems Yuchen Tang (9): etmem: add ETMEM feature CONFIG to mm/Kconfig etmem: add ETMEM scan feature CONFIG to mm/Kconfig mm: Export symbol __pud_trans_huge_lock mm: Export symbol walk_page_range etmem: add etmem scan feature mm: Export symbol reclaim_pages etmem: add etmem swap feature etmem: add original kernel swap enabled options etmem: enable etmem configurations arch/arm64/configs/openeuler_defconfig | 3 + arch/x86/configs/openeuler_defconfig | 3 + fs/proc/Makefile | 3 + fs/proc/base.c | 8 + fs/proc/etmem_proc.c | 216 ++++ fs/proc/etmem_scan.c | 1383 ++++++++++++++++++++++++ fs/proc/etmem_scan.h | 149 +++ fs/proc/etmem_swap.c | 109 ++ fs/proc/internal.h | 4 + include/linux/etmem.h | 47 + include/linux/mm.h | 4 + include/linux/mm_types.h | 4 + include/linux/swap.h | 1 + include/uapi/asm-generic/mman-common.h | 4 + mm/Kconfig | 33 + mm/Makefile | 1 + mm/etmem.c | 95 ++ mm/huge_memory.c | 1 + mm/internal.h | 1 - mm/madvise.c | 16 + mm/pagewalk.c | 1 + mm/swap_state.c | 4 + mm/vmscan.c | 8 + virt/kvm/kvm_main.c | 8 + 24 files changed, 2105 insertions(+), 1 deletion(-) create mode 100644 fs/proc/etmem_proc.c create mode 100644 fs/proc/etmem_scan.c create mode 100644 fs/proc/etmem_scan.h create mode 100644 fs/proc/etmem_swap.c create mode 100644 include/linux/etmem.h create mode 100644 mm/etmem.c -- 2.33.0

2 10

[PATCH openEuler-1.0-LTS] crypto: hisilicon/qm: fix several issues
by wangyuan 16 Jan '24

16 Jan '24

driver inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8WNSG CVE: NA -------------------------------------------------------- 1.qm_hw_error parse in qm_abnormal_irq and qm_log_hw_error is different, ARRAY_SIZE(qm_hw_error) exceeds actual treatment area. 2.add method judgement in qm_clear_device. Signed-off-by: wangyuan <wangyuan46(a)huawei.com> --- drivers/crypto/hisilicon/qm.c | 28 ++++++++++++++++++++-------- 1 file changed, 20 insertions(+), 8 deletions(-) diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c index 25bb24b4c131..6abaec751867 100644 --- a/drivers/crypto/hisilicon/qm.c +++ b/drivers/crypto/hisilicon/qm.c @@ -277,8 +277,7 @@ static const struct hisi_qm_hw_error qm_hw_error[] = { { .int_msk = BIT(9), .msg = "qm_sq_vf_invalid" }, { .int_msk = BIT(10), .msg = "qm_db_timeout" }, { .int_msk = BIT(11), .msg = "qm_of_fifo_of" }, - { .int_msk = BIT(12), .msg = "qm_db_random_invalid" }, - { /* sentinel */ } + { .int_msk = BIT(12), .msg = "qm_db_random_invalid" } }; static const char * const qm_db_timeout[] = { @@ -774,10 +773,11 @@ static irqreturn_t qm_aeq_irq(int irq, void *data) static irqreturn_t qm_abnormal_irq(int irq, void *data) { - const struct hisi_qm_hw_error *err = qm_hw_error; + const struct hisi_qm_hw_error *err; struct hisi_qm *qm = data; struct device *dev = &qm->pdev->dev; u32 error_status, tmp; + int i; atomic64_inc(&qm->debug.dfx.abnormal_irq_cnt); if (qm->abnormal_fix) { @@ -789,12 +789,13 @@ static irqreturn_t qm_abnormal_irq(int irq, void *data) tmp = readl(qm->io_base + QM_ABNORMAL_INT_STATUS); error_status = qm->msi_mask & tmp; - while (err->msg) { - if (err->int_msk & error_status) - dev_err(dev, "%s [error status=0x%x] found\n", - err->msg, err->int_msk); + for (i = 0; i < ARRAY_SIZE(qm_hw_error); i++) { + err = &qm_hw_error[i]; + if (!(err->int_msk & error_status)) + continue; - err++; + dev_err(dev, "%s [error status=0x%x] found\n", + err->msg, err->int_msk); } /* clear err sts */ @@ -2639,12 +2640,23 @@ static int hisi_qm_memory_init(struct hisi_qm *qm) static int qm_clear_device(struct hisi_qm *qm) { + acpi_handle handle = ACPI_HANDLE(&qm->pdev->dev); u32 val; int ret; if (qm->fun_type == QM_HW_VF) return 0; + if (!handle) { + pci_warn(qm->pdev, "Device does not support reset, return.\n"); + return 0; + } + + if (!acpi_has_method(handle, qm->err_ini.err_info.acpi_rst)) { + pci_warn(qm->pdev, "BIOS has no reset method, return.\n"); + return 0; + } + /* OOO register set and check */ writel(MASTER_GLOBAL_CTRL_SHUTDOWN, qm->io_base + MASTER_GLOBAL_CTRL); -- 2.33.0

2 1

[PATCH OLK-6.6 V7 00/12] sched: basic infrastructure for scheduler bpf
by Lu Jialin 16 Jan '24

16 Jan '24

From: Guan Jing <guanjing6(a)huawei.com> sched: basic infrastructure for scheduler bpf Guan Jing (12): sched: programmable: Introduce bpf sched sched: programmable: Add a tag for the task sched: programmable: Add a tag for the task group sched: programmable: Add user interface of task group tag sched: programmable: Add user interface of task tag sched: basic infrastructure for scheduler bpf sched: introduce bpf_sched_enable() libbpf: add support for scheduler bpf programs bpftool: recognize scheduler programs sched: programmable: Add hook in select_task_rq_fair() sched: programmable: Add hook in can_migrate_task() openeuler_defconfig: enable CONFIG_BPF_SCHED arch/arm64/configs/openeuler_defconfig | 1 + arch/x86/configs/openeuler_defconfig | 1 + fs/proc/base.c | 64 ++++++++++++++ include/linux/bpf_sched.h | 50 +++++++++++ include/linux/bpf_types.h | 4 + include/linux/sched.h | 27 ++++++ include/linux/sched_hook_defs.h | 4 + include/uapi/linux/bpf.h | 2 + init/init_task.c | 3 + kernel/bpf/Kconfig | 12 +++ kernel/bpf/btf.c | 3 + kernel/bpf/syscall.c | 41 +++++++++ kernel/bpf/trampoline.c | 3 + kernel/bpf/verifier.c | 23 +++++ kernel/sched/bpf_sched.c | 64 ++++++++++++++ kernel/sched/build_utility.c | 4 + kernel/sched/core.c | 118 +++++++++++++++++++++++++ kernel/sched/fair.c | 45 ++++++++++ kernel/sched/sched.h | 10 +++ scripts/bpf_doc.py | 2 + tools/include/uapi/linux/bpf.h | 2 + tools/lib/bpf/bpf.c | 1 + tools/lib/bpf/libbpf.c | 23 ++++- tools/lib/bpf/libbpf.h | 2 + tools/lib/bpf/libbpf.map | 1 + 25 files changed, 509 insertions(+), 1 deletion(-) create mode 100644 include/linux/bpf_sched.h create mode 100644 include/linux/sched_hook_defs.h create mode 100644 kernel/sched/bpf_sched.c -- 2.34.1

2 13

[PATCH OLK-5.10] fs:/dcache.c: fix negative dentry limit not complete problem
by Long Li 16 Jan '24

16 Jan '24

hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8WPQW CVE: NA -------------------------------- Restrictions of negative dentry can avoid softlock when too many dentry in memory, but restrictions before do not always take effect. For example, removing files which has been created would not enter retain_dentry(), because the dentry of file maybe has been added to lru list of superblock, it caused that fast_dput() reutrn true in last dput(). So, add restriction logic for the file which has been added to the lru list in fast_dput(), it prevents the negative dentry exceeding the limit when deleting existing file. Fixes: c44e1f780873 ("fs/dcache.c: avoid softlock since too many negative dentry") Signed-off-by: Long Li <leo.lilong(a)huawei.com> --- fs/dcache.c | 22 ++++++++++++++++++++-- 1 file changed, 20 insertions(+), 2 deletions(-) diff --git a/fs/dcache.c b/fs/dcache.c index f5b78cc80a00..6fb18d83aaf8 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -776,6 +776,7 @@ static inline bool fast_dput(struct dentry *dentry) { int ret; unsigned int d_flags; + struct dentry *parent; /* * If we have a d_op->d_delete() operation, we sould not @@ -837,8 +838,25 @@ static inline bool fast_dput(struct dentry *dentry) d_flags &= DCACHE_REFERENCED | DCACHE_LRU_LIST | DCACHE_DISCONNECTED; /* Nothing to do? Dropping the reference was all we needed? */ - if (d_flags == (DCACHE_REFERENCED | DCACHE_LRU_LIST) && !d_unhashed(dentry)) - return true; + if (d_flags == (DCACHE_REFERENCED | DCACHE_LRU_LIST) && !d_unhashed(dentry)) { + parent = dentry->d_parent; + if (!parent) + return true; + + WARN_ON((atomic_read(&parent->d_neg_dnum) < 0)); + if (!dentry->d_inode) { + if (!(dentry->d_flags & DCACHE_NEGATIVE_ACCOUNT)) { + unsigned int flags = READ_ONCE(dentry->d_flags); + + flags |= DCACHE_NEGATIVE_ACCOUNT; + WRITE_ONCE(dentry->d_flags, flags); + atomic_inc(&parent->d_neg_dnum); + } + } + if (dentry->d_inode || + atomic_read(&parent->d_neg_dnum) < NEG_DENTRY_LIMIT) + return true; + } /* * Not the fast normal case? Get the lock. We've already decremented -- 2.31.1

2 1

[PATCH OLK-6.6] ubi: fix slab-out-of-bounds in ubi_eba_get_ldesc+0xfb/0x130
by ZhaoLong Wang 16 Jan '24

16 Jan '24

From: Guo Xuenan <guoxuenan(a)huawei.com> hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8WPL1 CVE: NA ---------------------------------------- When using the ioctl interface to resize a UBI volume, `ubi_resize_volume` resizes the EBA table first but does not change `vol->reserved_pebs` in the same atomic context, which may cause concurrent access to the EBA table. For example, when a user shrinks UBI volume A by calling `ubi_resize_volume`, while another thread is writing to volume B and triggering wear-leveling, which may call `ubi_write_fastmap`, under these circumstances, KASAN may report a slab-out-of-bounds error in `ubi_eba_get_ldesc+0xfb/0x130`. This patch fixes race conditions in `ubi_resize_volume` and `ubi_update_fastmap` to avoid out-of-bounds reads of `eba_tbl`. First, it ensures that updates to `eba_tbl` and `reserved_pebs` are protected by `vol->volumes_lock`. Second, it implements a rollback mechanism in case of resize failure. It is also worth mentioning that for volume shrinkage failures, since part of the volume has already been shrunk and unmapped, there is no need to recover `{rsvd/avail}_pebs`. ================================================================== BUG: KASAN: slab-out-of-bounds in ubi_eba_get_ldesc+0xfb/0x130 [ubi] Read of size 4 at addr ffff88800f43f570 by task kworker/u16:0/7 CPU: 0 PID: 7 Comm: kworker/u16:0 Not tainted 5.16.0-rc7 #3 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1ubuntu1.1 04/01/2014 Workqueue: writeback wb_workfn (flush-ubifs_0_0) Call Trace: <TASK> dump_stack_lvl+0x4d/0x66 print_address_description.constprop.0+0x41/0x60 kasan_report.cold+0x83/0xdf ubi_eba_get_ldesc+0xfb/0x130 [ubi] ubi_update_fastmap.cold+0x60f/0xc7d [ubi] ubi_wl_get_peb+0x25b/0x4f0 [ubi] try_write_vid_and_data+0x9a/0x4d0 [ubi] ubi_eba_write_leb+0x7e4/0x17d0 [ubi] ubi_leb_map+0x1a0/0x2c0 [ubi] ubifs_leb_map+0x139/0x270 [ubifs] ubifs_add_bud_to_log+0xb40/0xf30 [ubifs] make_reservation+0x86e/0xb00 [ubifs] ubifs_jnl_write_data+0x430/0x9d0 [ubifs] do_writepage+0x1d1/0x550 [ubifs] ubifs_writepage+0x37c/0x670 [ubifs] __writepage+0x67/0x170 write_cache_pages+0x259/0xa90 do_writepages+0x277/0x5d0 __writeback_single_inode+0xb8/0x850 writeback_sb_inodes+0x4b3/0xb20 __writeback_inodes_wb+0xc1/0x220 wb_writeback+0x59f/0x740 wb_workfn+0x6d0/0xca0 process_one_work+0x711/0xfc0 worker_thread+0x95/0xd00 kthread+0x3a6/0x490 ret_from_fork+0x1f/0x30 </TASK> Allocated by task 711: kasan_save_stack+0x1e/0x50 __kasan_kmalloc+0x81/0xa0 ubi_eba_create_table+0x88/0x1a0 [ubi] ubi_resize_volume.cold+0x175/0xae7 [ubi] ubi_cdev_ioctl+0x57f/0x1a60 [ubi] __x64_sys_ioctl+0x13a/0x1c0 do_syscall_64+0x35/0x80 entry_SYSCALL_64_after_hwframe+0x44/0xae Last potentially related work creation: kasan_save_stack+0x1e/0x50 __kasan_record_aux_stack+0xb7/0xc0 call_rcu+0xd6/0x1000 blk_stat_free_callback+0x28/0x30 blk_release_queue+0x8a/0x2e0 kobject_put+0x186/0x4c0 scsi_device_dev_release_usercontext+0x620/0xbd0 execute_in_process_context+0x2f/0x120 device_release+0xa4/0x240 kobject_put+0x186/0x4c0 put_device+0x20/0x30 __scsi_remove_device+0x1c3/0x300 scsi_probe_and_add_lun+0x2140/0x2eb0 __scsi_scan_target+0x1f2/0xbb0 scsi_scan_channel+0x11b/0x1a0 scsi_scan_host_selected+0x24c/0x310 do_scsi_scan_host+0x1e0/0x250 do_scan_async+0x45/0x490 async_run_entry_fn+0xa2/0x530 process_one_work+0x711/0xfc0 worker_thread+0x95/0xd00 kthread+0x3a6/0x490 ret_from_fork+0x1f/0x30 The buggy address belongs to the object at ffff88800f43f500 which belongs to the cache kmalloc-128 of size 128 The buggy address is located 112 bytes inside of 128-byte region [ffff88800f43f500, ffff88800f43f580) The buggy address belongs to the page: page:ffffea00003d0f00 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0xf43c head:ffffea00003d0f00 order:2 compound_mapcount:0 compound_pincount:0 flags: 0x1fffff80010200(slab|head|node=0|zone=1|lastcpupid=0x1fffff) raw: 001fffff80010200 ffffea000046ba08 ffffea0000457208 ffff88810004d1c0 raw: 0000000000000000 0000000000190019 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff88800f43f400: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffff88800f43f480: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc > ffff88800f43f500: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 fc fc ^ ffff88800f43f580: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffff88800f43f600: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc The following steps can used to reproduce: Process 1: write and trigger ubi wear-leveling ubimkvol /dev/ubi0 -s 5000MiB -N v1 ubimkvol /dev/ubi0 -s 2000MiB -N v2 ubimkvol /dev/ubi0 -s 10MiB -N v3 mount -t ubifs /dev/ubi0_0 /mnt/ubifs while true; do filename=/mnt/ubifs/$((RANDOM)) dd if=/dev/random of=${filename} bs=1M count=$((RANDOM % 1000)) rm -rf ${filename} sync /mnt/ubifs/ done Process 2: do random resize struct ubi_rsvol_req req; req.vol_id = 1; req.bytes = (rand() % 50) * 512KB; ioctl(fd, UBI_IOCRSVOL, &req); V3: - Fix the commit message error. V2: - Add volumes_lock in ubi_eba_copy_leb() to avoid race caused by updating eba_tbl. V1: - Rebase the patch on the latest mainline. Signed-off-by: Guo Xuenan <guoxuenan(a)huawei.com> Signed-off-by: ZhaoLong Wang <wangzhaolong1(a)huawei.com> Reviewed-by: Zhihao Cheng <chengzhihao1(a)huawei.com> --- drivers/mtd/ubi/eba.c | 7 +++++++ drivers/mtd/ubi/vmt.c | 24 +++++++++++++++++------- 2 files changed, 24 insertions(+), 7 deletions(-) diff --git a/drivers/mtd/ubi/eba.c b/drivers/mtd/ubi/eba.c index 655ff41863e2..ce9ac7932cc3 100644 --- a/drivers/mtd/ubi/eba.c +++ b/drivers/mtd/ubi/eba.c @@ -1459,7 +1459,14 @@ int ubi_eba_copy_leb(struct ubi_device *ubi, int from, int to, } ubi_assert(vol->eba_tbl->entries[lnum].pnum == from); + + /** + * The volumes_lock lock is needed here to prevent the expired old eba_tbl + * being updated when the eba_tbl is copied in the ubi_resize_volume() process. + */ + spin_lock(&ubi->volumes_lock); vol->eba_tbl->entries[lnum].pnum = to; + spin_unlock(&ubi->volumes_lock); out_unlock_buf: mutex_unlock(&ubi->buf_mutex); diff --git a/drivers/mtd/ubi/vmt.c b/drivers/mtd/ubi/vmt.c index 2c867d16f89f..97294def01eb 100644 --- a/drivers/mtd/ubi/vmt.c +++ b/drivers/mtd/ubi/vmt.c @@ -408,6 +408,7 @@ int ubi_resize_volume(struct ubi_volume_desc *desc, int reserved_pebs) struct ubi_device *ubi = vol->ubi; struct ubi_vtbl_record vtbl_rec; struct ubi_eba_table *new_eba_tbl = NULL; + struct ubi_eba_table *old_eba_tbl = NULL; int vol_id = vol->vol_id; if (ubi->ro_mode) @@ -453,10 +454,13 @@ int ubi_resize_volume(struct ubi_volume_desc *desc, int reserved_pebs) err = -ENOSPC; goto out_free; } + ubi->avail_pebs -= pebs; ubi->rsvd_pebs += pebs; ubi_eba_copy_table(vol, new_eba_tbl, vol->reserved_pebs); - ubi_eba_replace_table(vol, new_eba_tbl); + old_eba_tbl = vol->eba_tbl; + vol->eba_tbl = new_eba_tbl; + vol->reserved_pebs = reserved_pebs; spin_unlock(&ubi->volumes_lock); } @@ -471,7 +475,9 @@ int ubi_resize_volume(struct ubi_volume_desc *desc, int reserved_pebs) ubi->avail_pebs -= pebs; ubi_update_reserved(ubi); ubi_eba_copy_table(vol, new_eba_tbl, reserved_pebs); - ubi_eba_replace_table(vol, new_eba_tbl); + old_eba_tbl = vol->eba_tbl; + vol->eba_tbl = new_eba_tbl; + vol->reserved_pebs = reserved_pebs; spin_unlock(&ubi->volumes_lock); } @@ -493,7 +499,6 @@ int ubi_resize_volume(struct ubi_volume_desc *desc, int reserved_pebs) if (err) goto out_acc; - vol->reserved_pebs = reserved_pebs; if (vol->vol_type == UBI_DYNAMIC_VOLUME) { vol->used_ebs = reserved_pebs; vol->last_eb_bytes = vol->usable_leb_size; @@ -501,19 +506,24 @@ int ubi_resize_volume(struct ubi_volume_desc *desc, int reserved_pebs) (long long)vol->used_ebs * vol->usable_leb_size; } + /* destroy old table */ + ubi_eba_destroy_table(old_eba_tbl); ubi_volume_notify(ubi, vol, UBI_VOLUME_RESIZED); self_check_volumes(ubi); return err; out_acc: + spin_lock(&ubi->volumes_lock); + vol->reserved_pebs = reserved_pebs - pebs; if (pebs > 0) { - spin_lock(&ubi->volumes_lock); ubi->rsvd_pebs -= pebs; ubi->avail_pebs += pebs; - spin_unlock(&ubi->volumes_lock); + ubi_eba_copy_table(vol, old_eba_tbl, vol->reserved_pebs); + } else { + ubi_eba_copy_table(vol, old_eba_tbl, reserved_pebs); } - return err; - + vol->eba_tbl = old_eba_tbl; + spin_unlock(&ubi->volumes_lock); out_free: ubi_eba_destroy_table(new_eba_tbl); return err; -- 2.39.2

2 1

[PATCH OLK-6.6] ubi: fix slab-out-of-bounds in ubi_eba_get_ldesc+0xfb/0x130
by ZhaoLong Wang 16 Jan '24

16 Jan '24

From: Guo Xuenan <guoxuenan(a)huawei.com> When using the ioctl interface to resize a UBI volume, `ubi_resize_volume` resizes the EBA table first but does not change `vol->reserved_pebs` in the same atomic context, which may cause concurrent access to the EBA table. For example, when a user shrinks UBI volume A by calling `ubi_resize_volume`, while another thread is writing to volume B and triggering wear-leveling, which may call `ubi_write_fastmap`, under these circumstances, KASAN may report a slab-out-of-bounds error in `ubi_eba_get_ldesc+0xfb/0x130`. This patch fixes race conditions in `ubi_resize_volume` and `ubi_update_fastmap` to avoid out-of-bounds reads of `eba_tbl`. First, it ensures that updates to `eba_tbl` and `reserved_pebs` are protected by `vol->volumes_lock`. Second, it implements a rollback mechanism in case of resize failure. It is also worth mentioning that for volume shrinkage failures, since part of the volume has already been shrunk and unmapped, there is no need to recover `{rsvd/avail}_pebs`. ================================================================== BUG: KASAN: slab-out-of-bounds in ubi_eba_get_ldesc+0xfb/0x130 [ubi] Read of size 4 at addr ffff88800f43f570 by task kworker/u16:0/7 CPU: 0 PID: 7 Comm: kworker/u16:0 Not tainted 5.16.0-rc7 #3 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1ubuntu1.1 04/01/2014 Workqueue: writeback wb_workfn (flush-ubifs_0_0) Call Trace: <TASK> dump_stack_lvl+0x4d/0x66 print_address_description.constprop.0+0x41/0x60 kasan_report.cold+0x83/0xdf ubi_eba_get_ldesc+0xfb/0x130 [ubi] ubi_update_fastmap.cold+0x60f/0xc7d [ubi] ubi_wl_get_peb+0x25b/0x4f0 [ubi] try_write_vid_and_data+0x9a/0x4d0 [ubi] ubi_eba_write_leb+0x7e4/0x17d0 [ubi] ubi_leb_map+0x1a0/0x2c0 [ubi] ubifs_leb_map+0x139/0x270 [ubifs] ubifs_add_bud_to_log+0xb40/0xf30 [ubifs] make_reservation+0x86e/0xb00 [ubifs] ubifs_jnl_write_data+0x430/0x9d0 [ubifs] do_writepage+0x1d1/0x550 [ubifs] ubifs_writepage+0x37c/0x670 [ubifs] __writepage+0x67/0x170 write_cache_pages+0x259/0xa90 do_writepages+0x277/0x5d0 __writeback_single_inode+0xb8/0x850 writeback_sb_inodes+0x4b3/0xb20 __writeback_inodes_wb+0xc1/0x220 wb_writeback+0x59f/0x740 wb_workfn+0x6d0/0xca0 process_one_work+0x711/0xfc0 worker_thread+0x95/0xd00 kthread+0x3a6/0x490 ret_from_fork+0x1f/0x30 </TASK> Allocated by task 711: kasan_save_stack+0x1e/0x50 __kasan_kmalloc+0x81/0xa0 ubi_eba_create_table+0x88/0x1a0 [ubi] ubi_resize_volume.cold+0x175/0xae7 [ubi] ubi_cdev_ioctl+0x57f/0x1a60 [ubi] __x64_sys_ioctl+0x13a/0x1c0 do_syscall_64+0x35/0x80 entry_SYSCALL_64_after_hwframe+0x44/0xae Last potentially related work creation: kasan_save_stack+0x1e/0x50 __kasan_record_aux_stack+0xb7/0xc0 call_rcu+0xd6/0x1000 blk_stat_free_callback+0x28/0x30 blk_release_queue+0x8a/0x2e0 kobject_put+0x186/0x4c0 scsi_device_dev_release_usercontext+0x620/0xbd0 execute_in_process_context+0x2f/0x120 device_release+0xa4/0x240 kobject_put+0x186/0x4c0 put_device+0x20/0x30 __scsi_remove_device+0x1c3/0x300 scsi_probe_and_add_lun+0x2140/0x2eb0 __scsi_scan_target+0x1f2/0xbb0 scsi_scan_channel+0x11b/0x1a0 scsi_scan_host_selected+0x24c/0x310 do_scsi_scan_host+0x1e0/0x250 do_scan_async+0x45/0x490 async_run_entry_fn+0xa2/0x530 process_one_work+0x711/0xfc0 worker_thread+0x95/0xd00 kthread+0x3a6/0x490 ret_from_fork+0x1f/0x30 The buggy address belongs to the object at ffff88800f43f500 which belongs to the cache kmalloc-128 of size 128 The buggy address is located 112 bytes inside of 128-byte region [ffff88800f43f500, ffff88800f43f580) The buggy address belongs to the page: page:ffffea00003d0f00 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0xf43c head:ffffea00003d0f00 order:2 compound_mapcount:0 compound_pincount:0 flags: 0x1fffff80010200(slab|head|node=0|zone=1|lastcpupid=0x1fffff) raw: 001fffff80010200 ffffea000046ba08 ffffea0000457208 ffff88810004d1c0 raw: 0000000000000000 0000000000190019 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff88800f43f400: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffff88800f43f480: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc > ffff88800f43f500: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 fc fc ^ ffff88800f43f580: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffff88800f43f600: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc The following steps can used to reproduce: Process 1: write and trigger ubi wear-leveling ubimkvol /dev/ubi0 -s 5000MiB -N v1 ubimkvol /dev/ubi0 -s 2000MiB -N v2 ubimkvol /dev/ubi0 -s 10MiB -N v3 mount -t ubifs /dev/ubi0_0 /mnt/ubifs while true; do filename=/mnt/ubifs/$((RANDOM)) dd if=/dev/random of=${filename} bs=1M count=$((RANDOM % 1000)) rm -rf ${filename} sync /mnt/ubifs/ done Process 2: do random resize struct ubi_rsvol_req req; req.vol_id = 1; req.bytes = (rand() % 50) * 512KB; ioctl(fd, UBI_IOCRSVOL, &req); V3: - Fix the commit message error. V2: - Add volumes_lock in ubi_eba_copy_leb() to avoid race caused by updating eba_tbl. V1: - Rebase the patch on the latest mainline. Signed-off-by: Guo Xuenan <guoxuenan(a)huawei.com> Signed-off-by: ZhaoLong Wang <wangzhaolong1(a)huawei.com> Reviewed-by: Zhihao Cheng <chengzhihao1(a)huawei.com> --- drivers/mtd/ubi/eba.c | 7 +++++++ drivers/mtd/ubi/vmt.c | 24 +++++++++++++++++------- 2 files changed, 24 insertions(+), 7 deletions(-) diff --git a/drivers/mtd/ubi/eba.c b/drivers/mtd/ubi/eba.c index 655ff41863e2..ce9ac7932cc3 100644 --- a/drivers/mtd/ubi/eba.c +++ b/drivers/mtd/ubi/eba.c @@ -1459,7 +1459,14 @@ int ubi_eba_copy_leb(struct ubi_device *ubi, int from, int to, } ubi_assert(vol->eba_tbl->entries[lnum].pnum == from); + + /** + * The volumes_lock lock is needed here to prevent the expired old eba_tbl + * being updated when the eba_tbl is copied in the ubi_resize_volume() process. + */ + spin_lock(&ubi->volumes_lock); vol->eba_tbl->entries[lnum].pnum = to; + spin_unlock(&ubi->volumes_lock); out_unlock_buf: mutex_unlock(&ubi->buf_mutex); diff --git a/drivers/mtd/ubi/vmt.c b/drivers/mtd/ubi/vmt.c index 2c867d16f89f..97294def01eb 100644 --- a/drivers/mtd/ubi/vmt.c +++ b/drivers/mtd/ubi/vmt.c @@ -408,6 +408,7 @@ int ubi_resize_volume(struct ubi_volume_desc *desc, int reserved_pebs) struct ubi_device *ubi = vol->ubi; struct ubi_vtbl_record vtbl_rec; struct ubi_eba_table *new_eba_tbl = NULL; + struct ubi_eba_table *old_eba_tbl = NULL; int vol_id = vol->vol_id; if (ubi->ro_mode) @@ -453,10 +454,13 @@ int ubi_resize_volume(struct ubi_volume_desc *desc, int reserved_pebs) err = -ENOSPC; goto out_free; } + ubi->avail_pebs -= pebs; ubi->rsvd_pebs += pebs; ubi_eba_copy_table(vol, new_eba_tbl, vol->reserved_pebs); - ubi_eba_replace_table(vol, new_eba_tbl); + old_eba_tbl = vol->eba_tbl; + vol->eba_tbl = new_eba_tbl; + vol->reserved_pebs = reserved_pebs; spin_unlock(&ubi->volumes_lock); } @@ -471,7 +475,9 @@ int ubi_resize_volume(struct ubi_volume_desc *desc, int reserved_pebs) ubi->avail_pebs -= pebs; ubi_update_reserved(ubi); ubi_eba_copy_table(vol, new_eba_tbl, reserved_pebs); - ubi_eba_replace_table(vol, new_eba_tbl); + old_eba_tbl = vol->eba_tbl; + vol->eba_tbl = new_eba_tbl; + vol->reserved_pebs = reserved_pebs; spin_unlock(&ubi->volumes_lock); } @@ -493,7 +499,6 @@ int ubi_resize_volume(struct ubi_volume_desc *desc, int reserved_pebs) if (err) goto out_acc; - vol->reserved_pebs = reserved_pebs; if (vol->vol_type == UBI_DYNAMIC_VOLUME) { vol->used_ebs = reserved_pebs; vol->last_eb_bytes = vol->usable_leb_size; @@ -501,19 +506,24 @@ int ubi_resize_volume(struct ubi_volume_desc *desc, int reserved_pebs) (long long)vol->used_ebs * vol->usable_leb_size; } + /* destroy old table */ + ubi_eba_destroy_table(old_eba_tbl); ubi_volume_notify(ubi, vol, UBI_VOLUME_RESIZED); self_check_volumes(ubi); return err; out_acc: + spin_lock(&ubi->volumes_lock); + vol->reserved_pebs = reserved_pebs - pebs; if (pebs > 0) { - spin_lock(&ubi->volumes_lock); ubi->rsvd_pebs -= pebs; ubi->avail_pebs += pebs; - spin_unlock(&ubi->volumes_lock); + ubi_eba_copy_table(vol, old_eba_tbl, vol->reserved_pebs); + } else { + ubi_eba_copy_table(vol, old_eba_tbl, reserved_pebs); } - return err; - + vol->eba_tbl = old_eba_tbl; + spin_unlock(&ubi->volumes_lock); out_free: ubi_eba_destroy_table(new_eba_tbl); return err; -- 2.39.2

2 1

[PATCH OLK-6.6 00/15] Support pv feature
by lishusen 16 Jan '24

16 Jan '24

Support pv feature Zenghui Yu (1): KVM: arm64: Fix {fp_asimd,sve}_exit_stat manipulation Zengruan Ye (10): KVM: arm64: Document PV-sched interface KVM: arm64: Implement PV_SCHED_FEATURES call KVM: arm64: Support pvsched preempted via shared structure KVM: arm64: Add interface to support vCPU preempted check KVM: arm64: Support the vCPU preemption check KVM: arm64: Add SMCCC PV-sched to kick cpu KVM: arm64: Implement PV_SCHED_KICK_CPU call KVM: arm64: Add interface to support PV qspinlock KVM: arm64: Enable PV qspinlock KVM: arm64: Add tracepoints for PV qspinlock chenjiajun (1): kvm: debugfs: export remaining aarch64 kvm exit reasons to debugfs lishusen (2): KVM: arm64: Replace pv.ops by static_call for PV qspinlock feature KVM: arm64: Add configuration for feature pv-sched yezengruan (1): kvm: arm64: fix some pvsched bugs C | 0 Documentation/virt/kvm/arm/pvsched.rst | 74 ++++++++ arch/arm64/Kconfig | 20 +++ arch/arm64/include/asm/Kbuild | 1 - arch/arm64/include/asm/kvm_host.h | 39 ++++ arch/arm64/include/asm/paravirt.h | 51 ++++++ arch/arm64/include/asm/pvsched-abi.h | 16 ++ arch/arm64/include/asm/qspinlock.h | 48 +++++ arch/arm64/include/asm/qspinlock_paravirt.h | 12 ++ arch/arm64/include/asm/spinlock.h | 13 ++ arch/arm64/kernel/Makefile | 3 +- arch/arm64/kernel/paravirt-spinlocks.c | 21 +++ arch/arm64/kernel/paravirt.c | 189 ++++++++++++++++++++ arch/arm64/kernel/trace-paravirt.h | 66 +++++++ arch/arm64/kvm/Makefile | 2 +- arch/arm64/kvm/arm.c | 34 ++++ arch/arm64/kvm/handle_exit.c | 12 ++ arch/arm64/kvm/hyp/include/hyp/switch.h | 2 + arch/arm64/kvm/hypercalls.c | 24 +++ arch/arm64/kvm/mmu.c | 1 + arch/arm64/kvm/pvsched.c | 81 +++++++++ arch/arm64/kvm/sys_regs.c | 11 ++ arch/arm64/kvm/trace_arm.h | 18 ++ include/linux/arm-smccc.h | 25 +++ include/linux/cpuhotplug.h | 1 + 25 files changed, 761 insertions(+), 3 deletions(-) create mode 100644 C create mode 100644 Documentation/virt/kvm/arm/pvsched.rst create mode 100644 arch/arm64/include/asm/pvsched-abi.h create mode 100644 arch/arm64/include/asm/qspinlock.h create mode 100644 arch/arm64/include/asm/qspinlock_paravirt.h create mode 100644 arch/arm64/kernel/paravirt-spinlocks.c create mode 100644 arch/arm64/kernel/trace-paravirt.h create mode 100644 arch/arm64/kvm/pvsched.c -- 2.33.0

2 16

[PATCH OLK-6.6 0/2] Support feature TWED
by lishusen 16 Jan '24

16 Jan '24

Support feature TWED Jingyi Wang (1): KVM: arm64: Make use of TWED feature Zengruan Ye (1): arm64: cpufeature: TWED support detection arch/arm64/Kconfig | 10 ++++++++++ arch/arm64/include/asm/kvm_arm.h | 8 ++++++++ arch/arm64/include/asm/kvm_emulate.h | 27 +++++++++++++++++++++++++++ arch/arm64/include/asm/kvm_host.h | 11 +++++++++++ arch/arm64/include/asm/virt.h | 5 +++++ arch/arm64/kernel/cpufeature.c | 12 ++++++++++++ arch/arm64/kvm/arm.c | 15 +++++++++++++++ arch/arm64/tools/cpucaps | 1 + 8 files changed, 89 insertions(+) -- 2.33.0

2 3

[PATCH OLK-6.6 0/2] Support feature TWED
by lishusen 16 Jan '24

16 Jan '24

Support feature TWED Jingyi Wang (1): KVM: arm64: Make use of TWED feature Zengruan Ye (1): arm64: cpufeature: TWED support detection arch/arm64/Kconfig | 10 ++++++++++ arch/arm64/include/asm/kvm_arm.h | 8 ++++++++ arch/arm64/include/asm/kvm_emulate.h | 27 +++++++++++++++++++++++++++ arch/arm64/include/asm/kvm_host.h | 8 ++++++++ arch/arm64/include/asm/virt.h | 5 +++++ arch/arm64/kernel/cpufeature.c | 12 ++++++++++++ arch/arm64/kvm/arm.c | 15 +++++++++++++++ arch/arm64/tools/cpucaps | 1 + 8 files changed, 86 insertions(+) -- 2.33.0

2 3

[PATCH openEuler-1.0-LTS] crypto: hisilicon/qm: fix several issues
by wangyuan 16 Jan '24

16 Jan '24

driver inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8WNSG CVE: NA -------------------------------------------------------- 1.qm_hw_error parse in qm_abnormal_irq and qm_log_hw_error is different, ARRAY_SIZE(qm_hw_error) exceeds actual treatment area. 2.add method judgement in qm_clear_device. Signed-off-by: wangyuan <wangyuan46(a)huawei.com> --- drivers/crypto/hisilicon/qm.c | 37 +++++++++++++++++++++++------------ 1 file changed, 24 insertions(+), 13 deletions(-) diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c index 25bb24b4c131..7ca30b7d0446 100644 --- a/drivers/crypto/hisilicon/qm.c +++ b/drivers/crypto/hisilicon/qm.c @@ -277,8 +277,7 @@ static const struct hisi_qm_hw_error qm_hw_error[] = { { .int_msk = BIT(9), .msg = "qm_sq_vf_invalid" }, { .int_msk = BIT(10), .msg = "qm_db_timeout" }, { .int_msk = BIT(11), .msg = "qm_of_fifo_of" }, - { .int_msk = BIT(12), .msg = "qm_db_random_invalid" }, - { /* sentinel */ } + { .int_msk = BIT(12), .msg = "qm_db_random_invalid" } }; static const char * const qm_db_timeout[] = { @@ -774,10 +773,11 @@ static irqreturn_t qm_aeq_irq(int irq, void *data) static irqreturn_t qm_abnormal_irq(int irq, void *data) { - const struct hisi_qm_hw_error *err = qm_hw_error; + const struct hisi_qm_hw_error *err; struct hisi_qm *qm = data; struct device *dev = &qm->pdev->dev; u32 error_status, tmp; + int i; atomic64_inc(&qm->debug.dfx.abnormal_irq_cnt); if (qm->abnormal_fix) { @@ -789,12 +789,12 @@ static irqreturn_t qm_abnormal_irq(int irq, void *data) tmp = readl(qm->io_base + QM_ABNORMAL_INT_STATUS); error_status = qm->msi_mask & tmp; - while (err->msg) { - if (err->int_msk & error_status) - dev_err(dev, "%s [error status=0x%x] found\n", - err->msg, err->int_msk); + for (i = 0; i < ARRAY_SIZE(qm_hw_error); i++) { + err = &qm_hw_error[i]; + if (!(err->int_msk & error_status)) + continue; - err++; + dev_err(dev, "%s [error status=0x%x] found\n", err->msg, err->int_msk); } /* clear err sts */ @@ -1218,8 +1218,10 @@ static int dump_show(struct hisi_qm *qm, void *info, #define BYTE_PER_DW 4 info_buf = kzalloc(info_size, GFP_KERNEL); - if (!info_buf) + if (!info_buf) { + dev_err(dev, "Fail to alloc dump info buf\n"); return -ENOMEM; + } for (i = 0; i < info_size; i++, info_curr++) { if (i % BYTE_PER_DW == 0) @@ -2639,12 +2641,23 @@ static int hisi_qm_memory_init(struct hisi_qm *qm) static int qm_clear_device(struct hisi_qm *qm) { + acpi_handle handle = ACPI_HANDLE(&qm->pdev->dev); u32 val; int ret; if (qm->fun_type == QM_HW_VF) return 0; + if (!handle) { + pci_warn(qm->pdev, "Device does not support reset, return.\n"); + return 0; + } + + if (!acpi_has_method(handle, qm->err_ini.err_info.acpi_rst)) { + pci_warn(qm->pdev, "BIOS has no reset method, return.\n"); + return 0; + } + /* OOO register set and check */ writel(MASTER_GLOBAL_CTRL_SHUTDOWN, qm->io_base + MASTER_GLOBAL_CTRL); @@ -3771,10 +3784,8 @@ static int qm_vf_reset_prepare(struct pci_dev *pdev, ret = hisi_qm_stop(qm, stop_reason); if (ret) { - hisi_qm_set_hw_reset(qm, - QM_RESET_STOP_TX_OFFSET); - hisi_qm_set_hw_reset(qm, - QM_RESET_STOP_RX_OFFSET); + hisi_qm_set_hw_reset(qm, QM_RESET_STOP_TX_OFFSET); + hisi_qm_set_hw_reset(qm, QM_RESET_STOP_RX_OFFSET); atomic_set(&qm->status.flags, QM_STOP); } } -- 2.33.0

2 1

[PATCH OLK-6.6 0/8] Support feature TLBI
by lishusen 16 Jan '24

16 Jan '24

Support feature TLBI Quan Zhou (5): KVM: arm64: Support a new HiSi CPU type KVM: arm64: Probe and configure DVMBM capability on HiSi CPUs KVM: arm64: Add kvm_vcpu_arch::cpus_ptr and pre_cpus_ptr KVM: arm64: Add kvm_arch::dvm_cpumask and dvm_lock KVM: arm64: Implement the capability of DVMBM Yanan Wang (1): KVM: arm64: Only probe Hisi ncsnp feature on Hisi CPUs Zenghui Yu (2): KVM: arm64: Probe Hisi CPU TYPE from ACPI/DTB KVM: arm64: Add support for probing Hisi ncsnp capability .../admin-guide/kernel-parameters.txt | 3 + arch/arm64/configs/openeuler_defconfig | 1 + arch/arm64/include/asm/hisi_cpu_model.h | 21 + arch/arm64/include/asm/kvm_host.h | 16 + arch/arm64/kernel/image-vars.h | 5 + arch/arm64/kvm/Kconfig | 1 + arch/arm64/kvm/Makefile | 1 + arch/arm64/kvm/arm.c | 52 +++ arch/arm64/kvm/hisilicon/Kconfig | 7 + arch/arm64/kvm/hisilicon/Makefile | 2 + arch/arm64/kvm/hisilicon/hisi_virt.c | 389 ++++++++++++++++++ arch/arm64/kvm/hisilicon/hisi_virt.h | 61 +++ arch/arm64/kvm/hyp/pgtable.c | 2 +- 13 files changed, 560 insertions(+), 1 deletion(-) create mode 100644 arch/arm64/include/asm/hisi_cpu_model.h create mode 100644 arch/arm64/kvm/hisilicon/Kconfig create mode 100644 arch/arm64/kvm/hisilicon/Makefile create mode 100644 arch/arm64/kvm/hisilicon/hisi_virt.c create mode 100644 arch/arm64/kvm/hisilicon/hisi_virt.h -- 2.33.0

2 9

[PATCH OLK-6.6 0/8] Support feature TLBI
by lishusen 16 Jan '24

16 Jan '24

Support feature TLBI Quan Zhou (5): KVM: arm64: Support a new HiSi CPU type KVM: arm64: Probe and configure DVMBM capability on HiSi CPUs KVM: arm64: Add kvm_vcpu_arch::cpus_ptr and pre_cpus_ptr KVM: arm64: Add kvm_arch::dvm_cpumask and dvm_lock KVM: arm64: Implement the capability of DVMBM Yanan Wang (1): KVM: arm64: Only probe Hisi ncsnp feature on Hisi CPUs Zenghui Yu (2): KVM: arm64: Probe Hisi CPU TYPE from ACPI/DTB KVM: arm64: Add support for probing Hisi ncsnp capability .../admin-guide/kernel-parameters.txt | 3 + arch/arm64/configs/openeuler_defconfig | 1 + arch/arm64/include/asm/hisi_cpu_model.h | 21 + arch/arm64/include/asm/kvm_host.h | 16 + arch/arm64/kernel/image-vars.h | 5 + arch/arm64/kvm/Kconfig | 1 + arch/arm64/kvm/Makefile | 1 + arch/arm64/kvm/arm.c | 52 +++ arch/arm64/kvm/hisilicon/Kconfig | 7 + arch/arm64/kvm/hisilicon/Makefile | 2 + arch/arm64/kvm/hisilicon/hisi_virt.c | 389 ++++++++++++++++++ arch/arm64/kvm/hisilicon/hisi_virt.h | 61 +++ arch/arm64/kvm/hyp/pgtable.c | 2 +- 13 files changed, 560 insertions(+), 1 deletion(-) create mode 100644 arch/arm64/include/asm/hisi_cpu_model.h create mode 100644 arch/arm64/kvm/hisilicon/Kconfig create mode 100644 arch/arm64/kvm/hisilicon/Makefile create mode 100644 arch/arm64/kvm/hisilicon/hisi_virt.c create mode 100644 arch/arm64/kvm/hisilicon/hisi_virt.h -- 2.33.0

2 9

[PATCH openEuler-1.0-LTS] crypto: hisilicon - replace 'smp_processor_id' with the raw version of the macro
by wangyuan 16 Jan '24

16 Jan '24

driver inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8WJ1D CVE: NA -------------------------------------------------------- smp_processor_id() is unsafe if it's used in a preemption-on critical section. It will cause the calltrace when the preemption-on and sets the CONFIG_DEBUG_PREEMPT. So replace 'smp_processor_id' with the raw version in preemptible to avoid the following calltrace: [ 7538.874350] BUG: using smp_processor_id() in preemptible [00000000] code: af_alg06/8438 [ 7538.874368] caller is debug_smp_processor_id+0x1c/0x28 [ 7538.874373] CPU: 50 PID: 8438 Comm: af_alg06 Kdump: loaded Not tainted 5.10.0.pc+ #18 [ 7538.874377] Call trace: [ 7538.874387] dump_backtrace+0x0/0x210 [ 7538.874389] show_stack+0x2c/0x38 [ 7538.874392] dump_stack+0x110/0x164 [ 7538.874392] dump_stack+0x110/0x164 [ 7538.874394] check_preemption_disabled+0xf4/0x108 [ 7538.874396] debug_smp_processor_id+0x1c/0x28 [ 7538.874406] sec_create_qps+0x24/0xe8 [hisi_sec2] [ 7538.874408] sec_ctx_base_init+0x20/0x4d8 [hisi_sec2] [ 7538.874411] sec_aead_ctx_init+0x68/0x180 [hisi_sec2] Signed-off-by: wangyuan <wangyuan46(a)huawei.com> --- drivers/crypto/hisilicon/hpre/hpre_main.c | 2 +- drivers/crypto/hisilicon/rde/rde_main.c | 2 +- drivers/crypto/hisilicon/sec2/sec_main.c | 2 +- drivers/crypto/hisilicon/zip/zip_main.c | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/crypto/hisilicon/hpre/hpre_main.c b/drivers/crypto/hisilicon/hpre/hpre_main.c index cbe8ea438fd2..d8f5a505472c 100644 --- a/drivers/crypto/hisilicon/hpre/hpre_main.c +++ b/drivers/crypto/hisilicon/hpre/hpre_main.c @@ -226,7 +226,7 @@ MODULE_PARM_DESC(vfs_num, "Number of VFs to enable(1-63), 0(default)"); struct hisi_qp *hpre_create_qp(void) { - int node = cpu_to_node(smp_processor_id()); + int node = cpu_to_node(raw_smp_processor_id()); struct hisi_qp *qp = NULL; int ret; diff --git a/drivers/crypto/hisilicon/rde/rde_main.c b/drivers/crypto/hisilicon/rde/rde_main.c index f2e00ff891db..a47be8f72064 100644 --- a/drivers/crypto/hisilicon/rde/rde_main.c +++ b/drivers/crypto/hisilicon/rde/rde_main.c @@ -218,7 +218,7 @@ MODULE_DEVICE_TABLE(pci, hisi_rde_dev_ids); struct hisi_qp *rde_create_qp(void) { - int node = cpu_to_node(smp_processor_id()); + int node = cpu_to_node(raw_smp_processor_id()); struct hisi_qp *qp; int ret; diff --git a/drivers/crypto/hisilicon/sec2/sec_main.c b/drivers/crypto/hisilicon/sec2/sec_main.c index 0f32dcb69e12..438f0a206a1b 100644 --- a/drivers/crypto/hisilicon/sec2/sec_main.c +++ b/drivers/crypto/hisilicon/sec2/sec_main.c @@ -189,7 +189,7 @@ void sec_destroy_qps(struct hisi_qp **qps, int qp_num) struct hisi_qp **sec_create_qps(void) { - int node = cpu_to_node(smp_processor_id()); + int node = cpu_to_node(raw_smp_processor_id()); u32 ctx_num = ctx_q_num; struct hisi_qp **qps; int ret; diff --git a/drivers/crypto/hisilicon/zip/zip_main.c b/drivers/crypto/hisilicon/zip/zip_main.c index 1ca51793e26a..e9e4b43acdbf 100644 --- a/drivers/crypto/hisilicon/zip/zip_main.c +++ b/drivers/crypto/hisilicon/zip/zip_main.c @@ -268,7 +268,7 @@ MODULE_DEVICE_TABLE(pci, hisi_zip_dev_ids); int zip_create_qps(struct hisi_qp **qps, int ctx_num) { - int node = cpu_to_node(smp_processor_id()); + int node = cpu_to_node(raw_smp_processor_id()); return hisi_qm_alloc_qps_node(node, &zip_devices, qps, ctx_num, 0); -- 2.33.0

1 0

[PATCH OLK-6.6 0/8] Support feature TLBI
by lishusen 16 Jan '24

16 Jan '24

Support feature TLBI Quan Zhou (5): KVM: arm64: Support a new HiSi CPU type KVM: arm64: Probe and configure DVMBM capability on HiSi CPUs KVM: arm64: Add kvm_vcpu_arch::cpus_ptr and pre_cpus_ptr KVM: arm64: Add kvm_arch::dvm_cpumask and dvm_lock KVM: arm64: Implement the capability of DVMBM Yanan Wang (1): KVM: arm64: Only probe Hisi ncsnp feature on Hisi CPUs Zenghui Yu (2): KVM: arm64: Probe Hisi CPU TYPE from ACPI/DTB KVM: arm64: Add support for probing Hisi ncsnp capability .../admin-guide/kernel-parameters.txt | 3 + arch/arm64/configs/openeuler_defconfig | 1 + arch/arm64/include/asm/kvm_host.h | 16 + arch/arm64/kernel/image-vars.h | 5 + arch/arm64/kvm/Kconfig | 1 + arch/arm64/kvm/Makefile | 1 + arch/arm64/kvm/arm.c | 52 +++ arch/arm64/kvm/hisilicon/Kconfig | 7 + arch/arm64/kvm/hisilicon/Makefile | 2 + arch/arm64/kvm/hisilicon/hisi_virt.c | 389 ++++++++++++++++++ arch/arm64/kvm/hisilicon/hisi_virt.h | 61 +++ arch/arm64/kvm/hyp/pgtable.c | 2 +- 12 files changed, 539 insertions(+), 1 deletion(-) create mode 100644 arch/arm64/kvm/hisilicon/Kconfig create mode 100644 arch/arm64/kvm/hisilicon/Makefile create mode 100644 arch/arm64/kvm/hisilicon/hisi_virt.c create mode 100644 arch/arm64/kvm/hisilicon/hisi_virt.h -- 2.33.0

2 9

[PATCH OLK-6.6 0/2] Support feature TWED
by lishusen 16 Jan '24

16 Jan '24

Support feature TWED Jingyi Wang (1): KVM: arm64: Make use of TWED feature Zengruan Ye (1): arm64: cpufeature: TWED support detection arch/arm64/Kconfig | 10 ++++++++++ arch/arm64/include/asm/kvm_arm.h | 8 ++++++++ arch/arm64/include/asm/kvm_emulate.h | 27 +++++++++++++++++++++++++++ arch/arm64/include/asm/kvm_host.h | 8 ++++++++ arch/arm64/include/asm/virt.h | 5 +++++ arch/arm64/kernel/cpufeature.c | 12 ++++++++++++ arch/arm64/kvm/arm.c | 15 +++++++++++++++ arch/arm64/tools/cpucaps | 1 + 8 files changed, 86 insertions(+) -- 2.33.0

2 3

[PATCH OLK-5.10] netfilter: nf_tables: Reject tables of unsupported family
by Liu Jian 16 Jan '24

16 Jan '24

From: Phil Sutter <phil(a)nwl.cc> mainline inclusion from mainline-v5.18-rc1 commit f1082dd31fe461d482d69da2a8eccfeb7bf07ac2 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I8VPKT CVE: CVE-2023-6040 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… --------------------------- An nftables family is merely a hollow container, its family just a number and such not reliant on compile-time options other than nftables support itself. Add an artificial check so attempts at using a family the kernel can't support fail as early as possible. This helps user space detect kernels which lack e.g. NFPROTO_INET. Signed-off-by: Phil Sutter <phil(a)nwl.cc> Signed-off-by: Pablo Neira Ayuso <pablo(a)netfilter.org> Signed-off-by: Liu Jian <liujian56(a)huawei.com> Conflicts: net/netfilter/nf_tables_api.c --- net/netfilter/nf_tables_api.c | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 3be68ec4f3d9..208b77e374e4 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1151,6 +1151,30 @@ static int nft_objname_hash_cmp(struct rhashtable_compare_arg *arg, return strcmp(obj->key.name, k->name); } +static bool nft_supported_family(u8 family) +{ + return false +#ifdef CONFIG_NF_TABLES_INET + || family == NFPROTO_INET +#endif +#ifdef CONFIG_NF_TABLES_IPV4 + || family == NFPROTO_IPV4 +#endif +#ifdef CONFIG_NF_TABLES_ARP + || family == NFPROTO_ARP +#endif +#ifdef CONFIG_NF_TABLES_NETDEV + || family == NFPROTO_NETDEV +#endif +#if IS_ENABLED(CONFIG_NF_TABLES_BRIDGE) + || family == NFPROTO_BRIDGE +#endif +#ifdef CONFIG_NF_TABLES_IPV6 + || family == NFPROTO_IPV6 +#endif + ; +} + static int nf_tables_newtable(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[], @@ -1166,6 +1190,9 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk, u32 flags = 0; int err; + if (!nft_supported_family(family)) + return -EOPNOTSUPP; + lockdep_assert_held(&nft_net->commit_mutex); attr = nla[NFTA_TABLE_NAME]; table = nft_table_lookup(net, attr, family, genmask); -- 2.34.1

2 1

[PATCH openEuler-1.0-LTS] netfilter: nf_tables: Reject tables of unsupported family
by Liu Jian 16 Jan '24

16 Jan '24

From: Phil Sutter <phil(a)nwl.cc> mainline inclusion from mainline-v5.18-rc1 commit f1082dd31fe461d482d69da2a8eccfeb7bf07ac2 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I8VPKT CVE: CVE-2023-6040 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… --------------------------- An nftables family is merely a hollow container, its family just a number and such not reliant on compile-time options other than nftables support itself. Add an artificial check so attempts at using a family the kernel can't support fail as early as possible. This helps user space detect kernels which lack e.g. NFPROTO_INET. Signed-off-by: Phil Sutter <phil(a)nwl.cc> Signed-off-by: Pablo Neira Ayuso <pablo(a)netfilter.org> Signed-off-by: Liu Jian <liujian56(a)huawei.com> Conflicts: net/netfilter/nf_tables_api.c --- net/netfilter/nf_tables_api.c | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index c3fedbfd0ee2..e07c497e7344 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -853,6 +853,30 @@ static int nft_chain_hash_cmp(struct rhashtable_compare_arg *arg, return strcmp(chain->name, name); } +static bool nft_supported_family(u8 family) +{ + return false +#ifdef CONFIG_NF_TABLES_INET + || family == NFPROTO_INET +#endif +#ifdef CONFIG_NF_TABLES_IPV4 + || family == NFPROTO_IPV4 +#endif +#ifdef CONFIG_NF_TABLES_ARP + || family == NFPROTO_ARP +#endif +#ifdef CONFIG_NF_TABLES_NETDEV + || family == NFPROTO_NETDEV +#endif +#if IS_ENABLED(CONFIG_NF_TABLES_BRIDGE) + || family == NFPROTO_BRIDGE +#endif +#ifdef CONFIG_NF_TABLES_IPV6 + || family == NFPROTO_IPV6 +#endif + ; +} + static int nf_tables_newtable(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[], @@ -867,6 +891,9 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk, struct nft_ctx ctx; int err; + if (!nft_supported_family(family)) + return -EOPNOTSUPP; + lockdep_assert_held(&net->nft.commit_mutex); attr = nla[NFTA_TABLE_NAME]; table = nft_table_lookup(net, attr, family, genmask); -- 2.34.1

2 1