- Kernel - mailweb.openeuler.org

[PATCH openEuler-22.03-LTS-SP2] netfilter: nf_tables: disallow rule removal from chain binding
by Ziyang Xuan 11 Oct '23

11 Oct '23

From: Pablo Neira Ayuso <pablo(a)netfilter.org> mainline inclusion from mainline-v6.6-rc3 commit f15f29fd4779be8a418b66e9d52979bb6d6c2325 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I84NFY CVE: CVE-2023-5197 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… --------------------------- Chain binding only requires the rule addition/insertion command within the same transaction. Removal of rules from chain bindings within the same transaction makes no sense, userspace does not utilize this feature. Replace nft_chain_is_bound() check to nft_chain_binding() in rule deletion commands. Replace command implies a rule deletion, reject this command too. Rule flush command can also safely rely on this nft_chain_binding() check because unbound chains are not allowed since 62e1e94b246e ("netfilter: nf_tables: reject unbound chain set before commit phase"). Fixes: d0e2c7de92c7 ("netfilter: nf_tables: add NFT_CHAIN_BINDING") Reported-by: Kevin Rich <kevinrich1337(a)gmail.com> Signed-off-by: Pablo Neira Ayuso <pablo(a)netfilter.org> Conflicts: net/netfilter/nf_tables_api.c Signed-off-by: Ziyang Xuan <william.xuanziyang(a)huawei.com> --- net/netfilter/nf_tables_api.c | 19 +++++++++++++++---- 1 file changed, 15 insertions(+), 4 deletions(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 4ac499c6ef47..121ad5981520 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1250,7 +1250,7 @@ static int nft_flush_table(struct nft_ctx *ctx) if (!nft_is_active_next(ctx->net, chain)) continue; - if (nft_chain_is_bound(chain)) + if (nft_chain_binding(chain)) continue; ctx->chain = chain; @@ -1295,7 +1295,7 @@ static int nft_flush_table(struct nft_ctx *ctx) if (!nft_is_active_next(ctx->net, chain)) continue; - if (nft_chain_is_bound(chain)) + if (nft_chain_binding(chain)) continue; ctx->chain = chain; @@ -2579,6 +2579,9 @@ static int nf_tables_delchain(struct net *net, struct sock *nlsk, return PTR_ERR(chain); } + if (nft_chain_binding(chain)) + return -EOPNOTSUPP; + if (nlh->nlmsg_flags & NLM_F_NONREC && chain->use > 0) return -EBUSY; @@ -3474,6 +3477,11 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, } if (nlh->nlmsg_flags & NLM_F_REPLACE) { + if (nft_chain_binding(chain)) { + err = -EOPNOTSUPP; + goto err2; + } + trans = nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule); if (trans == NULL) { err = -ENOMEM; @@ -3580,7 +3588,7 @@ static int nf_tables_delrule(struct net *net, struct sock *nlsk, NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_CHAIN]); return PTR_ERR(chain); } - if (nft_chain_is_bound(chain)) + if (nft_chain_binding(chain)) return -EOPNOTSUPP; } @@ -3610,7 +3618,7 @@ static int nf_tables_delrule(struct net *net, struct sock *nlsk, list_for_each_entry(chain, &table->chains, list) { if (!nft_is_active_next(net, chain)) continue; - if (nft_chain_is_bound(chain)) + if (nft_chain_binding(chain)) continue; ctx.chain = chain; @@ -9194,6 +9202,9 @@ static void __nft_release_table(struct net *net, struct nft_table *table) ctx.family = table->family; ctx.table = table; list_for_each_entry(chain, &table->chains, list) { + if (nft_chain_binding(chain)) + continue; + ctx.chain = chain; list_for_each_entry_safe(rule, nr, &chain->rules, list) { list_del(&rule->list); -- 2.25.1

2 1

[PATCH openEuler-22.03-LTS-SP1] netfilter: nf_tables: disallow rule removal from chain binding
by Ziyang Xuan 11 Oct '23

11 Oct '23

From: Pablo Neira Ayuso <pablo(a)netfilter.org> mainline inclusion from mainline-v6.6-rc3 commit f15f29fd4779be8a418b66e9d52979bb6d6c2325 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I84NFY CVE: CVE-2023-5197 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… --------------------------- Chain binding only requires the rule addition/insertion command within the same transaction. Removal of rules from chain bindings within the same transaction makes no sense, userspace does not utilize this feature. Replace nft_chain_is_bound() check to nft_chain_binding() in rule deletion commands. Replace command implies a rule deletion, reject this command too. Rule flush command can also safely rely on this nft_chain_binding() check because unbound chains are not allowed since 62e1e94b246e ("netfilter: nf_tables: reject unbound chain set before commit phase"). Fixes: d0e2c7de92c7 ("netfilter: nf_tables: add NFT_CHAIN_BINDING") Reported-by: Kevin Rich <kevinrich1337(a)gmail.com> Signed-off-by: Pablo Neira Ayuso <pablo(a)netfilter.org> Conflicts: net/netfilter/nf_tables_api.c Signed-off-by: Ziyang Xuan <william.xuanziyang(a)huawei.com> --- net/netfilter/nf_tables_api.c | 19 +++++++++++++++---- 1 file changed, 15 insertions(+), 4 deletions(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 74394c865105..b2d5e1dda99a 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1250,7 +1250,7 @@ static int nft_flush_table(struct nft_ctx *ctx) if (!nft_is_active_next(ctx->net, chain)) continue; - if (nft_chain_is_bound(chain)) + if (nft_chain_binding(chain)) continue; ctx->chain = chain; @@ -1295,7 +1295,7 @@ static int nft_flush_table(struct nft_ctx *ctx) if (!nft_is_active_next(ctx->net, chain)) continue; - if (nft_chain_is_bound(chain)) + if (nft_chain_binding(chain)) continue; ctx->chain = chain; @@ -2579,6 +2579,9 @@ static int nf_tables_delchain(struct net *net, struct sock *nlsk, return PTR_ERR(chain); } + if (nft_chain_binding(chain)) + return -EOPNOTSUPP; + if (nlh->nlmsg_flags & NLM_F_NONREC && chain->use > 0) return -EBUSY; @@ -3474,6 +3477,11 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, } if (nlh->nlmsg_flags & NLM_F_REPLACE) { + if (nft_chain_binding(chain)) { + err = -EOPNOTSUPP; + goto err2; + } + trans = nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule); if (trans == NULL) { err = -ENOMEM; @@ -3580,7 +3588,7 @@ static int nf_tables_delrule(struct net *net, struct sock *nlsk, NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_CHAIN]); return PTR_ERR(chain); } - if (nft_chain_is_bound(chain)) + if (nft_chain_binding(chain)) return -EOPNOTSUPP; } @@ -3610,7 +3618,7 @@ static int nf_tables_delrule(struct net *net, struct sock *nlsk, list_for_each_entry(chain, &table->chains, list) { if (!nft_is_active_next(net, chain)) continue; - if (nft_chain_is_bound(chain)) + if (nft_chain_binding(chain)) continue; ctx.chain = chain; @@ -9194,6 +9202,9 @@ static void __nft_release_table(struct net *net, struct nft_table *table) ctx.family = table->family; ctx.table = table; list_for_each_entry(chain, &table->chains, list) { + if (nft_chain_binding(chain)) + continue; + ctx.chain = chain; list_for_each_entry_safe(rule, nr, &chain->rules, list) { list_del(&rule->list); -- 2.25.1

2 1

[PATCH openEuler-22.03-LTS] netfilter: nf_tables: disallow rule removal from chain binding
by Ziyang Xuan 11 Oct '23

11 Oct '23

From: Pablo Neira Ayuso <pablo(a)netfilter.org> mainline inclusion from mainline-v6.6-rc3 commit f15f29fd4779be8a418b66e9d52979bb6d6c2325 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I84NFY CVE: CVE-2023-5197 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… --------------------------- Chain binding only requires the rule addition/insertion command within the same transaction. Removal of rules from chain bindings within the same transaction makes no sense, userspace does not utilize this feature. Replace nft_chain_is_bound() check to nft_chain_binding() in rule deletion commands. Replace command implies a rule deletion, reject this command too. Rule flush command can also safely rely on this nft_chain_binding() check because unbound chains are not allowed since 62e1e94b246e ("netfilter: nf_tables: reject unbound chain set before commit phase"). Fixes: d0e2c7de92c7 ("netfilter: nf_tables: add NFT_CHAIN_BINDING") Reported-by: Kevin Rich <kevinrich1337(a)gmail.com> Signed-off-by: Pablo Neira Ayuso <pablo(a)netfilter.org> Conflicts: net/netfilter/nf_tables_api.c Signed-off-by: Ziyang Xuan <william.xuanziyang(a)huawei.com> --- net/netfilter/nf_tables_api.c | 19 +++++++++++++++---- 1 file changed, 15 insertions(+), 4 deletions(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index b0bf9342b2e5..c6507d52b4eb 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1250,7 +1250,7 @@ static int nft_flush_table(struct nft_ctx *ctx) if (!nft_is_active_next(ctx->net, chain)) continue; - if (nft_chain_is_bound(chain)) + if (nft_chain_binding(chain)) continue; ctx->chain = chain; @@ -1295,7 +1295,7 @@ static int nft_flush_table(struct nft_ctx *ctx) if (!nft_is_active_next(ctx->net, chain)) continue; - if (nft_chain_is_bound(chain)) + if (nft_chain_binding(chain)) continue; ctx->chain = chain; @@ -2577,6 +2577,9 @@ static int nf_tables_delchain(struct net *net, struct sock *nlsk, return PTR_ERR(chain); } + if (nft_chain_binding(chain)) + return -EOPNOTSUPP; + if (nlh->nlmsg_flags & NLM_F_NONREC && chain->use > 0) return -EBUSY; @@ -3472,6 +3475,11 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, } if (nlh->nlmsg_flags & NLM_F_REPLACE) { + if (nft_chain_binding(chain)) { + err = -EOPNOTSUPP; + goto err2; + } + trans = nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule); if (trans == NULL) { err = -ENOMEM; @@ -3578,7 +3586,7 @@ static int nf_tables_delrule(struct net *net, struct sock *nlsk, NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_CHAIN]); return PTR_ERR(chain); } - if (nft_chain_is_bound(chain)) + if (nft_chain_binding(chain)) return -EOPNOTSUPP; } @@ -3608,7 +3616,7 @@ static int nf_tables_delrule(struct net *net, struct sock *nlsk, list_for_each_entry(chain, &table->chains, list) { if (!nft_is_active_next(net, chain)) continue; - if (nft_chain_is_bound(chain)) + if (nft_chain_binding(chain)) continue; ctx.chain = chain; @@ -9192,6 +9200,9 @@ static void __nft_release_table(struct net *net, struct nft_table *table) ctx.family = table->family; ctx.table = table; list_for_each_entry(chain, &table->chains, list) { + if (nft_chain_binding(chain)) + continue; + ctx.chain = chain; list_for_each_entry_safe(rule, nr, &chain->rules, list) { list_del(&rule->list); -- 2.25.1

2 1

[PATCH openEuler-22.03-LTS 00/19] nf_table LTS
by Lu Wei 11 Oct '23

11 Oct '23

Florian Westphal (1): netfilter: nf_tables: use net_generic infra for transaction data Lu Wei (7): Revert "netfilter: nf_tables: unbind non-anonymous set if rule construction fails" Revert "netfilter: nf_tables: skip immediate deactivate in _PREPARE_ERROR" Revert "netfilter: nf_tables: add NFT_TRANS_PREPARE_ERROR to deal with bound set/chain" Revert "netfilter: nf_tables: fix chain binding transaction logic" Revert "netfilter: nf_tables: incorrect error path handling with NFT_MSG_NEWRULE" Revert "netfilter: nf_tables: skip bound chain on rule flush" Revert "netfilter: nf_tables: disallow rule addition to bound chain via NFTA_RULE_CHAIN_ID" Pablo Neira Ayuso (11): netfilter: nf_tables: incorrect error path handling with NFT_MSG_NEWRULE netfilter: nf_tables: fix chain binding transaction logic netfilter: nf_tables: add NFT_TRANS_PREPARE_ERROR to deal with bound set/chain netfilter: nf_tables: reject unbound anonymous set before commit phase netfilter: nf_tables: reject unbound chain set before commit phase netfilter: nftables: rename set element data activation/deactivation functions netfilter: nf_tables: drop map element references from preparation phase netfilter: nf_tables: unbind non-anonymous set if rule construction fails netfilter: nf_tables: skip immediate deactivate in _PREPARE_ERROR netfilter: nf_tables: skip bound chain on rule flush netfilter: nf_tables: disallow rule addition to bound chain via NFTA_RULE_CHAIN_ID include/net/netfilter/nf_tables.h | 18 +- include/net/netns/nftables.h | 14 +- net/netfilter/nf_tables_api.c | 534 +++++++++++++++++++++--------- net/netfilter/nf_tables_offload.c | 30 +- net/netfilter/nft_chain_filter.c | 11 +- net/netfilter/nft_dynset.c | 6 +- net/netfilter/nft_set_bitmap.c | 5 +- net/netfilter/nft_set_hash.c | 23 +- net/netfilter/nft_set_pipapo.c | 14 +- net/netfilter/nft_set_rbtree.c | 5 +- 10 files changed, 458 insertions(+), 202 deletions(-) -- 2.34.1

2 20

[PATCH v3 OLK-5.10 00/19] Introduce PBHA and PBHA bit0 to control the usage of HBM Cache precisely
by Wupeng Ma 11 Oct '23

11 Oct '23

From: Ma Wupeng <mawupeng1(a)huawei.com> Patch 1: move FDT init out of kaslr_early_init for future use. Patch 2 to 8: enable feature PBHA for arm64. Patch 9-18: Control the usage of HBM cache for kernel and task precisely. Patch 19: Enable feature PBHA for arm64 by default. Changelog since v2: - correct the error Documentation in patch #18 Changelog since v1: - fix kabi broken due to include files James Morse (7): KVM: arm64: Detect and enable PBHA for stage2 dt-bindings: Rename the description of cpu nodes cpu.yaml dt-bindings: arm: Add binding for Page Based Hardware Attributes arm64: cpufeature: Enable PBHA bits for stage1 arm64: mm: Add pgprot_pbha() to allow drivers to request PBHA values KVM: arm64: Configure PBHA bits for stage2 Documentation: arm64: Describe the support and expectations for PBHA Ma Wupeng (11): arm64: cpufeature: Enable PBHA for stage1 early via FDT arm64: mm: Detect and enable PBHA bit0 at early startup arm64: mm: Update kernel pte entries if pbha bit0 enabled arm64: mm: Show PBHA bit 59 as PBHA0 in ptdump arm64: mm: Introduce VM_PBHA_BIT0 to enable pbha bit0 for single vma arm64: mm: Set PBHA0 bit for VM_PBHA_BIT0 arm64: mm: Introduce sysfs interface to bypass whole task arm64: mm: Set flag VM_PBHA_BIT0 for global init task arm64: mm: Introduce prctl to control pbha behavior arm64: mm: Introduce kernel param pbha openeuler: configs: arm64: Enable PBHA by default Marc Zyngier (1): arm64: Extract early FDT mapping from kaslr_early_init() .../admin-guide/kernel-parameters.txt | 8 + Documentation/arm64/index.rst | 1 + Documentation/arm64/pbha.rst | 85 +++ .../devicetree/bindings/arm/cpu.yaml | 537 ++++++++++++++++ .../devicetree/bindings/arm/cpus.yaml | 584 +++--------------- arch/arm64/Kconfig | 20 + arch/arm64/configs/openeuler_defconfig | 1 + arch/arm64/include/asm/cpucaps.h | 3 + arch/arm64/include/asm/cpufeature.h | 15 + arch/arm64/include/asm/kvm_arm.h | 1 + arch/arm64/include/asm/kvm_pgtable.h | 9 + arch/arm64/include/asm/mman.h | 10 + arch/arm64/include/asm/pgtable-hwdef.h | 6 + arch/arm64/include/asm/pgtable.h | 26 + arch/arm64/include/asm/setup.h | 3 + arch/arm64/include/uapi/asm/mman.h | 1 + arch/arm64/kernel/cpufeature.c | 258 ++++++++ arch/arm64/kernel/head.S | 6 +- arch/arm64/kernel/image-vars.h | 3 + arch/arm64/kernel/kaslr.c | 7 +- arch/arm64/kernel/setup.c | 15 + arch/arm64/kvm/reset.c | 15 +- arch/arm64/mm/hugetlbpage.c | 2 + arch/arm64/mm/mmu.c | 14 +- arch/arm64/mm/ptdump.c | 5 + .../firmware/efi/libstub/efi-stub-helper.c | 3 + drivers/firmware/efi/libstub/fdt.c | 57 ++ drivers/soc/hisilicon/Makefile | 1 + drivers/soc/hisilicon/pbha.c | 204 ++++++ fs/proc/base.c | 103 +++ fs/proc/task_mmu.c | 3 + include/linux/mm.h | 8 +- include/linux/pbha.h | 66 ++ include/uapi/asm-generic/mman-common.h | 1 + include/uapi/linux/prctl.h | 2 + kernel/sys.c | 10 + mm/memory.c | 4 + mm/vmalloc.c | 5 + 38 files changed, 1579 insertions(+), 523 deletions(-) create mode 100644 Documentation/arm64/pbha.rst create mode 100644 Documentation/devicetree/bindings/arm/cpu.yaml create mode 100644 drivers/soc/hisilicon/pbha.c create mode 100644 include/linux/pbha.h -- 2.25.1

2 20

[PATCH] RDMA/core: fix kabi compatibility for SRQ resource tracing
by Chengchang Tang 11 Oct '23

11 Oct '23

From: wenglianfa <wenglianfa(a)huawei.com> In the patch related to SRQ resource tracing, members are added to the structure, which causes Kapi incompatibility. To solve this problem, perform the following operations: First, make sure that the data structure of the new member has little impact and the risk is controllable, then Use the __GENKSYMS__ macro to shield the new structure members and place the new members at the end of the data structure. Fixes: d7b7ce53b3be ("RDMA/hns: Support SRQ restrack ops for hns driver") Fixes: 788310f83ffc ("RDMA/core: Add support to dump SRQ resource in RAW format") Fixes: 31cc28f1894f ("RDMA/core: Add dedicated SRQ resource tracker function") Fixes: f54d69b7874e ("RDMA/nldev: Add QP numbers to SRQ information") Fixes: 6102284160fd ("RDMA/nldev: Return SRQ information") Fixes: 4e38b5a1267f ("RDMA/restrack: Add support to get resource tracking for SRQ") Fixes: 0c32db26a6c4 ("RDMA/nldev: Return context information") Signed-off-by: wenglianfa <wenglianfa(a)huawei.com> --- include/rdma/ib_verbs.h | 9 +++++++-- include/rdma/restrack.h | 2 ++ include/uapi/rdma/rdma_netlink.h | 4 ++++ 3 files changed, 13 insertions(+), 2 deletions(-) diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index fc32b16d5bb3..db46f3150b99 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -1608,10 +1608,12 @@ struct ib_srq { }; } ext; +#ifndef __GENKSYMS__ /* * Implementation details of the RDMA core, don't use in drivers: */ struct rdma_restrack_entry res; +#endif }; enum ib_raw_packet_caps { @@ -2548,8 +2550,6 @@ struct ib_device_ops { int (*fill_res_qp_entry)(struct sk_buff *msg, struct ib_qp *ibqp); int (*fill_res_qp_entry_raw)(struct sk_buff *msg, struct ib_qp *ibqp); int (*fill_res_cm_id_entry)(struct sk_buff *msg, struct rdma_cm_id *id); - int (*fill_res_srq_entry)(struct sk_buff *msg, struct ib_srq *ib_srq); - int (*fill_res_srq_entry_raw)(struct sk_buff *msg, struct ib_srq *ib_srq); /* Device lifecycle callbacks */ /* @@ -2619,6 +2619,11 @@ struct ib_device_ops { DECLARE_RDMA_OBJ_SIZE(ib_srq); DECLARE_RDMA_OBJ_SIZE(ib_ucontext); DECLARE_RDMA_OBJ_SIZE(ib_xrcd); + +#ifndef __GENKSYMS__ + int (*fill_res_srq_entry)(struct sk_buff *msg, struct ib_srq *ib_srq); + int (*fill_res_srq_entry_raw)(struct sk_buff *msg, struct ib_srq *ib_srq); +#endif }; struct ib_core_device { diff --git a/include/rdma/restrack.h b/include/rdma/restrack.h index bdfb6fce0bed..57fca78afc47 100644 --- a/include/rdma/restrack.h +++ b/include/rdma/restrack.h @@ -49,10 +49,12 @@ enum rdma_restrack_type { * @RDMA_RESTRACK_COUNTER: Statistic Counter */ RDMA_RESTRACK_COUNTER, +#ifndef __GENKSYMS__ /** * @RDMA_RESTRACK_SRQ: Shared receive queue (SRQ) */ RDMA_RESTRACK_SRQ, +#endif /** * @RDMA_RESTRACK_MAX: Last entry, used for array dclarations */ diff --git a/include/uapi/rdma/rdma_netlink.h b/include/uapi/rdma/rdma_netlink.h index 05392cd8e627..5ab830103e32 100644 --- a/include/uapi/rdma/rdma_netlink.h +++ b/include/uapi/rdma/rdma_netlink.h @@ -293,11 +293,13 @@ enum rdma_nldev_command { RDMA_NLDEV_CMD_RES_MR_GET_RAW, +#ifndef __GENKSYMS__ RDMA_NLDEV_CMD_RES_CTX_GET, /* can dump */ RDMA_NLDEV_CMD_RES_SRQ_GET, /* can dump */ RDMA_NLDEV_CMD_RES_SRQ_GET_RAW, +#endif RDMA_NLDEV_NUM_OPS }; @@ -539,6 +541,7 @@ enum rdma_nldev_attr { RDMA_NLDEV_ATTR_RES_RAW, /* binary */ +#ifndef __GENKSYMS__ RDMA_NLDEV_ATTR_RES_CTX, /* nested table */ RDMA_NLDEV_ATTR_RES_CTX_ENTRY, /* nested table */ @@ -548,6 +551,7 @@ enum rdma_nldev_attr { RDMA_NLDEV_ATTR_MIN_RANGE, /* u32 */ RDMA_NLDEV_ATTR_MAX_RANGE, /* u32 */ +#endif /* * Always the end */ -- 2.33.0

1 0

[PATCH openEuler-22.03-LTS-SP2 00/19] nf_table LTS
by Lu Wei 11 Oct '23

11 Oct '23

Florian Westphal (1): netfilter: nf_tables: use net_generic infra for transaction data Lu Wei (7): Revert "netfilter: nf_tables: unbind non-anonymous set if rule construction fails" Revert "netfilter: nf_tables: skip immediate deactivate in _PREPARE_ERROR" Revert "netfilter: nf_tables: add NFT_TRANS_PREPARE_ERROR to deal with bound set/chain" Revert "netfilter: nf_tables: fix chain binding transaction logic" Revert "netfilter: nf_tables: incorrect error path handling with NFT_MSG_NEWRULE" Revert "netfilter: nf_tables: skip bound chain on rule flush" Revert "netfilter: nf_tables: disallow rule addition to bound chain via NFTA_RULE_CHAIN_ID" Pablo Neira Ayuso (11): netfilter: nf_tables: incorrect error path handling with NFT_MSG_NEWRULE netfilter: nf_tables: fix chain binding transaction logic netfilter: nf_tables: add NFT_TRANS_PREPARE_ERROR to deal with bound set/chain netfilter: nf_tables: reject unbound anonymous set before commit phase netfilter: nf_tables: reject unbound chain set before commit phase netfilter: nftables: rename set element data activation/deactivation functions netfilter: nf_tables: drop map element references from preparation phase netfilter: nf_tables: unbind non-anonymous set if rule construction fails netfilter: nf_tables: skip immediate deactivate in _PREPARE_ERROR netfilter: nf_tables: skip bound chain on rule flush netfilter: nf_tables: disallow rule addition to bound chain via NFTA_RULE_CHAIN_ID include/net/netfilter/nf_tables.h | 18 +- include/net/netns/nftables.h | 14 +- net/netfilter/nf_tables_api.c | 534 +++++++++++++++++++++--------- net/netfilter/nf_tables_offload.c | 30 +- net/netfilter/nft_chain_filter.c | 11 +- net/netfilter/nft_dynset.c | 6 +- net/netfilter/nft_set_bitmap.c | 5 +- net/netfilter/nft_set_hash.c | 23 +- net/netfilter/nft_set_pipapo.c | 14 +- net/netfilter/nft_set_rbtree.c | 5 +- 10 files changed, 458 insertions(+), 202 deletions(-) -- 2.34.1

2 20

[PATCH openEuler-22.03-LTS-SP1 00/19] nf_table LTS
by Lu Wei 11 Oct '23

11 Oct '23

Florian Westphal (1): netfilter: nf_tables: use net_generic infra for transaction data Lu Wei (7): Revert "netfilter: nf_tables: unbind non-anonymous set if rule construction fails" Revert "netfilter: nf_tables: skip immediate deactivate in _PREPARE_ERROR" Revert "netfilter: nf_tables: add NFT_TRANS_PREPARE_ERROR to deal with bound set/chain" Revert "netfilter: nf_tables: fix chain binding transaction logic" Revert "netfilter: nf_tables: incorrect error path handling with NFT_MSG_NEWRULE" Revert "netfilter: nf_tables: skip bound chain on rule flush" Revert "netfilter: nf_tables: disallow rule addition to bound chain via NFTA_RULE_CHAIN_ID" Pablo Neira Ayuso (11): netfilter: nf_tables: incorrect error path handling with NFT_MSG_NEWRULE netfilter: nf_tables: fix chain binding transaction logic netfilter: nf_tables: add NFT_TRANS_PREPARE_ERROR to deal with bound set/chain netfilter: nf_tables: reject unbound anonymous set before commit phase netfilter: nf_tables: reject unbound chain set before commit phase netfilter: nftables: rename set element data activation/deactivation functions netfilter: nf_tables: drop map element references from preparation phase netfilter: nf_tables: unbind non-anonymous set if rule construction fails netfilter: nf_tables: skip immediate deactivate in _PREPARE_ERROR netfilter: nf_tables: skip bound chain on rule flush netfilter: nf_tables: disallow rule addition to bound chain via NFTA_RULE_CHAIN_ID include/net/netfilter/nf_tables.h | 18 +- include/net/netns/nftables.h | 14 +- net/netfilter/nf_tables_api.c | 534 +++++++++++++++++++++--------- net/netfilter/nf_tables_offload.c | 30 +- net/netfilter/nft_chain_filter.c | 11 +- net/netfilter/nft_dynset.c | 6 +- net/netfilter/nft_set_bitmap.c | 5 +- net/netfilter/nft_set_hash.c | 23 +- net/netfilter/nft_set_pipapo.c | 14 +- net/netfilter/nft_set_rbtree.c | 5 +- 10 files changed, 458 insertions(+), 202 deletions(-) -- 2.34.1

2 20

[PATCH openEuler-22.03-LTS 00/19] nf_table LTS
by Lu Wei 11 Oct '23

11 Oct '23

Florian Westphal (1): netfilter: nf_tables: use net_generic infra for transaction data Lu Wei (7): Revert "netfilter: nf_tables: unbind non-anonymous set if rule construction fails" Revert "netfilter: nf_tables: skip immediate deactivate in _PREPARE_ERROR" Revert "netfilter: nf_tables: add NFT_TRANS_PREPARE_ERROR to deal with bound set/chain" Revert "netfilter: nf_tables: fix chain binding transaction logic" Revert "netfilter: nf_tables: incorrect error path handling with NFT_MSG_NEWRULE" Revert "netfilter: nf_tables: skip bound chain on rule flush" Revert "netfilter: nf_tables: disallow rule addition to bound chain via NFTA_RULE_CHAIN_ID" Pablo Neira Ayuso (11): netfilter: nf_tables: incorrect error path handling with NFT_MSG_NEWRULE netfilter: nf_tables: fix chain binding transaction logic netfilter: nf_tables: add NFT_TRANS_PREPARE_ERROR to deal with bound set/chain netfilter: nf_tables: reject unbound anonymous set before commit phase netfilter: nf_tables: reject unbound chain set before commit phase netfilter: nftables: rename set element data activation/deactivation functions netfilter: nf_tables: drop map element references from preparation phase netfilter: nf_tables: unbind non-anonymous set if rule construction fails netfilter: nf_tables: skip immediate deactivate in _PREPARE_ERROR netfilter: nf_tables: skip bound chain on rule flush netfilter: nf_tables: disallow rule addition to bound chain via NFTA_RULE_CHAIN_ID include/net/netfilter/nf_tables.h | 18 +- include/net/netns/nftables.h | 14 +- net/netfilter/nf_tables_api.c | 534 +++++++++++++++++++++--------- net/netfilter/nf_tables_offload.c | 30 +- net/netfilter/nft_chain_filter.c | 11 +- net/netfilter/nft_dynset.c | 6 +- net/netfilter/nft_set_bitmap.c | 5 +- net/netfilter/nft_set_hash.c | 23 +- net/netfilter/nft_set_pipapo.c | 14 +- net/netfilter/nft_set_rbtree.c | 5 +- 10 files changed, 458 insertions(+), 202 deletions(-) -- 2.34.1

1 19

[PATCH OLK-5.10] netfilter: nf_tables: disallow rule removal from chain binding
by Ziyang Xuan 10 Oct '23

10 Oct '23

From: Pablo Neira Ayuso <pablo(a)netfilter.org> mainline inclusion from mainline-v6.6-rc3 commit f15f29fd4779be8a418b66e9d52979bb6d6c2325 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I84NFY CVE: CVE-2023-5197 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… --------------------------- Chain binding only requires the rule addition/insertion command within the same transaction. Removal of rules from chain bindings within the same transaction makes no sense, userspace does not utilize this feature. Replace nft_chain_is_bound() check to nft_chain_binding() in rule deletion commands. Replace command implies a rule deletion, reject this command too. Rule flush command can also safely rely on this nft_chain_binding() check because unbound chains are not allowed since 62e1e94b246e ("netfilter: nf_tables: reject unbound chain set before commit phase"). Fixes: d0e2c7de92c7 ("netfilter: nf_tables: add NFT_CHAIN_BINDING") Reported-by: Kevin Rich <kevinrich1337(a)gmail.com> Signed-off-by: Pablo Neira Ayuso <pablo(a)netfilter.org> Conflicts: net/netfilter/nf_tables_api.c Signed-off-by: Ziyang Xuan <william.xuanziyang(a)huawei.com> --- net/netfilter/nf_tables_api.c | 19 +++++++++++++++---- 1 file changed, 15 insertions(+), 4 deletions(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 4ac499c6ef47..121ad5981520 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1250,7 +1250,7 @@ static int nft_flush_table(struct nft_ctx *ctx) if (!nft_is_active_next(ctx->net, chain)) continue; - if (nft_chain_is_bound(chain)) + if (nft_chain_binding(chain)) continue; ctx->chain = chain; @@ -1295,7 +1295,7 @@ static int nft_flush_table(struct nft_ctx *ctx) if (!nft_is_active_next(ctx->net, chain)) continue; - if (nft_chain_is_bound(chain)) + if (nft_chain_binding(chain)) continue; ctx->chain = chain; @@ -2579,6 +2579,9 @@ static int nf_tables_delchain(struct net *net, struct sock *nlsk, return PTR_ERR(chain); } + if (nft_chain_binding(chain)) + return -EOPNOTSUPP; + if (nlh->nlmsg_flags & NLM_F_NONREC && chain->use > 0) return -EBUSY; @@ -3474,6 +3477,11 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, } if (nlh->nlmsg_flags & NLM_F_REPLACE) { + if (nft_chain_binding(chain)) { + err = -EOPNOTSUPP; + goto err2; + } + trans = nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule); if (trans == NULL) { err = -ENOMEM; @@ -3580,7 +3588,7 @@ static int nf_tables_delrule(struct net *net, struct sock *nlsk, NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_CHAIN]); return PTR_ERR(chain); } - if (nft_chain_is_bound(chain)) + if (nft_chain_binding(chain)) return -EOPNOTSUPP; } @@ -3610,7 +3618,7 @@ static int nf_tables_delrule(struct net *net, struct sock *nlsk, list_for_each_entry(chain, &table->chains, list) { if (!nft_is_active_next(net, chain)) continue; - if (nft_chain_is_bound(chain)) + if (nft_chain_binding(chain)) continue; ctx.chain = chain; @@ -9194,6 +9202,9 @@ static void __nft_release_table(struct net *net, struct nft_table *table) ctx.family = table->family; ctx.table = table; list_for_each_entry(chain, &table->chains, list) { + if (nft_chain_binding(chain)) + continue; + ctx.chain = chain; list_for_each_entry_safe(rule, nr, &chain->rules, list) { list_del(&rule->list); -- 2.25.1

2 1

[PATCH OLK-5.10 00/19] nf_table LTS
by Lu Wei 10 Oct '23

10 Oct '23

Florian Westphal (1): netfilter: nf_tables: use net_generic infra for transaction data Lu Wei (7): Revert "netfilter: nf_tables: unbind non-anonymous set if rule construction fails" Revert "netfilter: nf_tables: skip immediate deactivate in _PREPARE_ERROR" Revert "netfilter: nf_tables: add NFT_TRANS_PREPARE_ERROR to deal with bound set/chain" Revert "netfilter: nf_tables: fix chain binding transaction logic" Revert "netfilter: nf_tables: incorrect error path handling with NFT_MSG_NEWRULE" Revert "netfilter: nf_tables: skip bound chain on rule flush" Revert "netfilter: nf_tables: disallow rule addition to bound chain via NFTA_RULE_CHAIN_ID" Pablo Neira Ayuso (11): netfilter: nf_tables: incorrect error path handling with NFT_MSG_NEWRULE netfilter: nf_tables: fix chain binding transaction logic netfilter: nf_tables: add NFT_TRANS_PREPARE_ERROR to deal with bound set/chain netfilter: nf_tables: reject unbound anonymous set before commit phase netfilter: nf_tables: reject unbound chain set before commit phase netfilter: nftables: rename set element data activation/deactivation functions netfilter: nf_tables: drop map element references from preparation phase netfilter: nf_tables: unbind non-anonymous set if rule construction fails netfilter: nf_tables: skip immediate deactivate in _PREPARE_ERROR netfilter: nf_tables: skip bound chain on rule flush netfilter: nf_tables: disallow rule addition to bound chain via NFTA_RULE_CHAIN_ID include/net/netfilter/nf_tables.h | 18 +- include/net/netns/nftables.h | 14 +- net/netfilter/nf_tables_api.c | 534 +++++++++++++++++++++--------- net/netfilter/nf_tables_offload.c | 30 +- net/netfilter/nft_chain_filter.c | 11 +- net/netfilter/nft_dynset.c | 6 +- net/netfilter/nft_set_bitmap.c | 5 +- net/netfilter/nft_set_hash.c | 23 +- net/netfilter/nft_set_pipapo.c | 14 +- net/netfilter/nft_set_rbtree.c | 5 +- 10 files changed, 458 insertions(+), 202 deletions(-) -- 2.34.1

2 20

[PATCH OLK-5.10 0/3] scsi: mpt3sas: Driver patch set for openEuler-22.03
by Hao Zhang 10 Oct '23

10 Oct '23

Get patch set from upstream 5.10 LTS stable branch Ranjan Kumar (1): scsi: mpt3sas: Perform additional retries if doorbell read returns 0 Tomas Henzl (1): scsi: mpt3sas: Fix a memory leak Wenchao Hao (1): scsi: mpt3sas: Fix NULL pointer access in mpt3sas_transport_port_add() drivers/scsi/mpt3sas/mpt3sas_base.c | 49 +++++++++++++++++------- drivers/scsi/mpt3sas/mpt3sas_base.h | 1 + drivers/scsi/mpt3sas/mpt3sas_transport.c | 14 ++++++- 3 files changed, 49 insertions(+), 15 deletions(-) -- 2.33.0

2 4

[PATCH OLK-5.10,00/19] nf_table LTS
by Lu Wei 10 Oct '23

10 Oct '23

Florian Westphal (1): netfilter: nf_tables: use net_generic infra for transaction data Lu Wei (7): Revert "netfilter: nf_tables: unbind non-anonymous set if rule construction fails" Revert "netfilter: nf_tables: skip immediate deactivate in _PREPARE_ERROR" Revert "netfilter: nf_tables: add NFT_TRANS_PREPARE_ERROR to deal with bound set/chain" Revert "netfilter: nf_tables: fix chain binding transaction logic" Revert "netfilter: nf_tables: incorrect error path handling with NFT_MSG_NEWRULE" Revert "netfilter: nf_tables: skip bound chain on rule flush" Revert "netfilter: nf_tables: disallow rule addition to bound chain via NFTA_RULE_CHAIN_ID" Pablo Neira Ayuso (11): netfilter: nf_tables: incorrect error path handling with NFT_MSG_NEWRULE netfilter: nf_tables: fix chain binding transaction logic netfilter: nf_tables: add NFT_TRANS_PREPARE_ERROR to deal with bound set/chain netfilter: nf_tables: reject unbound anonymous set before commit phase netfilter: nf_tables: reject unbound chain set before commit phase netfilter: nftables: rename set element data activation/deactivation functions netfilter: nf_tables: drop map element references from preparation phase netfilter: nf_tables: unbind non-anonymous set if rule construction fails netfilter: nf_tables: skip immediate deactivate in _PREPARE_ERROR netfilter: nf_tables: skip bound chain on rule flush netfilter: nf_tables: disallow rule addition to bound chain via NFTA_RULE_CHAIN_ID include/net/netfilter/nf_tables.h | 18 +- include/net/netns/nftables.h | 14 +- net/netfilter/nf_tables_api.c | 534 +++++++++++++++++++++--------- net/netfilter/nf_tables_offload.c | 30 +- net/netfilter/nft_chain_filter.c | 11 +- net/netfilter/nft_dynset.c | 6 +- net/netfilter/nft_set_bitmap.c | 5 +- net/netfilter/nft_set_hash.c | 23 +- net/netfilter/nft_set_pipapo.c | 14 +- net/netfilter/nft_set_rbtree.c | 5 +- 10 files changed, 458 insertions(+), 202 deletions(-) -- 2.34.1

1 19

[PATCH OLK-5.10,00/19] nf_table LTS
by Lu Wei 10 Oct '23

10 Oct '23

Florian Westphal (1): netfilter: nf_tables: use net_generic infra for transaction data Lu Wei (7): Revert "netfilter: nf_tables: unbind non-anonymous set if rule construction fails" Revert "netfilter: nf_tables: skip immediate deactivate in _PREPARE_ERROR" Revert "netfilter: nf_tables: add NFT_TRANS_PREPARE_ERROR to deal with bound set/chain" Revert "netfilter: nf_tables: fix chain binding transaction logic" Revert "netfilter: nf_tables: incorrect error path handling with NFT_MSG_NEWRULE" Revert "netfilter: nf_tables: skip bound chain on rule flush" Revert "netfilter: nf_tables: disallow rule addition to bound chain via NFTA_RULE_CHAIN_ID" Pablo Neira Ayuso (11): netfilter: nf_tables: incorrect error path handling with NFT_MSG_NEWRULE netfilter: nf_tables: fix chain binding transaction logic netfilter: nf_tables: add NFT_TRANS_PREPARE_ERROR to deal with bound set/chain netfilter: nf_tables: reject unbound anonymous set before commit phase netfilter: nf_tables: reject unbound chain set before commit phase netfilter: nftables: rename set element data activation/deactivation functions netfilter: nf_tables: drop map element references from preparation phase netfilter: nf_tables: unbind non-anonymous set if rule construction fails netfilter: nf_tables: skip immediate deactivate in _PREPARE_ERROR netfilter: nf_tables: skip bound chain on rule flush netfilter: nf_tables: disallow rule addition to bound chain via NFTA_RULE_CHAIN_ID include/net/netfilter/nf_tables.h | 18 +- include/net/netns/nftables.h | 14 +- net/netfilter/nf_tables_api.c | 534 +++++++++++++++++++++--------- net/netfilter/nf_tables_offload.c | 30 +- net/netfilter/nft_chain_filter.c | 11 +- net/netfilter/nft_dynset.c | 6 +- net/netfilter/nft_set_bitmap.c | 5 +- net/netfilter/nft_set_hash.c | 23 +- net/netfilter/nft_set_pipapo.c | 14 +- net/netfilter/nft_set_rbtree.c | 5 +- 10 files changed, 458 insertions(+), 202 deletions(-) -- 2.34.1

1 19

[PATCH OLK-5.10 0/2] tracing: Backport bugfixes
by Zheng Yejian 10 Oct '23

10 Oct '23

Chen Lin (1): ring-buffer: Do not swap cpu_buffer during resize process Steven Rostedt (Google) (1): ring-buffer: Do not attempt to read past "commit" kernel/trace/ring_buffer.c | 19 ++++++++++++++++++- kernel/trace/trace.c | 3 ++- 2 files changed, 20 insertions(+), 2 deletions(-) -- 2.25.1

2 3

[PATCH OLK-5.10 1/2] ring-buffer: Do not swap cpu_buffer during resize process
by Zheng Yejian 10 Oct '23

10 Oct '23

From: Chen Lin <chen.lin5(a)zte.com.cn> mainline inclusion from mainline-v6.5-rc3 commit 8a96c0288d0737ad77882024974c075345c72011 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I86Q1D Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… ------------------------------------------------- When ring_buffer_swap_cpu was called during resize process, the cpu buffer was swapped in the middle, resulting in incorrect state. Continuing to run in the wrong state will result in oops. This issue can be easily reproduced using the following two scripts: /tmp # cat test1.sh //#! /bin/sh for i in `seq 0 100000` do echo 2000 > /sys/kernel/debug/tracing/buffer_size_kb sleep 0.5 echo 5000 > /sys/kernel/debug/tracing/buffer_size_kb sleep 0.5 done /tmp # cat test2.sh //#! /bin/sh for i in `seq 0 100000` do echo irqsoff > /sys/kernel/debug/tracing/current_tracer sleep 1 echo nop > /sys/kernel/debug/tracing/current_tracer sleep 1 done /tmp # ./test1.sh & /tmp # ./test2.sh & A typical oops log is as follows, sometimes with other different oops logs. [ 231.711293] WARNING: CPU: 0 PID: 9 at kernel/trace/ring_buffer.c:2026 rb_update_pages+0x378/0x3f8 [ 231.713375] Modules linked in: [ 231.714735] CPU: 0 PID: 9 Comm: kworker/0:1 Tainted: G W 6.5.0-rc1-00276-g20edcec23f92 #15 [ 231.716750] Hardware name: linux,dummy-virt (DT) [ 231.718152] Workqueue: events update_pages_handler [ 231.719714] pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) [ 231.721171] pc : rb_update_pages+0x378/0x3f8 [ 231.722212] lr : rb_update_pages+0x25c/0x3f8 [ 231.723248] sp : ffff800082b9bd50 [ 231.724169] x29: ffff800082b9bd50 x28: ffff8000825f7000 x27: 0000000000000000 [ 231.726102] x26: 0000000000000001 x25: fffffffffffff010 x24: 0000000000000ff0 [ 231.728122] x23: ffff0000c3a0b600 x22: ffff0000c3a0b5c0 x21: fffffffffffffe0a [ 231.730203] x20: ffff0000c3a0b600 x19: ffff0000c0102400 x18: 0000000000000000 [ 231.732329] x17: 0000000000000000 x16: 0000000000000000 x15: 0000ffffe7aa8510 [ 231.734212] x14: 0000000000000000 x13: 0000000000000000 x12: 0000000000000002 [ 231.736291] x11: ffff8000826998a8 x10: ffff800082b9baf0 x9 : ffff800081137558 [ 231.738195] x8 : fffffc00030e82c8 x7 : 0000000000000000 x6 : 0000000000000001 [ 231.740192] x5 : ffff0000ffbafe00 x4 : 0000000000000000 x3 : 0000000000000000 [ 231.742118] x2 : 00000000000006aa x1 : 0000000000000001 x0 : ffff0000c0007208 [ 231.744196] Call trace: [ 231.744892] rb_update_pages+0x378/0x3f8 [ 231.745893] update_pages_handler+0x1c/0x38 [ 231.746893] process_one_work+0x1f0/0x468 [ 231.747852] worker_thread+0x54/0x410 [ 231.748737] kthread+0x124/0x138 [ 231.749549] ret_from_fork+0x10/0x20 [ 231.750434] ---[ end trace 0000000000000000 ]--- [ 233.720486] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000 [ 233.721696] Mem abort info: [ 233.721935] ESR = 0x0000000096000004 [ 233.722283] EC = 0x25: DABT (current EL), IL = 32 bits [ 233.722596] SET = 0, FnV = 0 [ 233.722805] EA = 0, S1PTW = 0 [ 233.723026] FSC = 0x04: level 0 translation fault [ 233.723458] Data abort info: [ 233.723734] ISV = 0, ISS = 0x00000004, ISS2 = 0x00000000 [ 233.724176] CM = 0, WnR = 0, TnD = 0, TagAccess = 0 [ 233.724589] GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0 [ 233.725075] user pgtable: 4k pages, 48-bit VAs, pgdp=0000000104943000 [ 233.725592] [0000000000000000] pgd=0000000000000000, p4d=0000000000000000 [ 233.726231] Internal error: Oops: 0000000096000004 [#1] PREEMPT SMP [ 233.726720] Modules linked in: [ 233.727007] CPU: 0 PID: 9 Comm: kworker/0:1 Tainted: G W 6.5.0-rc1-00276-g20edcec23f92 #15 [ 233.727777] Hardware name: linux,dummy-virt (DT) [ 233.728225] Workqueue: events update_pages_handler [ 233.728655] pstate: 200000c5 (nzCv daIF -PAN -UAO -TCO -DIT -SSBS BTYPE=--) [ 233.729054] pc : rb_update_pages+0x1a8/0x3f8 [ 233.729334] lr : rb_update_pages+0x154/0x3f8 [ 233.729592] sp : ffff800082b9bd50 [ 233.729792] x29: ffff800082b9bd50 x28: ffff8000825f7000 x27: 0000000000000000 [ 233.730220] x26: 0000000000000000 x25: ffff800082a8b840 x24: ffff0000c0102418 [ 233.730653] x23: 0000000000000000 x22: fffffc000304c880 x21: 0000000000000003 [ 233.731105] x20: 00000000000001f4 x19: ffff0000c0102400 x18: ffff800082fcbc58 [ 233.731727] x17: 0000000000000000 x16: 0000000000000001 x15: 0000000000000001 [ 233.732282] x14: ffff8000825fe0c8 x13: 0000000000000001 x12: 0000000000000000 [ 233.732709] x11: ffff8000826998a8 x10: 0000000000000ae0 x9 : ffff8000801b760c [ 233.733148] x8 : fefefefefefefeff x7 : 0000000000000018 x6 : ffff0000c03298c0 [ 233.733553] x5 : 0000000000000002 x4 : 0000000000000000 x3 : 0000000000000000 [ 233.733972] x2 : ffff0000c3a0b600 x1 : 0000000000000000 x0 : 0000000000000000 [ 233.734418] Call trace: [ 233.734593] rb_update_pages+0x1a8/0x3f8 [ 233.734853] update_pages_handler+0x1c/0x38 [ 233.735148] process_one_work+0x1f0/0x468 [ 233.735525] worker_thread+0x54/0x410 [ 233.735852] kthread+0x124/0x138 [ 233.736064] ret_from_fork+0x10/0x20 [ 233.736387] Code: 92400000 910006b5 aa000021 aa0303f7 (f9400060) [ 233.736959] ---[ end trace 0000000000000000 ]--- After analysis, the seq of the error is as follows [1-5]: int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size, int cpu_id) { for_each_buffer_cpu(buffer, cpu) { cpu_buffer = buffer->buffers[cpu]; //1. get cpu_buffer, aka cpu_buffer(A) ... ... schedule_work_on(cpu, &cpu_buffer->update_pages_work); //2. 'update_pages_work' is queue on 'cpu', cpu_buffer(A) is passed to // update_pages_handler, do the update process, set 'update_done' in // complete(&cpu_buffer->update_done) and to wakeup resize process. //----> //3. Just at this moment, ring_buffer_swap_cpu is triggered, //cpu_buffer(A) be swaped to cpu_buffer(B), the max_buffer. //ring_buffer_swap_cpu is called as the 'Call trace' below. Call trace: dump_backtrace+0x0/0x2f8 show_stack+0x18/0x28 dump_stack+0x12c/0x188 ring_buffer_swap_cpu+0x2f8/0x328 update_max_tr_single+0x180/0x210 check_critical_timing+0x2b4/0x2c8 tracer_hardirqs_on+0x1c0/0x200 trace_hardirqs_on+0xec/0x378 el0_svc_common+0x64/0x260 do_el0_svc+0x90/0xf8 el0_svc+0x20/0x30 el0_sync_handler+0xb0/0xb8 el0_sync+0x180/0x1c0 //<---- /* wait for all the updates to complete */ for_each_buffer_cpu(buffer, cpu) { cpu_buffer = buffer->buffers[cpu]; //4. get cpu_buffer, cpu_buffer(B) is used in the following process, //the state of cpu_buffer(A) and cpu_buffer(B) is totally wrong. //for example, cpu_buffer(A)->update_done will leave be set 1, and will //not 'wait_for_completion' at the next resize round. if (!cpu_buffer->nr_pages_to_update) continue; if (cpu_online(cpu)) wait_for_completion(&cpu_buffer->update_done); cpu_buffer->nr_pages_to_update = 0; } ... } //5. the state of cpu_buffer(A) and cpu_buffer(B) is totally wrong, //Continuing to run in the wrong state, then oops occurs. Link: https://lore.kernel.org/linux-trace-kernel/202307191558478409990@zte.com.cn Signed-off-by: Chen Lin <chen.lin5(a)zte.com.cn> Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> Signed-off-by: Zheng Yejian <zhengyejian1(a)huawei.com> --- kernel/trace/ring_buffer.c | 14 +++++++++++++- kernel/trace/trace.c | 3 ++- 2 files changed, 15 insertions(+), 2 deletions(-) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 6c901a8f1202..c90988652986 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -539,6 +539,7 @@ struct trace_buffer { unsigned flags; int cpus; atomic_t record_disabled; + atomic_t resizing; cpumask_var_t cpumask; struct lock_class_key *reader_lock_key; @@ -2038,7 +2039,7 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size, /* prevent another thread from changing buffer sizes */ mutex_lock(&buffer->mutex); - + atomic_inc(&buffer->resizing); if (cpu_id == RING_BUFFER_ALL_CPUS) { /* @@ -2181,6 +2182,7 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size, atomic_dec(&buffer->record_disabled); } + atomic_dec(&buffer->resizing); mutex_unlock(&buffer->mutex); return 0; @@ -2201,6 +2203,7 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size, } } out_err_unlock: + atomic_dec(&buffer->resizing); mutex_unlock(&buffer->mutex); return err; } @@ -5237,6 +5240,15 @@ int ring_buffer_swap_cpu(struct trace_buffer *buffer_a, if (local_read(&cpu_buffer_b->committing)) goto out_dec; + /* + * When resize is in progress, we cannot swap it because + * it will mess the state of the cpu buffer. + */ + if (atomic_read(&buffer_a->resizing)) + goto out_dec; + if (atomic_read(&buffer_b->resizing)) + goto out_dec; + buffer_a->buffers[cpu] = cpu_buffer_b; buffer_b->buffers[cpu] = cpu_buffer_a; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 5062939700b6..77ad035d6365 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1876,9 +1876,10 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) * place on this CPU. We fail to record, but we reset * the max trace buffer (no one writes directly to it) * and flag that it failed. + * Another reason is resize is in progress. */ trace_array_printk_buf(tr->max_buffer.buffer, _THIS_IP_, - "Failed to swap buffers due to commit in progress\n"); + "Failed to swap buffers due to commit or resize in progress\n"); } WARN_ON_ONCE(ret && ret != -EAGAIN && ret != -EBUSY); -- 2.25.1

2 2

[PATCH openEuler-23.09] mm: gmem: Display VM_PEER_SHARED as ps during smaps
by Wupeng Ma 10 Oct '23

10 Oct '23

From: Ma Wupeng <mawupeng1(a)huawei.com> euleros inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I7WLVX --------------------------------------------- Display VM_PEER_SHARED as ps during smaps. Signed-off-by: Ma Wupeng <mawupeng1(a)huawei.com> --- fs/proc/task_mmu.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index f1f3b03e1867..509fcbc73e3e 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -712,6 +712,9 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma) #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR [ilog2(VM_UFFD_MINOR)] = "ui", #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */ +#ifdef CONFIG_GMEM + [ilog2(VM_PEER_SHARED)] = "ps", +#endif }; size_t i; -- 2.25.1

2 1

[PATCH OLK-5.10 00/10] scsi: mpt3sas: Driver patch set for openEuler-22.03
by Hao Zhang 10 Oct '23

10 Oct '23

Get patch set from upstream 5.10 LTS stable branch Matt Lupfer (1): scsi: mpt3sas: Page fault in reply q processing Ranjan Kumar (1): scsi: mpt3sas: Perform additional retries if doorbell read returns 0 Sreekanth Reddy (4): scsi: mpt3sas: Fix use-after-free warning scsi: mpt3sas: Don't change DMA mask while reallocating pools scsi: mpt3sas: re-do lost mpt3sas DMA mask fix scsi: mpt3sas: Remove usage of dma_get_required_mask() API Suganath Prabu S (1): scsi: mpt3sas: Force PCIe scatterlist allocations to be within same 4 GB region Tomas Henzl (1): scsi: mpt3sas: Fix a memory leak Wenchao Hao (1): scsi: mpt3sas: Fix NULL pointer access in mpt3sas_transport_port_add() Yang Yingliang (1): scsi: mpt3sas: Fix possible resource leaks in mpt3sas_transport_port_add() drivers/scsi/mpt3sas/mpt3sas_base.c | 227 ++++++++++++++++------- drivers/scsi/mpt3sas/mpt3sas_base.h | 2 + drivers/scsi/mpt3sas/mpt3sas_scsih.c | 2 +- drivers/scsi/mpt3sas/mpt3sas_transport.c | 16 +- 4 files changed, 178 insertions(+), 69 deletions(-) -- 2.33.0

2 11

[PATCH openEuler-22.03-LTS] mm: gmem: Display VM_PEER_SHARED as ps during smaps
by Wupeng Ma 10 Oct '23

10 Oct '23

From: Ma Wupeng <mawupeng1(a)huawei.com> euleros inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I7WLVX --------------------------------------------- Display VM_PEER_SHARED as ps during smaps. Signed-off-by: Ma Wupeng <mawupeng1(a)huawei.com> --- fs/proc/task_mmu.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index f1f3b03e1867..509fcbc73e3e 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -712,6 +712,9 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma) #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR [ilog2(VM_UFFD_MINOR)] = "ui", #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */ +#ifdef CONFIG_GMEM + [ilog2(VM_PEER_SHARED)] = "ps", +#endif }; size_t i; -- 2.25.1

2 1

[PATCH openEuler-22.03-LTS 1/1] mm: gmem: Display VM_PEER_SHARED as ps during smaps
by Wupeng Ma 10 Oct '23

10 Oct '23

From: Ma Wupeng <mawupeng1(a)huawei.com> euleros inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I7WLVX --------------------------------------------- Display VM_PEER_SHARED as ps during smaps. Signed-off-by: Ma Wupeng <mawupeng1(a)huawei.com> --- fs/proc/task_mmu.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index f1f3b03e1867..509fcbc73e3e 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -712,6 +712,9 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma) #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR [ilog2(VM_UFFD_MINOR)] = "ui", #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */ +#ifdef CONFIG_GMEM + [ilog2(VM_PEER_SHARED)] = "ps", +#endif }; size_t i; -- 2.25.1

2 1

[PATCH OLK-5.10,00/19] nf_table LTS
by Lu Wei 10 Oct '23

10 Oct '23

Florian Westphal (1): netfilter: nf_tables: use net_generic infra for transaction data Lu Wei (7): Revert "netfilter: nf_tables: unbind non-anonymous set if rule construction fails" Revert "netfilter: nf_tables: skip immediate deactivate in _PREPARE_ERROR" Revert "netfilter: nf_tables: add NFT_TRANS_PREPARE_ERROR to deal with bound set/chain" Revert "netfilter: nf_tables: fix chain binding transaction logic" Revert "netfilter: nf_tables: incorrect error path handling with NFT_MSG_NEWRULE" Revert "netfilter: nf_tables: skip bound chain on rule flush" Revert "netfilter: nf_tables: disallow rule addition to bound chain via NFTA_RULE_CHAIN_ID" Pablo Neira Ayuso (11): netfilter: nf_tables: incorrect error path handling with NFT_MSG_NEWRULE netfilter: nf_tables: fix chain binding transaction logic netfilter: nf_tables: add NFT_TRANS_PREPARE_ERROR to deal with bound set/chain netfilter: nf_tables: reject unbound anonymous set before commit phase netfilter: nf_tables: reject unbound chain set before commit phase netfilter: nftables: rename set element data activation/deactivation functions netfilter: nf_tables: drop map element references from preparation phase netfilter: nf_tables: unbind non-anonymous set if rule construction fails netfilter: nf_tables: skip immediate deactivate in _PREPARE_ERROR netfilter: nf_tables: skip bound chain on rule flush netfilter: nf_tables: disallow rule addition to bound chain via NFTA_RULE_CHAIN_ID include/net/netfilter/nf_tables.h | 18 +- include/net/netns/nftables.h | 14 +- net/netfilter/nf_tables_api.c | 534 +++++++++++++++++++++--------- net/netfilter/nf_tables_offload.c | 30 +- net/netfilter/nft_chain_filter.c | 11 +- net/netfilter/nft_dynset.c | 6 +- net/netfilter/nft_set_bitmap.c | 5 +- net/netfilter/nft_set_hash.c | 23 +- net/netfilter/nft_set_pipapo.c | 14 +- net/netfilter/nft_set_rbtree.c | 5 +- 10 files changed, 458 insertions(+), 202 deletions(-) -- 2.34.1

1 19

[PATCH V1 OLK-5.10 00/24] Introduce some vdpa ops to support vdpa device hotmigrate
by Jiang Dongxu 10 Oct '23

10 Oct '23

From: jiangdongxu1 <jiangdongxu1(a)huawei.com> Patch 1-15: some bugfix and ops intruduced by upstream Patch 16-17: introduce vdpa device logging ops Patch 18: get_backend_feature ops intruduced by upstream Patch 19-20: introduce vdpa device state ops Patch 21-22: introduce vdpa migrate state ops Patch 23: introduce new VHOST feature BYTEMAPLOG Patch 24: introduce vmstate header file used for vender vdpa driver jiangdongxu1 (24): vhost-vdpa: fix an iotlb memory leak vhost_vdpa: fix the crash in unmap a large memory vdpa: Add resume operation vhost-vdpa: Introduce RESUME backend feature bit vhost-vdpa: uAPI to resume the device vhost-vdpa: free iommu domain after last use during cleanup vhost-vdpa: vhost_vdpa_alloc_domain() should be using a const struct bus_type * vdpa: add bind_mm/unbind_mm callbacks vhost-vdpa: use bind_mm/unbind_mm device callbacks vhost_vdpa: fix unmap process in no-batch mode vhost_vdpa: tell vqs about the negotiated vhost_vdpa: support PACKED when setting-getting vring_base PCI/IOV: Add pci_iov_vf_id() to get VF index virtio: update virtio id table, add transitional ids virtio: fix virtio transitional ids vdpa: add log operations vhost-vdpa: add uAPI for logging vdpa: add get_backend_features vdpa operation vdpa: add device state operations vhost-vdpa: add uAPI for device buffer vdpa: add vdpa device migration status ops vhost-vdpa: add uAPI for device migration status vhost: add VHOST feature VHOST_BACKEND_F_BYTEMAPLOG vdpa: add vmstate struct definition drivers/pci/iov.c | 14 ++ drivers/vhost/vdpa.c | 316 +++++++++++++++++++++++++++---- include/linux/pci.h | 8 +- include/linux/vdpa.h | 60 +++++- include/linux/vdpa_vmstate.h | 162 ++++++++++++++++ include/uapi/linux/vhost.h | 20 ++ include/uapi/linux/vhost_types.h | 21 ++ include/uapi/linux/virtio_ids.h | 12 ++ 8 files changed, 577 insertions(+), 36 deletions(-) create mode 100644 include/linux/vdpa_vmstate.h -- 2.33.0

2 25

[PATCH OLK-5.10] ipv4: fix null-deref in ipv4_link_failure
by Lu Wei 10 Oct '23

10 Oct '23

From: Kyle Zeng <zengyhkyle(a)gmail.com> mainline inclusion from mainline-v6.6-rc3 commit 0113d9c9d1ccc07f5a3710dac4aa24b6d711278c category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I85DZB CVE: CVE-2023-42754 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Currently, we assume the skb is associated with a device before calling __ip_options_compile, which is not always the case if it is re-routed by ipvs. When skb->dev is NULL, dev_net(skb->dev) will become null-dereference. This patch adds a check for the edge case and switch to use the net_device from the rtable when skb->dev is NULL. Fixes: ed0de45a1008 ("ipv4: recompile ip options in ipv4_link_failure") Suggested-by: David Ahern <dsahern(a)kernel.org> Signed-off-by: Kyle Zeng <zengyhkyle(a)gmail.com> Cc: Stephen Suryaputra <ssuryaextr(a)gmail.com> Cc: Vadim Fedorenko <vfedorenko(a)novek.ru> Reviewed-by: David Ahern <dsahern(a)kernel.org> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Lu Wei <luwei32(a)huawei.com> --- net/ipv4/route.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 216f76b548ff..f85eaf566b9b 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1240,6 +1240,7 @@ static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie) static void ipv4_send_dest_unreach(struct sk_buff *skb) { + struct net_device *dev; struct ip_options opt; int res; @@ -1257,7 +1258,8 @@ static void ipv4_send_dest_unreach(struct sk_buff *skb) opt.optlen = ip_hdr(skb)->ihl * 4 - sizeof(struct iphdr); rcu_read_lock(); - res = __ip_options_compile(dev_net(skb->dev), &opt, skb, NULL); + dev = skb->dev ? skb->dev : skb_rtable(skb)->dst.dev; + res = __ip_options_compile(dev_net(dev), &opt, skb, NULL); rcu_read_unlock(); if (res) -- 2.34.1

2 1

[PATCH OLK-5.10 01/24] vhost-vdpa: fix an iotlb memory leak
by Jiang Dongxu 09 Oct '23

09 Oct '23

From: jiangdongxu1 <jiangdongxu1(a)huawei.com> mainline inclusion from v6.2-rc3 commit c070c1912a83432530cbb4271d5b9b11fa36b67a category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I86ITO Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Before commit 3d5698793897 ("vhost-vdpa: introduce asid based IOTLB") we called vhost_vdpa_iotlb_unmap(v, iotlb, 0ULL, 0ULL - 1) during release to free all the resources allocated when processing user IOTLB messages through vhost_vdpa_process_iotlb_update(). That commit changed the handling of IOTLB a bit, and we accidentally removed some code called during the release. We partially fixed this with commit 037d4305569a ("vhost-vdpa: call vhost_vdpa_cleanup during the release") but a potential memory leak is still there as showed by kmemleak if the application does not send VHOST_IOTLB_INVALIDATE or crashes: unreferenced object 0xffff888007fbaa30 (size 16): comm "blkio-bench", pid 914, jiffies 4294993521 (age 885.500s) hex dump (first 16 bytes): 40 73 41 07 80 88 ff ff 00 00 00 00 00 00 00 00 @sA............. backtrace: [<0000000087736d2a>] kmem_cache_alloc_trace+0x142/0x1c0 [<0000000060740f50>] vhost_vdpa_process_iotlb_msg+0x68c/0x901 [vhost_vdpa] [<0000000083e8e205>] vhost_chr_write_iter+0xc0/0x4a0 [vhost] [<000000008f2f414a>] vhost_vdpa_chr_write_iter+0x18/0x20 [vhost_vdpa] [<00000000de1cd4a0>] vfs_write+0x216/0x4b0 [<00000000a2850200>] ksys_write+0x71/0xf0 [<00000000de8e720b>] __x64_sys_write+0x19/0x20 [<0000000018b12cbb>] do_syscall_64+0x3f/0x90 [<00000000986ec465>] entry_SYSCALL_64_after_hwframe+0x63/0xcd Let's fix this calling vhost_vdpa_iotlb_unmap() on the whole range in vhost_vdpa_remove_as(). We move that call before vhost_dev_cleanup() since we need a valid v->vdev.mm in vhost_vdpa_pa_unmap(). vhost_iotlb_reset() call can be removed, since vhost_vdpa_iotlb_unmap() on the whole range removes all the entries. The kmemleak log reported was observed with a vDPA device that has `use_va` set to true (e.g. VDUSE). This patch has been tested with both types of devices. Fixes: 037d4305569a ("vhost-vdpa: call vhost_vdpa_cleanup during the release") Fixes: 3d5698793897 ("vhost-vdpa: introduce asid based IOTLB") Signed-off-by: Stefano Garzarella <sgarzare(a)redhat.com> Message-Id: <20221109154213.146789-1-sgarzare(a)redhat.com> Signed-off-by: Michael S. Tsirkin <mst(a)redhat.com> Acked-by: Jason Wang <jasowang(a)redhat.com> Signed-off-by: jiangdongxu1 <jiangdongxu1(a)huawei.com> --- drivers/vhost/vdpa.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index ebafc05d2b74..eee3189985b9 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -65,6 +65,10 @@ static DEFINE_IDA(vhost_vdpa_ida); static dev_t vhost_vdpa_major; +static void vhost_vdpa_iotlb_unmap(struct vhost_vdpa *v, + struct vhost_iotlb *iotlb, + u64 start, u64 last); + static inline u32 iotlb_to_asid(struct vhost_iotlb *iotlb) { struct vhost_vdpa_as *as = container_of(iotlb, struct @@ -135,7 +139,7 @@ static int vhost_vdpa_remove_as(struct vhost_vdpa *v, u32 asid) return -EINVAL; hlist_del(&as->hash_link); - vhost_iotlb_reset(&as->iotlb); + vhost_vdpa_iotlb_unmap(v, &as->iotlb, 0ULL, 0ULL - 1); kfree(as); return 0; @@ -1166,14 +1170,14 @@ static void vhost_vdpa_cleanup(struct vhost_vdpa *v) struct vhost_vdpa_as *as; u32 asid; - vhost_dev_cleanup(&v->vdev); - kfree(v->vdev.vqs); - for (asid = 0; asid < v->vdpa->nas; asid++) { as = asid_to_as(v, asid); if (as) vhost_vdpa_remove_as(v, asid); } + + vhost_dev_cleanup(&v->vdev); + kfree(v->vdev.vqs); } static int vhost_vdpa_open(struct inode *inode, struct file *filep) -- 2.33.0

2 24

[PATCH 00/24] Introduce vdpa ops to support vdpa device hotmigrate
by Jiang Dongxu 09 Oct '23

09 Oct '23

From: jiangdongxu1 <jiangdongxu1(a)huawei.com> Patch 1-15: some bugfix and ops intruduced by upstream Patch 16-17: introduce vdpa device logging ops Patch 18: get_backend_feature ops intruduced by upstream Patch 19-20: introduce vdpa device state ops Patch 21-22: introduce vdpa migrate state ops Patch 23: introduce new VHOST feature BYTEMAPLOG Patch 24: introduce vmstate header file used for vender vdpa driver jiangdongxu1 (24): vhost-vdpa: fix an iotlb memory leak vhost_vdpa: fix the crash in unmap a large memory vdpa: Add resume operation vhost-vdpa: Introduce RESUME backend feature bit vhost-vdpa: uAPI to resume the device vhost-vdpa: free iommu domain after last use during cleanup vhost-vdpa: vhost_vdpa_alloc_domain() should be using a const struct bus_type * vdpa: add bind_mm/unbind_mm callbacks vhost-vdpa: use bind_mm/unbind_mm device callbacks vhost_vdpa: fix unmap process in no-batch mode vhost_vdpa: tell vqs about the negotiated vhost_vdpa: support PACKED when setting-getting vring_base PCI/IOV: Add pci_iov_vf_id() to get VF index virtio: update virtio id table, add transitional ids virtio: fix virtio transitional ids vdpa: add log operations vhost-vdpa: add uAPI for logging vdpa: add get_backend_features vdpa operation vdpa: add device state operations vhost-vdpa: add uAPI for device buffer vdpa: add vdpa device migration status ops vhost-vdpa: add uAPI for device migration status vhost: add VHOST feature VHOST_BACKEND_F_BYTEMAPLOG vdpa: add vmstate struct definition drivers/pci/iov.c | 14 ++ drivers/vhost/vdpa.c | 316 +++++++++++++++++++++++++++---- include/linux/pci.h | 8 +- include/linux/vdpa.h | 60 +++++- include/linux/vdpa_vmstate.h | 162 ++++++++++++++++ include/uapi/linux/vhost.h | 20 ++ include/uapi/linux/vhost_types.h | 21 ++ include/uapi/linux/virtio_ids.h | 12 ++ 8 files changed, 577 insertions(+), 36 deletions(-) create mode 100644 include/linux/vdpa_vmstate.h -- 2.33.0

1 0

[PATCH v2 OLK-5.10 00/19] Introduce PBHA and PBHA bit0 to control the usage of HBM Cache precisely
by Wupeng Ma 09 Oct '23

09 Oct '23

From: Ma Wupeng <mawupeng1(a)huawei.com> Patch 1: move FDT init out of kaslr_early_init for future use. Patch 2 to 8: enable feature PBHA for arm64. Patch 9-18: Control the usage of HBM cache for kernel and task precisely. Patch 19: Enable feature PBHA for arm64 by default. Changelog since v1: - fix kabi broken due to include files James Morse (7): KVM: arm64: Detect and enable PBHA for stage2 dt-bindings: Rename the description of cpu nodes cpu.yaml dt-bindings: arm: Add binding for Page Based Hardware Attributes arm64: cpufeature: Enable PBHA bits for stage1 arm64: mm: Add pgprot_pbha() to allow drivers to request PBHA values KVM: arm64: Configure PBHA bits for stage2 Documentation: arm64: Describe the support and expectations for PBHA Ma Wupeng (11): arm64: cpufeature: Enable PBHA for stage1 early via FDT arm64: mm: Detect and enable PBHA bit0 at early startup arm64: mm: Update kernel pte entries if pbha bit0 enabled arm64: mm: Show PBHA bit 59 as PBHA0 in ptdump arm64: mm: Introduce VM_PBHA_BIT0 to enable pbha bit0 for single vma arm64: mm: Set PBHA0 bit for VM_PBHA_BIT0 arm64: mm: Introduce sysfs interface to bypass whole task arm64: mm: Set flag VM_PBHA_BIT0 for global init task arm64: mm: Introduce prctl to control pbha behavior arm64: mm: Introduce kernel param pbha openeuler: configs: arm64: Enable PBHA by default Marc Zyngier (1): arm64: Extract early FDT mapping from kaslr_early_init() .../admin-guide/kernel-parameters.txt | 8 + Documentation/arm64/index.rst | 1 + Documentation/arm64/pbha.rst | 85 +++ .../devicetree/bindings/arm/cpu.yaml | 537 ++++++++++++++++ .../devicetree/bindings/arm/cpus.yaml | 584 +++--------------- arch/arm64/Kconfig | 20 + arch/arm64/configs/openeuler_defconfig | 1 + arch/arm64/include/asm/cpucaps.h | 3 + arch/arm64/include/asm/cpufeature.h | 15 + arch/arm64/include/asm/kvm_arm.h | 1 + arch/arm64/include/asm/kvm_pgtable.h | 9 + arch/arm64/include/asm/mman.h | 10 + arch/arm64/include/asm/pgtable-hwdef.h | 6 + arch/arm64/include/asm/pgtable.h | 26 + arch/arm64/include/asm/setup.h | 3 + arch/arm64/include/uapi/asm/mman.h | 1 + arch/arm64/kernel/cpufeature.c | 258 ++++++++ arch/arm64/kernel/head.S | 6 +- arch/arm64/kernel/image-vars.h | 3 + arch/arm64/kernel/kaslr.c | 7 +- arch/arm64/kernel/setup.c | 15 + arch/arm64/kvm/reset.c | 15 +- arch/arm64/mm/hugetlbpage.c | 2 + arch/arm64/mm/mmu.c | 14 +- arch/arm64/mm/ptdump.c | 5 + .../firmware/efi/libstub/efi-stub-helper.c | 3 + drivers/firmware/efi/libstub/fdt.c | 57 ++ drivers/soc/hisilicon/Makefile | 1 + drivers/soc/hisilicon/pbha.c | 204 ++++++ fs/proc/base.c | 103 +++ fs/proc/task_mmu.c | 3 + include/linux/mm.h | 8 +- include/linux/pbha.h | 66 ++ include/uapi/asm-generic/mman-common.h | 1 + include/uapi/linux/prctl.h | 2 + kernel/sys.c | 10 + mm/memory.c | 4 + mm/vmalloc.c | 5 + 38 files changed, 1579 insertions(+), 523 deletions(-) create mode 100644 Documentation/arm64/pbha.rst create mode 100644 Documentation/devicetree/bindings/arm/cpu.yaml create mode 100644 drivers/soc/hisilicon/pbha.c create mode 100644 include/linux/pbha.h -- 2.25.1

2 20

[PATCH OLK-5.10 01/19] Revert "netfilter: nf_tables: unbind non-anonymous set if rule construction fails"
by Lu Wei 09 Oct '23

09 Oct '23

Offering: HULK hulk inclusion category: bugfix bugzilla: NA ------------------------------- This reverts commit dbc47736365771e25f6c831a57d4ff384ba983ef. Backport the dependency patch and then re-backport this patch. Signed-off-by: Lu Wei <luwei32(a)huawei.com> --- net/netfilter/nf_tables_api.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index bbe6e7023683..40fbf2d78427 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -4564,8 +4564,6 @@ void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set, nft_set_trans_unbind(ctx, set); if (nft_set_is_anonymous(set)) nft_deactivate_next(ctx->net, set); - else - list_del_rcu(&binding->list); set->use--; break; -- 2.34.1

2 19

[PATCH v2 OLK-5.10 00/19] Introduce PBHA and PBHA bit0 to control the usage of HBM Cache precisely
by Wupeng Ma 09 Oct '23

09 Oct '23

From: Ma Wupeng <mawupeng1(a)huawei.com> Patch 1: move FDT init out of kaslr_early_init for future use. Patch 2 to 8: enable feature PBHA for arm64. Patch 9-18: Control the usage of HBM cache for kernel and task precisely. Patch 19: Enable feature PBHA for arm64 by default. Changelog since v1: - fix kabi broken due to include files James Morse (7): KVM: arm64: Detect and enable PBHA for stage2 dt-bindings: Rename the description of cpu nodes cpu.yaml dt-bindings: arm: Add binding for Page Based Hardware Attributes arm64: cpufeature: Enable PBHA bits for stage1 arm64: mm: Add pgprot_pbha() to allow drivers to request PBHA values KVM: arm64: Configure PBHA bits for stage2 Documentation: arm64: Describe the support and expectations for PBHA Ma Wupeng (11): arm64: cpufeature: Enable PBHA for stage1 early via FDT arm64: mm: Detect and enable PBHA bit0 at early startup arm64: mm: Update kernel pte entries if pbha bit0 enabled arm64: mm: Show PBHA bit 59 as PBHA0 in ptdump arm64: mm: Introduce VM_PBHA_BIT0 to enable pbha bit0 for single vma arm64: mm: Set PBHA0 bit for VM_PBHA_BIT0 arm64: mm: Introduce sysfs interface to bypass whole task arm64: mm: Set flag VM_PBHA_BIT0 for global init task arm64: mm: Introduce prctl to control pbha behavior arm64: mm: Introduce kernel param pbha openeuler: configs: arm64: Enable PBHA by default Marc Zyngier (1): arm64: Extract early FDT mapping from kaslr_early_init() .../admin-guide/kernel-parameters.txt | 8 + Documentation/arm64/index.rst | 1 + Documentation/arm64/pbha.rst | 85 +++ .../devicetree/bindings/arm/cpu.yaml | 537 ++++++++++++++++ .../devicetree/bindings/arm/cpus.yaml | 584 +++--------------- arch/arm64/Kconfig | 20 + arch/arm64/configs/openeuler_defconfig | 1 + arch/arm64/include/asm/cpucaps.h | 3 + arch/arm64/include/asm/cpufeature.h | 15 + arch/arm64/include/asm/kvm_arm.h | 1 + arch/arm64/include/asm/kvm_pgtable.h | 9 + arch/arm64/include/asm/mman.h | 10 + arch/arm64/include/asm/pgtable-hwdef.h | 6 + arch/arm64/include/asm/pgtable.h | 26 + arch/arm64/include/asm/setup.h | 3 + arch/arm64/include/uapi/asm/mman.h | 1 + arch/arm64/kernel/cpufeature.c | 258 ++++++++ arch/arm64/kernel/head.S | 6 +- arch/arm64/kernel/image-vars.h | 3 + arch/arm64/kernel/kaslr.c | 7 +- arch/arm64/kernel/setup.c | 15 + arch/arm64/kvm/reset.c | 15 +- arch/arm64/mm/hugetlbpage.c | 2 + arch/arm64/mm/mmu.c | 14 +- arch/arm64/mm/ptdump.c | 5 + .../firmware/efi/libstub/efi-stub-helper.c | 3 + drivers/firmware/efi/libstub/fdt.c | 57 ++ drivers/soc/hisilicon/Makefile | 1 + drivers/soc/hisilicon/pbha.c | 204 ++++++ fs/proc/base.c | 103 +++ fs/proc/task_mmu.c | 3 + include/linux/mm.h | 8 +- include/linux/pbha.h | 66 ++ include/uapi/asm-generic/mman-common.h | 1 + include/uapi/linux/prctl.h | 2 + kernel/sys.c | 10 + mm/memory.c | 4 + mm/vmalloc.c | 5 + 38 files changed, 1579 insertions(+), 523 deletions(-) create mode 100644 Documentation/arm64/pbha.rst create mode 100644 Documentation/devicetree/bindings/arm/cpu.yaml create mode 100644 drivers/soc/hisilicon/pbha.c create mode 100644 include/linux/pbha.h -- 2.25.1

1 19

[PATCH OLK-5.10 00/10] scsi: mpt3sas: Driver patch set for
by Hao Zhang 09 Oct '23

09 Oct '23

Get patch set from upstream 5.10 LTS stable branch Matt Lupfer (1): scsi: mpt3sas: Page fault in reply q processing Ranjan Kumar (1): scsi: mpt3sas: Perform additional retries if doorbell read returns 0 Sreekanth Reddy (4): scsi: mpt3sas: Fix use-after-free warning scsi: mpt3sas: Don't change DMA mask while reallocating pools scsi: mpt3sas: re-do lost mpt3sas DMA mask fix scsi: mpt3sas: Remove usage of dma_get_required_mask() API Suganath Prabu S (1): scsi: mpt3sas: Force PCIe scatterlist allocations to be within same 4 GB region Tomas Henzl (1): scsi: mpt3sas: Fix a memory leak Wenchao Hao (1): scsi: mpt3sas: Fix NULL pointer access in mpt3sas_transport_port_add() Yang Yingliang (1): scsi: mpt3sas: Fix possible resource leaks in mpt3sas_transport_port_add() drivers/scsi/mpt3sas/mpt3sas_base.c | 227 ++++++++++++++++------- drivers/scsi/mpt3sas/mpt3sas_base.h | 2 + drivers/scsi/mpt3sas/mpt3sas_scsih.c | 2 +- drivers/scsi/mpt3sas/mpt3sas_transport.c | 16 +- 4 files changed, 178 insertions(+), 69 deletions(-) -- 2.33.0

1 10

[PATCH openEuler-1.0-LTS] scsi: hisi_sas: Handle the NCQ error returned by D2H frame
by Xingui Yang 09 Oct '23

09 Oct '23

driver inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I86GWG CVE: NA ----------------------------------------------------------------------- We find that some disks use D2H frame instead of SDB frame to return NCQ error. Currently, only the I/O corresponding to the D2H frame is processed in this scenario, which does not meet the processing requirements of the NCQ error scenario. So we set dev_status to HISI_SAS_DEV_NCQ_ERR and abort all I/Os of the disk in this scenario. Signed-off-by: Xingui Yang <yangxingui(a)huawei.com> Reviewed-by: Xiang Chen <chenxiang66(a)hisilicon.com> --- drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c index f79060fca..79010d02a 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c @@ -2341,7 +2341,15 @@ slot_err_v3_hw(struct hisi_hba *hisi_hba, struct sas_task *task, case SAS_PROTOCOL_SATA | SAS_PROTOCOL_STP: if ((dw0 & CMPLT_HDR_RSPNS_XFRD_MSK) && (sipc_rx_err_type & RX_FIS_STATUS_ERR_MSK)) { - ts->stat = SAS_PROTO_RESPONSE; + if (task->ata_task.use_ncq) { + struct domain_device *device = task->dev; + struct hisi_sas_device *sas_dev = + device->lldd_dev; + sas_dev->dev_status = HISI_SAS_DEV_NCQ_ERR; + slot->abort = 1; + } else { + ts->stat = SAS_PROTO_RESPONSE; + } } else if ((dw3 & CMPLT_HDR_IO_IN_TARGET_MSK) || (dw3 & SATA_DISK_IN_ERROR_STATUS)) { ts->stat = SAS_PHY_DOWN; -- 2.17.1

2 1

[PATCH OLK-5.10] netfilter: ipset: add the missing IP_SET_HASH_WITH_NET0 macro for ip_set_hash_netportnet.c
by Lu Wei 09 Oct '23

09 Oct '23

From: Kyle Zeng <zengyhkyle(a)gmail.com> mainline inclusion from mainline-v6.6-rc1 commit 050d91c03b28ca479df13dfb02bcd2c60dd6a878 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I83QCZ CVE: CVE-2023-42753 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… --------------------------- The missing IP_SET_HASH_WITH_NET0 macro in ip_set_hash_netportnet can lead to the use of wrong `CIDR_POS(c)` for calculating array offsets, which can lead to integer underflow. As a result, it leads to slab out-of-bound access. This patch adds back the IP_SET_HASH_WITH_NET0 macro to ip_set_hash_netportnet to address the issue. Fixes: 886503f34d63 ("netfilter: ipset: actually allow allowable CIDR 0 in hash:net,port,net") Suggested-by: Jozsef Kadlecsik <kadlec(a)netfilter.org> Signed-off-by: Kyle Zeng <zengyhkyle(a)gmail.com> Acked-by: Jozsef Kadlecsik <kadlec(a)netfilter.org> Signed-off-by: Florian Westphal <fw(a)strlen.de> Signed-off-by: Lu Wei <luwei32(a)huawei.com> --- net/netfilter/ipset/ip_set_hash_netportnet.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/netfilter/ipset/ip_set_hash_netportnet.c b/net/netfilter/ipset/ip_set_hash_netportnet.c index 144346faffc1..b8ec2c414a5f 100644 --- a/net/netfilter/ipset/ip_set_hash_netportnet.c +++ b/net/netfilter/ipset/ip_set_hash_netportnet.c @@ -35,6 +35,7 @@ MODULE_ALIAS("ip_set_hash:net,port,net"); #define IP_SET_HASH_WITH_PROTO #define IP_SET_HASH_WITH_NETS #define IPSET_NET_COUNT 2 +#define IP_SET_HASH_WITH_NET0 /* IPv4 variant */ -- 2.34.1

2 1

[PATCH openEuler-23.09 00/13] LoongArch: fix some pci problems
by Hongchen Zhang 09 Oct '23

09 Oct '23

Hongchen Zhang (13): LoongArch: fix ls2k500 bmc not work when installing iso LS7A2000 : Add quirk for OHCI device rev 0x02 PCI: Check if entry->offset already exist for mem resource PCI: Check if the pci controller can use both CFG0 and CFG1 mode to access configuration space PCI: PM: Fix pcie mrrs restoring pci: fix kabi error caused by pm_suspend_target_state LoongArch: Fixed some pcie card not scanning properly pci/quirks: ls7a2000: fix pm transition of devices under pcie port LS7A2000: PCIE: Fixup GPU card error pci: fix X server auto probe fail when both ast and etnaviv drm present LoongArch: pci root bridige set acpi companion only when not acpi_disabled. LoongArch: Fix secondary bridge routing errors pci: irq: Add early_param pci_irq_limit to limit pci irq numbers arch/loongarch/pci/acpi.c | 23 ++-- drivers/gpu/drm/loongson/loongson_module.c | 15 +++ drivers/irqchip/irq-loongson-pch-pic.c | 6 +- drivers/pci/controller/pci-loongson.c | 147 ++++++++++++++++++++- drivers/pci/msi/msi.c | 25 ++++ drivers/pci/pci.c | 20 ++- 6 files changed, 217 insertions(+), 19 deletions(-) -- 2.33.0

2 14

[PATCH 02/28] x86/bugs: Increase the x86 bugs vector size to two u32s
by Jialin Zhang 09 Oct '23

09 Oct '23

From: "Borislav Petkov (AMD)" <bp(a)alien8.de> stable inclusion from stable-v5.10.189 commit 073a28a9b50662991e7d6956c2cf2fc5d54f28cd category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I7RQ67 CVE: CVE-2023-20569 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- Upstream commit: 0e52740ffd10c6c316837c6c128f460f1aaba1ea There was never a doubt in my mind that they would not fit into a single u32 eventually. Signed-off-by: Borislav Petkov (AMD) <bp(a)alien8.de> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Conflicts: arch/x86/include/asm/cpufeatures.h tools/arch/x86/include/asm/cpufeatures.h Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> --- arch/x86/include/asm/cpufeatures.h | 2 +- tools/arch/x86/include/asm/cpufeatures.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 1a6680712025..f51fc445a24b 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -14,7 +14,7 @@ * Defines x86 CPU feature bits */ #define NCAPINTS 19 /* N 32-bit words worth of info */ -#define NBUGINTS 1 /* N 32-bit bug flags */ +#define NBUGINTS 2 /* N 32-bit bug flags */ /* * Note: If the comment begins with a quoted string, that string is used diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 238287abee0c..6186aebff9c0 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -14,7 +14,7 @@ * Defines x86 CPU feature bits */ #define NCAPINTS 19 /* N 32-bit words worth of info */ -#define NBUGINTS 1 /* N 32-bit bug flags */ +#define NBUGINTS 2 /* N 32-bit bug flags */ /* * Note: If the comment begins with a quoted string, that string is used -- 2.25.1

1 26

[PATCH OLK-5.10 0/3] uacce: uacce fixes some bugs
by Weili Qian 09 Oct '23

09 Oct '23

From: JiangShui Yang <yangjiangshui(a)h-partners.com> Weili Qian (3): uacce: fix NULL pointer when unbind device uacce: cleanup some unused codes uacce: remove unused file 'dev_state' drivers/crypto/hisilicon/qm.c | 12 ----- drivers/misc/uacce/uacce.c | 87 +++++++++++------------------------ include/linux/uacce.h | 17 ------- 3 files changed, 27 insertions(+), 89 deletions(-) -- 2.33.0

2 4

[PATCH OLK-5.10 00/19] Introduce PBHA and PBHA bit0 to control the usage of HBM Cache precisely
by Wupeng Ma 09 Oct '23

09 Oct '23

From: Ma Wupeng <mawupeng1(a)huawei.com> Patch 1: move FDT init out of kaslr_early_init for future use. Patch 2 to 8: enable feature PBHA for arm64. Patch 9-18: Control the usage of HBM cache for kernel and task precisely. Patch 19: Enable feature PBHA for arm64 by default. James Morse (7): KVM: arm64: Detect and enable PBHA for stage2 dt-bindings: Rename the description of cpu nodes cpu.yaml dt-bindings: arm: Add binding for Page Based Hardware Attributes arm64: cpufeature: Enable PBHA bits for stage1 arm64: mm: Add pgprot_pbha() to allow drivers to request PBHA values KVM: arm64: Configure PBHA bits for stage2 Documentation: arm64: Describe the support and expectations for PBHA Ma Wupeng (11): arm64: cpufeature: Enable PBHA for stage1 early via FDT arm64: mm: Detect and enable PBHA bit0 at early startup arm64: mm: Update kernel pte entries if pbha bit0 enabled arm64: mm: Show PBHA bit 59 as PBHA0 in ptdump arm64: mm: Introduce VM_PBHA_BIT0 to enable pbha bit0 for single vma arm64: mm: Set PBHA0 bit for VM_PBHA_BIT0 arm64: mm: Introduce sysfs interface to bypass whole task arm64: mm: Set flag VM_PBHA_BIT0 for global init task arm64: mm: Introduce prctl to control pbha behavior arm64: mm: Introduce kernel param pbha openeuler: configs: arm64: Enable PBHA by default Marc Zyngier (1): arm64: Extract early FDT mapping from kaslr_early_init() .../admin-guide/kernel-parameters.txt | 8 + Documentation/arm64/index.rst | 1 + Documentation/arm64/pbha.rst | 85 +++ .../devicetree/bindings/arm/cpu.yaml | 537 ++++++++++++++++ .../devicetree/bindings/arm/cpus.yaml | 584 +++--------------- arch/arm64/Kconfig | 20 + arch/arm64/configs/openeuler_defconfig | 1 + arch/arm64/include/asm/cpucaps.h | 3 + arch/arm64/include/asm/cpufeature.h | 15 + arch/arm64/include/asm/kvm_arm.h | 1 + arch/arm64/include/asm/kvm_pgtable.h | 9 + arch/arm64/include/asm/mman.h | 10 + arch/arm64/include/asm/pgtable-hwdef.h | 6 + arch/arm64/include/asm/pgtable.h | 26 + arch/arm64/include/asm/setup.h | 3 + arch/arm64/include/uapi/asm/mman.h | 1 + arch/arm64/kernel/cpufeature.c | 258 ++++++++ arch/arm64/kernel/head.S | 6 +- arch/arm64/kernel/image-vars.h | 3 + arch/arm64/kernel/kaslr.c | 7 +- arch/arm64/kernel/setup.c | 15 + arch/arm64/kvm/reset.c | 15 +- arch/arm64/mm/hugetlbpage.c | 2 + arch/arm64/mm/mmu.c | 14 +- arch/arm64/mm/ptdump.c | 5 + .../firmware/efi/libstub/efi-stub-helper.c | 3 + drivers/firmware/efi/libstub/fdt.c | 57 ++ drivers/soc/hisilicon/Makefile | 1 + drivers/soc/hisilicon/pbha.c | 204 ++++++ fs/proc/base.c | 103 +++ fs/proc/task_mmu.c | 3 + include/linux/mm.h | 8 +- include/linux/pbha.h | 67 ++ include/uapi/asm-generic/mman-common.h | 1 + include/uapi/linux/prctl.h | 2 + kernel/sys.c | 10 + mm/memory.c | 4 + mm/vmalloc.c | 5 + 38 files changed, 1580 insertions(+), 523 deletions(-) create mode 100644 Documentation/arm64/pbha.rst create mode 100644 Documentation/devicetree/bindings/arm/cpu.yaml create mode 100644 drivers/soc/hisilicon/pbha.c create mode 100644 include/linux/pbha.h -- 2.25.1

2 20

[PATCH OLK-5.10] net: ipv4: fix one memleak in __inet_del_ifa()
by Liu Jian 08 Oct '23

08 Oct '23

stable inclusion from stable-v5.10.195 commit 7c8ddcdab1b900bed69cad6beef477fff116289e category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I869PY CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… --------------------------- [ Upstream commit ac28b1ec6135649b5d78b028e47264cb3ebca5ea ] I got the below warning when do fuzzing test: unregister_netdevice: waiting for bond0 to become free. Usage count = 2 It can be repoduced via: ip link add bond0 type bond sysctl -w net.ipv4.conf.bond0.promote_secondaries=1 ip addr add 4.117.174.103/0 scope 0x40 dev bond0 ip addr add 192.168.100.111/255.255.255.254 scope 0 dev bond0 ip addr add 0.0.0.4/0 scope 0x40 secondary dev bond0 ip addr del 4.117.174.103/0 scope 0x40 dev bond0 ip link delete bond0 type bond In this reproduction test case, an incorrect 'last_prim' is found in __inet_del_ifa(), as a result, the secondary address(0.0.0.4/0 scope 0x40) is lost. The memory of the secondary address is leaked and the reference of in_device and net_device is leaked. Fix this problem: Look for 'last_prim' starting at location of the deleted IP and inserting the promoted IP into the location of 'last_prim'. Fixes: 0ff60a45678e ("[IPV4]: Fix secondary IP addresses after promotion") Signed-off-by: Liu Jian <liujian56(a)huawei.com> Signed-off-by: Julian Anastasov <ja(a)ssi.bg> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Liu Jian <liujian56(a)huawei.com> --- net/ipv4/devinet.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 88b6120878cd..da1ca8081c03 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -351,14 +351,14 @@ static void __inet_del_ifa(struct in_device *in_dev, { struct in_ifaddr *promote = NULL; struct in_ifaddr *ifa, *ifa1; - struct in_ifaddr *last_prim; + struct in_ifaddr __rcu **last_prim; struct in_ifaddr *prev_prom = NULL; int do_promote = IN_DEV_PROMOTE_SECONDARIES(in_dev); ASSERT_RTNL(); ifa1 = rtnl_dereference(*ifap); - last_prim = rtnl_dereference(in_dev->ifa_list); + last_prim = ifap; if (in_dev->dead) goto no_promotions; @@ -372,7 +372,7 @@ static void __inet_del_ifa(struct in_device *in_dev, while ((ifa = rtnl_dereference(*ifap1)) != NULL) { if (!(ifa->ifa_flags & IFA_F_SECONDARY) && ifa1->ifa_scope <= ifa->ifa_scope) - last_prim = ifa; + last_prim = &ifa->ifa_next; if (!(ifa->ifa_flags & IFA_F_SECONDARY) || ifa1->ifa_mask != ifa->ifa_mask || @@ -436,9 +436,9 @@ static void __inet_del_ifa(struct in_device *in_dev, rcu_assign_pointer(prev_prom->ifa_next, next_sec); - last_sec = rtnl_dereference(last_prim->ifa_next); + last_sec = rtnl_dereference(*last_prim); rcu_assign_pointer(promote->ifa_next, last_sec); - rcu_assign_pointer(last_prim->ifa_next, promote); + rcu_assign_pointer(*last_prim, promote); } promote->ifa_flags &= ~IFA_F_SECONDARY; -- 2.34.1

2 1

[PATCH 01/26] [Backport] tools headers cpufeatures: Sync with the kernel sources
by Jialin Zhang 08 Oct '23

08 Oct '23

From: Arnaldo Carvalho de Melo <acme(a)redhat.com> stable inclusion from stable-v5.10.189 commit 9b7fe7c6fbc007564f97805ff45882e79f0c70d0 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I7RQ67 CVE: CVE-2023-20569 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 1a9bcadd0058a3e81c1beca48e5e08dee9446a01 upstream. To pick the changes from: 3b9c723ed7cfa4e1 ("KVM: SVM: Add support for SVM instruction address check change") b85a0425d8056f3b ("Enumerate AVX Vector Neural Network instructions") fb35d30fe5b06cc2 ("x86/cpufeatures: Assign dedicated feature word for CPUID_0x8000001F[EAX]") This only causes these perf files to be rebuilt: CC /tmp/build/perf/bench/mem-memcpy-x86-64-asm.o CC /tmp/build/perf/bench/mem-memset-x86-64-asm.o And addresses this perf build warning: Warning: Kernel ABI header at 'tools/arch/x86/include/asm/cpufeatures.h' differs from latest version at 'arch/x86/include/asm/cpufeatures.h' diff -u tools/arch/x86/include/asm/cpufeatures.h arch/x86/include/asm/cpufeatures.h Cc: Borislav Petkov <bp(a)suse.de> Cc: Kyung Min Park <kyung.min.park(a)intel.com> Cc: Paolo Bonzini <pbonzini(a)redhat.com> Cc: Sean Christopherson <seanjc(a)google.com> Cc: Wei Huang <wei.huang2(a)amd.com> Signed-off-by: Arnaldo Carvalho de Melo <acme(a)redhat.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Conflicts: tools/arch/x86/include/asm/cpufeatures.h Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> --- tools/arch/x86/include/asm/cpufeatures.h | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 1a139412f78e..76a860a3d754 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -96,7 +96,7 @@ #define X86_FEATURE_SYSCALL32 ( 3*32+14) /* "" syscall in IA32 userspace */ #define X86_FEATURE_SYSENTER32 ( 3*32+15) /* "" sysenter in IA32 userspace */ #define X86_FEATURE_REP_GOOD ( 3*32+16) /* REP microcode works well */ -#define X86_FEATURE_SME_COHERENT ( 3*32+17) /* "" AMD hardware-enforced cache coherency */ +/* FREE! ( 3*32+17) */ #define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) /* "" LFENCE synchronizes RDTSC */ #define X86_FEATURE_ACC_POWER ( 3*32+19) /* AMD Accumulated Power Mechanism */ #define X86_FEATURE_NOPL ( 3*32+20) /* The NOPL (0F 1F) instructions */ @@ -201,7 +201,7 @@ #define X86_FEATURE_INVPCID_SINGLE ( 7*32+ 7) /* Effectively INVPCID && CR4.PCIDE=1 */ #define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ -#define X86_FEATURE_SME ( 7*32+10) /* AMD Secure Memory Encryption */ +/* FREE! ( 7*32+10) */ #define X86_FEATURE_PTI ( 7*32+11) /* Kernel Page Table Isolation enabled */ #define X86_FEATURE_KERNEL_IBRS ( 7*32+12) /* "" Set/clear IBRS on kernel entry/exit */ #define X86_FEATURE_RSB_VMEXIT ( 7*32+13) /* "" Fill RSB on VM-Exit */ @@ -211,7 +211,7 @@ #define X86_FEATURE_SSBD ( 7*32+17) /* Speculative Store Bypass Disable */ #define X86_FEATURE_MBA ( 7*32+18) /* Memory Bandwidth Allocation */ #define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* "" Fill RSB on context switches */ -#define X86_FEATURE_SEV ( 7*32+20) /* AMD Secure Encrypted Virtualization */ +/* FREE! ( 7*32+20) */ #define X86_FEATURE_USE_IBPB ( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */ #define X86_FEATURE_USE_IBRS_FW ( 7*32+22) /* "" Use IBRS during runtime firmware calls */ #define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE ( 7*32+23) /* "" Disable Speculative Store Bypass. */ @@ -236,7 +236,6 @@ #define X86_FEATURE_EPT_AD ( 8*32+17) /* Intel Extended Page Table access-dirty bit */ #define X86_FEATURE_VMCALL ( 8*32+18) /* "" Hypervisor supports the VMCALL instruction */ #define X86_FEATURE_VMW_VMMCALL ( 8*32+19) /* "" VMware prefers VMMCALL hypercall instruction */ -#define X86_FEATURE_SEV_ES ( 8*32+20) /* AMD Secure Encrypted Virtualization - Encrypted State */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */ #define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/ @@ -302,6 +301,7 @@ #define X86_FEATURE_MSR_TSX_CTRL (11*32+18) /* "" MSR IA32_TSX_CTRL (Intel) implemented */ /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ +#define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */ #define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */ /* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */ @@ -346,6 +346,7 @@ #define X86_FEATURE_AVIC (15*32+13) /* Virtual Interrupt Controller */ #define X86_FEATURE_V_VMSAVE_VMLOAD (15*32+15) /* Virtual VMSAVE VMLOAD */ #define X86_FEATURE_VGIF (15*32+16) /* Virtual GIF */ +#define X86_FEATURE_SVME_ADDR_CHK (15*32+28) /* "" SVME addr check */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (ECX), word 16 */ #define X86_FEATURE_AVX512VBMI (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/ @@ -374,6 +375,13 @@ #define X86_FEATURE_SUCCOR (17*32+ 1) /* Uncorrectable error containment and recovery */ #define X86_FEATURE_SMCA (17*32+ 3) /* Scalable MCA */ +/* AMD-defined memory encryption features, CPUID level 0x8000001f (EAX), word 19 */ +#define X86_FEATURE_SME (17*32+27) /* AMD Secure Memory Encryption */ +#define X86_FEATURE_SEV (17*32+28) /* AMD Secure Encrypted Virtualization */ +#define X86_FEATURE_VM_PAGE_FLUSH (17*32+29) /* "" VM Page Flush MSR is supported */ +#define X86_FEATURE_SEV_ES (17*32+30) /* AMD Secure Encrypted Virtualization - Encrypted State */ +#define X86_FEATURE_SME_COHERENT (17*32+31) /* "" AMD hardware-enforced cache coherency */ + /* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */ #define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* AVX-512 Neural Network Instructions */ #define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */ -- 2.25.1

1 25

[PATCH openEuler-1.0-LTS] quota: fix warning in dqgrab()
by Long Li 08 Oct '23

08 Oct '23

From: Ye Bin <yebin10(a)huawei.com> stable inclusion from stable-v4.19.273 commit 965bad2bf1afef64ec16249da676dc7310cca32e category: bugfix bugzilla: 188627, https://gitee.com/openeuler/kernel/issues/I85XNK CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?h=… -------------------------------- [ Upstream commit d6a95db3c7ad160bc16b89e36449705309b52bcb ] There's issue as follows when do fault injection: WARNING: CPU: 1 PID: 14870 at include/linux/quotaops.h:51 dquot_disable+0x13b7/0x18c0 Modules linked in: CPU: 1 PID: 14870 Comm: fsconfig Not tainted 6.3.0-next-20230505-00006-g5107a9c821af-dirty #541 RIP: 0010:dquot_disable+0x13b7/0x18c0 RSP: 0018:ffffc9000acc79e0 EFLAGS: 00010246 RAX: 0000000000000000 RBX: 0000000000000000 RCX: ffff88825e41b980 RDX: 0000000000000000 RSI: ffff88825e41b980 RDI: 0000000000000002 RBP: ffff888179f68000 R08: ffffffff82087ca7 R09: 0000000000000000 R10: 0000000000000001 R11: ffffed102f3ed026 R12: ffff888179f68130 R13: ffff888179f68110 R14: dffffc0000000000 R15: ffff888179f68118 FS: 00007f450a073740(0000) GS:ffff88882fc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007ffe96f2efd8 CR3: 000000025c8ad000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> dquot_load_quota_sb+0xd53/0x1060 dquot_resume+0x172/0x230 ext4_reconfigure+0x1dc6/0x27b0 reconfigure_super+0x515/0xa90 __x64_sys_fsconfig+0xb19/0xd20 do_syscall_64+0x39/0xb0 entry_SYSCALL_64_after_hwframe+0x63/0xcd Above issue may happens as follows: ProcessA ProcessB ProcessC sys_fsconfig vfs_fsconfig_locked reconfigure_super ext4_remount dquot_suspend -> suspend all type quota sys_fsconfig vfs_fsconfig_locked reconfigure_super ext4_remount dquot_resume ret = dquot_load_quota_sb add_dquot_ref do_open -> open file O_RDWR vfs_open do_dentry_open get_write_access atomic_inc_unless_negative(&inode->i_writecount) ext4_file_open dquot_file_open dquot_initialize __dquot_initialize dqget atomic_inc(&dquot->dq_count); __dquot_initialize __dquot_initialize dqget if (!test_bit(DQ_ACTIVE_B, &dquot->dq_flags)) ext4_acquire_dquot -> Return error DQ_ACTIVE_B flag isn't set dquot_disable invalidate_dquots if (atomic_read(&dquot->dq_count)) dqgrab WARN_ON_ONCE(!test_bit(DQ_ACTIVE_B, &dquot->dq_flags)) -> Trigger warning In the above scenario, 'dquot->dq_flags' has no DQ_ACTIVE_B is normal when dqgrab(). To solve above issue just replace the dqgrab() use in invalidate_dquots() with atomic_inc(&dquot->dq_count). Signed-off-by: Ye Bin <yebin10(a)huawei.com> Signed-off-by: Jan Kara <jack(a)suse.cz> Message-Id: <20230605140731.2427629-3-yebin10(a)huawei.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Long Li <leo.lilong(a)huawei.com> --- fs/quota/dquot.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index ca7a38ce46f5..b763b87dc2d0 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -577,7 +577,7 @@ static void invalidate_dquots(struct super_block *sb, int type) goto restart; } - dqgrab(dquot); + atomic_inc(&dquot->dq_count); spin_unlock(&dq_list_lock); /* * Once dqput() wakes us up, we know it's time to free -- 2.31.1

2 1

[PATCH openEuler-1.0-LTS] net: ipv4: fix one memleak in __inet_del_ifa()
by Liu Jian 08 Oct '23

08 Oct '23

mainline inclusion from mainline-v6.6-rc2 commit ac28b1ec6135649b5d78b028e47264cb3ebca5ea category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I869PY CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… --------------------------- I got the below warning when do fuzzing test: unregister_netdevice: waiting for bond0 to become free. Usage count = 2 It can be repoduced via: ip link add bond0 type bond sysctl -w net.ipv4.conf.bond0.promote_secondaries=1 ip addr add 4.117.174.103/0 scope 0x40 dev bond0 ip addr add 192.168.100.111/255.255.255.254 scope 0 dev bond0 ip addr add 0.0.0.4/0 scope 0x40 secondary dev bond0 ip addr del 4.117.174.103/0 scope 0x40 dev bond0 ip link delete bond0 type bond In this reproduction test case, an incorrect 'last_prim' is found in __inet_del_ifa(), as a result, the secondary address(0.0.0.4/0 scope 0x40) is lost. The memory of the secondary address is leaked and the reference of in_device and net_device is leaked. Fix this problem: Look for 'last_prim' starting at location of the deleted IP and inserting the promoted IP into the location of 'last_prim'. Fixes: 0ff60a45678e ("[IPV4]: Fix secondary IP addresses after promotion") Signed-off-by: Liu Jian <liujian56(a)huawei.com> Signed-off-by: Julian Anastasov <ja(a)ssi.bg> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Liu Jian <liujian56(a)huawei.com> Conflicts: net/ipv4/devinet.c --- net/ipv4/devinet.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 12a2cea9d606..64f0fa0be370 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -341,12 +341,13 @@ static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, { struct in_ifaddr *promote = NULL; struct in_ifaddr *ifa, *ifa1 = *ifap; - struct in_ifaddr *last_prim = in_dev->ifa_list; + struct in_ifaddr **last_prim; struct in_ifaddr *prev_prom = NULL; int do_promote = IN_DEV_PROMOTE_SECONDARIES(in_dev); ASSERT_RTNL(); + last_prim = ifap; if (in_dev->dead) goto no_promotions; @@ -360,7 +361,7 @@ static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, while ((ifa = *ifap1) != NULL) { if (!(ifa->ifa_flags & IFA_F_SECONDARY) && ifa1->ifa_scope <= ifa->ifa_scope) - last_prim = ifa; + last_prim = &ifa->ifa_next; if (!(ifa->ifa_flags & IFA_F_SECONDARY) || ifa1->ifa_mask != ifa->ifa_mask || @@ -420,8 +421,8 @@ static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, if (prev_prom) { prev_prom->ifa_next = promote->ifa_next; - promote->ifa_next = last_prim->ifa_next; - last_prim->ifa_next = promote; + promote->ifa_next = *last_prim; + *last_prim = promote; } promote->ifa_flags &= ~IFA_F_SECONDARY; -- 2.34.1

2 1

[PATCH OLK-5.10 v2] RDMA/irdma: Prevent zero-length STAG registration
by Liu Jian 08 Oct '23

08 Oct '23

From: Christopher Bednarz <christopher.n.bednarz(a)intel.com> mainline inclusion from mainline-v6.6-rc1 commit bb6d73d9add68ad270888db327514384dfa44958 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I7YFVN CVE: CVE-2023-25775 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… --------------------------- Currently irdma allows zero-length STAGs to be programmed in HW during the kernel mode fast register flow. Zero-length MR or STAG registration disable HW memory length checks. Improve gaps in bounds checking in irdma by preventing zero-length STAG or MR registrations except if the IB_PD_UNSAFE_GLOBAL_RKEY is set. This addresses the disclosure CVE-2023-25775. Fixes: b48c24c2d710 ("RDMA/irdma: Implement device supported verb APIs") Signed-off-by: Christopher Bednarz <christopher.n.bednarz(a)intel.com> Signed-off-by: Shiraz Saleem <shiraz.saleem(a)intel.com> Link: https://lore.kernel.org/r/20230818144838.1758-1-shiraz.saleem@intel.com Signed-off-by: Leon Romanovsky <leon(a)kernel.org> Signed-off-by: Liu Jian <liujian56(a)huawei.com> Conflicts: drivers/infiniband/hw/i40iw/i40iw_ctrl.c drivers/infiniband/hw/i40iw/i40iw_type.h drivers/infiniband/hw/i40iw/i40iw_verbs.c drivers/infiniband/hw/irdma/ctrl.c drivers/infiniband/hw/irdma/type.h drivers/infiniband/hw/irdma/verbs.c --- drivers/infiniband/hw/i40iw/i40iw_ctrl.c | 6 ++++++ drivers/infiniband/hw/i40iw/i40iw_type.h | 2 ++ drivers/infiniband/hw/i40iw/i40iw_verbs.c | 10 ++++++++-- 3 files changed, 16 insertions(+), 2 deletions(-) diff --git a/drivers/infiniband/hw/i40iw/i40iw_ctrl.c b/drivers/infiniband/hw/i40iw/i40iw_ctrl.c index 86d3f8aff329..2b18bb36e4e3 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_ctrl.c +++ b/drivers/infiniband/hw/i40iw/i40iw_ctrl.c @@ -3033,6 +3033,9 @@ static enum i40iw_status_code i40iw_sc_alloc_stag( u64 header; enum i40iw_page_size page_size; + if (!info->total_len && !info->all_memory) + return -EINVAL; + page_size = (info->page_size == 0x200000) ? I40IW_PAGE_SIZE_2M : I40IW_PAGE_SIZE_4K; cqp = dev->cqp; wqe = i40iw_sc_cqp_get_next_send_wqe(cqp, scratch); @@ -3091,6 +3094,9 @@ static enum i40iw_status_code i40iw_sc_mr_reg_non_shared( u8 addr_type; enum i40iw_page_size page_size; + if (!info->total_len && !info->all_memory) + return -EINVAL; + page_size = (info->page_size == 0x200000) ? I40IW_PAGE_SIZE_2M : I40IW_PAGE_SIZE_4K; if (info->access_rights & (I40IW_ACCESS_FLAGS_REMOTEREAD_ONLY | I40IW_ACCESS_FLAGS_REMOTEWRITE_ONLY)) diff --git a/drivers/infiniband/hw/i40iw/i40iw_type.h b/drivers/infiniband/hw/i40iw/i40iw_type.h index c3babf3cbb8e..341aa6b1b6c1 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_type.h +++ b/drivers/infiniband/hw/i40iw/i40iw_type.h @@ -786,6 +786,7 @@ struct i40iw_allocate_stag_info { bool use_hmc_fcn_index; u8 hmc_fcn_index; bool use_pf_rid; + bool all_memory; }; struct i40iw_reg_ns_stag_info { @@ -804,6 +805,7 @@ struct i40iw_reg_ns_stag_info { bool use_hmc_fcn_index; u8 hmc_fcn_index; bool use_pf_rid; + bool all_memory; }; struct i40iw_fast_reg_stag_info { diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.c b/drivers/infiniband/hw/i40iw/i40iw_verbs.c index 533f3caecb7a..89654dc91d81 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c +++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c @@ -1494,7 +1494,8 @@ static int i40iw_handle_q_mem(struct i40iw_device *iwdev, static int i40iw_hw_alloc_stag(struct i40iw_device *iwdev, struct i40iw_mr *iwmr) { struct i40iw_allocate_stag_info *info; - struct i40iw_pd *iwpd = to_iwpd(iwmr->ibmr.pd); + struct ib_pd *pd = iwmr->ibmr.pd; + struct i40iw_pd *iwpd = to_iwpd(pd); enum i40iw_status_code status; int err = 0; struct i40iw_cqp_request *cqp_request; @@ -1511,6 +1512,7 @@ static int i40iw_hw_alloc_stag(struct i40iw_device *iwdev, struct i40iw_mr *iwmr info->stag_idx = iwmr->stag >> I40IW_CQPSQ_STAG_IDX_SHIFT; info->pd_id = iwpd->sc_pd.pd_id; info->total_len = iwmr->length; + info->all_memory = pd->flags & IB_PD_UNSAFE_GLOBAL_RKEY; info->remote_access = true; cqp_info->cqp_cmd = OP_ALLOC_STAG; cqp_info->post_sq = 1; @@ -1563,6 +1565,8 @@ static struct ib_mr *i40iw_alloc_mr(struct ib_pd *pd, enum ib_mr_type mr_type, iwmr->type = IW_MEMREG_TYPE_MEM; palloc = &iwpbl->pble_alloc; iwmr->page_cnt = max_num_sg; + /* Use system PAGE_SIZE as the sg page sizes are unknown at this point */ + iwmr->length = max_num_sg * PAGE_SIZE; mutex_lock(&iwdev->pbl_mutex); status = i40iw_get_pble(&iwdev->sc_dev, iwdev->pble_rsrc, palloc, iwmr->page_cnt); mutex_unlock(&iwdev->pbl_mutex); @@ -1659,7 +1663,8 @@ static int i40iw_hwreg_mr(struct i40iw_device *iwdev, { struct i40iw_pbl *iwpbl = &iwmr->iwpbl; struct i40iw_reg_ns_stag_info *stag_info; - struct i40iw_pd *iwpd = to_iwpd(iwmr->ibmr.pd); + struct ib_pd *pd = iwmr->ibmr.pd; + struct i40iw_pd *iwpd = to_iwpd(pd); struct i40iw_pble_alloc *palloc = &iwpbl->pble_alloc; enum i40iw_status_code status; int err = 0; @@ -1679,6 +1684,7 @@ static int i40iw_hwreg_mr(struct i40iw_device *iwdev, stag_info->total_len = iwmr->length; stag_info->access_rights = access; stag_info->pd_id = iwpd->sc_pd.pd_id; + stag_info->all_memory = pd->flags & IB_PD_UNSAFE_GLOBAL_RKEY; stag_info->addr_type = I40IW_ADDR_TYPE_VA_BASED; stag_info->page_size = iwmr->page_size; -- 2.34.1

2 1

[PATCH openEuler-1.0-LTS v2] RDMA/irdma: Prevent zero-length STAG registration
by Liu Jian 08 Oct '23

08 Oct '23

From: Christopher Bednarz <christopher.n.bednarz(a)intel.com> mainline inclusion from mainline-v6.6-rc1 commit bb6d73d9add68ad270888db327514384dfa44958 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I7YFVN CVE: CVE-2023-25775 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… --------------------------- Currently irdma allows zero-length STAGs to be programmed in HW during the kernel mode fast register flow. Zero-length MR or STAG registration disable HW memory length checks. Improve gaps in bounds checking in irdma by preventing zero-length STAG or MR registrations except if the IB_PD_UNSAFE_GLOBAL_RKEY is set. This addresses the disclosure CVE-2023-25775. Fixes: b48c24c2d710 ("RDMA/irdma: Implement device supported verb APIs") Signed-off-by: Christopher Bednarz <christopher.n.bednarz(a)intel.com> Signed-off-by: Shiraz Saleem <shiraz.saleem(a)intel.com> Link: https://lore.kernel.org/r/20230818144838.1758-1-shiraz.saleem@intel.com Signed-off-by: Leon Romanovsky <leon(a)kernel.org> Signed-off-by: Liu Jian <liujian56(a)huawei.com> Conflicts: drivers/infiniband/hw/i40iw/i40iw_ctrl.c drivers/infiniband/hw/i40iw/i40iw_type.h drivers/infiniband/hw/i40iw/i40iw_verbs.c drivers/infiniband/hw/irdma/ctrl.c drivers/infiniband/hw/irdma/type.h drivers/infiniband/hw/irdma/verbs.c --- drivers/infiniband/hw/i40iw/i40iw_ctrl.c | 6 ++++++ drivers/infiniband/hw/i40iw/i40iw_type.h | 2 ++ drivers/infiniband/hw/i40iw/i40iw_verbs.c | 10 ++++++++-- 3 files changed, 16 insertions(+), 2 deletions(-) diff --git a/drivers/infiniband/hw/i40iw/i40iw_ctrl.c b/drivers/infiniband/hw/i40iw/i40iw_ctrl.c index 4d841a3c68f3..026557aa2307 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_ctrl.c +++ b/drivers/infiniband/hw/i40iw/i40iw_ctrl.c @@ -2945,6 +2945,9 @@ static enum i40iw_status_code i40iw_sc_alloc_stag( u64 header; enum i40iw_page_size page_size; + if (!info->total_len && !info->all_memory) + return -EINVAL; + page_size = (info->page_size == 0x200000) ? I40IW_PAGE_SIZE_2M : I40IW_PAGE_SIZE_4K; cqp = dev->cqp; wqe = i40iw_sc_cqp_get_next_send_wqe(cqp, scratch); @@ -3003,6 +3006,9 @@ static enum i40iw_status_code i40iw_sc_mr_reg_non_shared( u8 addr_type; enum i40iw_page_size page_size; + if (!info->total_len && !info->all_memory) + return -EINVAL; + page_size = (info->page_size == 0x200000) ? I40IW_PAGE_SIZE_2M : I40IW_PAGE_SIZE_4K; if (info->access_rights & (I40IW_ACCESS_FLAGS_REMOTEREAD_ONLY | I40IW_ACCESS_FLAGS_REMOTEWRITE_ONLY)) diff --git a/drivers/infiniband/hw/i40iw/i40iw_type.h b/drivers/infiniband/hw/i40iw/i40iw_type.h index adc8d2ec523d..5c4e2f206105 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_type.h +++ b/drivers/infiniband/hw/i40iw/i40iw_type.h @@ -779,6 +779,7 @@ struct i40iw_allocate_stag_info { bool use_hmc_fcn_index; u8 hmc_fcn_index; bool use_pf_rid; + bool all_memory; }; struct i40iw_reg_ns_stag_info { @@ -797,6 +798,7 @@ struct i40iw_reg_ns_stag_info { bool use_hmc_fcn_index; u8 hmc_fcn_index; bool use_pf_rid; + bool all_memory; }; struct i40iw_fast_reg_stag_info { diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.c b/drivers/infiniband/hw/i40iw/i40iw_verbs.c index a5e3349b8a7c..9cf8bf2c87e7 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c +++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c @@ -1603,7 +1603,8 @@ static int i40iw_handle_q_mem(struct i40iw_device *iwdev, static int i40iw_hw_alloc_stag(struct i40iw_device *iwdev, struct i40iw_mr *iwmr) { struct i40iw_allocate_stag_info *info; - struct i40iw_pd *iwpd = to_iwpd(iwmr->ibmr.pd); + struct ib_pd *pd = iwmr->ibmr.pd; + struct i40iw_pd *iwpd = to_iwpd(pd); enum i40iw_status_code status; int err = 0; struct i40iw_cqp_request *cqp_request; @@ -1620,6 +1621,7 @@ static int i40iw_hw_alloc_stag(struct i40iw_device *iwdev, struct i40iw_mr *iwmr info->stag_idx = iwmr->stag >> I40IW_CQPSQ_STAG_IDX_SHIFT; info->pd_id = iwpd->sc_pd.pd_id; info->total_len = iwmr->length; + info->all_memory = pd->flags & IB_PD_UNSAFE_GLOBAL_RKEY; info->remote_access = true; cqp_info->cqp_cmd = OP_ALLOC_STAG; cqp_info->post_sq = 1; @@ -1673,6 +1675,8 @@ static struct ib_mr *i40iw_alloc_mr(struct ib_pd *pd, iwmr->type = IW_MEMREG_TYPE_MEM; palloc = &iwpbl->pble_alloc; iwmr->page_cnt = max_num_sg; + /* Use system PAGE_SIZE as the sg page sizes are unknown at this point */ + iwmr->length = max_num_sg * PAGE_SIZE; mutex_lock(&iwdev->pbl_mutex); status = i40iw_get_pble(&iwdev->sc_dev, iwdev->pble_rsrc, palloc, iwmr->page_cnt); mutex_unlock(&iwdev->pbl_mutex); @@ -1769,7 +1773,8 @@ static int i40iw_hwreg_mr(struct i40iw_device *iwdev, { struct i40iw_pbl *iwpbl = &iwmr->iwpbl; struct i40iw_reg_ns_stag_info *stag_info; - struct i40iw_pd *iwpd = to_iwpd(iwmr->ibmr.pd); + struct ib_pd *pd = iwmr->ibmr.pd; + struct i40iw_pd *iwpd = to_iwpd(pd); struct i40iw_pble_alloc *palloc = &iwpbl->pble_alloc; enum i40iw_status_code status; int err = 0; @@ -1789,6 +1794,7 @@ static int i40iw_hwreg_mr(struct i40iw_device *iwdev, stag_info->total_len = iwmr->length; stag_info->access_rights = access; stag_info->pd_id = iwpd->sc_pd.pd_id; + stag_info->all_memory = pd->flags & IB_PD_UNSAFE_GLOBAL_RKEY; stag_info->addr_type = I40IW_ADDR_TYPE_VA_BASED; stag_info->page_size = iwmr->page_size; -- 2.34.1

2 1

[PATCH openEuler-1.0-LTS 0/2] Backport lts bugfix patch for macvlan
by Ziyang Xuan 08 Oct '23

08 Oct '23

Backport lts commit f916e5988ae4 ("bonding: fix macvlan over alb bond support"). Hangbin Liu (1): bonding: fix macvlan over alb bond support Jakub Kicinski (1): net: remove bond_slave_has_mac_rcu() drivers/net/bonding/bond_alb.c | 6 +++--- include/net/bonding.h | 25 +------------------------ 2 files changed, 4 insertions(+), 27 deletions(-) -- 2.25.1

2 3

[PATCH openEuler-1.0-LTS 0/2] PCI: acpiphp: linux-4.19.y bugfixes backport
by Jialin Zhang 08 Oct '23

08 Oct '23

Igor Mammedov (2): PCI: acpiphp: Reassign resources on bridge if necessary PCI: acpiphp: Use pci_assign_unassigned_bridge_resources() only for non-root bus drivers/pci/hotplug/acpiphp_glue.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) -- 2.25.1

2 3

[PATCH OLK-5.10 v3 00/44] xfs: recent patches to fix xfs issues
by Long Li 08 Oct '23

08 Oct '23

Baokun Li (1): xfs: propagate the return value of xfs_log_force() to avoid soft lockup Colin Ian King (2): xfs: remove redundant initializations of pointers drop_leaf and save_leaf xfs: remove redundant pointer lip Darrick J. Wong (9): xfs: use setattr_copy to set vfs inode attributes xfs: remove kmem_zone typedef xfs: rename _zone variables to _cache xfs: compact deferred intent item structures xfs: create slab caches for frequently-used deferred items xfs: rename xfs_bmap_add_free to xfs_free_extent_later xfs: reduce the size of struct xfs_extent_free_item xfs: remove unused parameter from refcount code xfs: pass xfs_extent_free_item directly through the log intent code Dave Chinner (19): xfs: don't assert fail on perag references on teardown xfs: set prealloc flag in xfs_alloc_file_space() xfs: validity check agbnos on the AGFL xfs: validate block number being freed before adding to xefi xfs: don't reverse order of items in bulk AIL insertion xfs: use deferred frees for btree block freeing xfs: pass alloc flags through to xfs_extent_busy_flush() xfs: allow extent free intents to be retried xfs: don't block in busy flushing when freeing extents xfs: journal geometry is not properly bounds checked xfs: AGF length has never been bounds checked xfs: fix bounds check in xfs_defer_agfl_block() xfs: block reservation too large for minleft allocation xfs: punching delalloc extents on write failure is racy xfs: use byte ranges for write cleanup ranges xfs,iomap: move delalloc punching to iomap iomap: buffered write failure should not truncate the page cache xfs: xfs_bmap_punch_delalloc_range() should take a byte range xfs: fix off-by-one-block in xfs_discard_folio() Gaosheng Cui (1): xfs: remove xfs_setattr_time() declaration Guo Xuenan (1): xfs: set minleft correctly for randomly sparse inode allocations Jiapeng Chong (1): xfs: Remove redundant assignment to busy Long Li (6): xfs: fix dir3 block read verify fail during log recover Revert "xfs: propagate the return value of xfs_log_force() to avoid soft lockup" xfs: xfs_trans_cancel() path must check for log shutdown xfs: don't verify agf length when log recovery xfs: shutdown to ensure submits buffers on LSN boundaries xfs: update the last_sync_lsn with ctx start lsn yangerkun (4): xfs: keep growfs sb log item active until ail flush success xfs: fix xfs shutdown since we reserve more blocks in agfl fixup xfs: longest free extent no need consider postalloc xfs: shutdown xfs once inode double free fs/xfs/kmem.h | 4 - fs/xfs/libxfs/xfs_alloc.c | 390 +++++++++++++++++++++-------- fs/xfs/libxfs/xfs_alloc.h | 51 +++- fs/xfs/libxfs/xfs_alloc_btree.c | 2 +- fs/xfs/libxfs/xfs_attr_leaf.c | 2 - fs/xfs/libxfs/xfs_bmap.c | 90 +++---- fs/xfs/libxfs/xfs_bmap.h | 37 +-- fs/xfs/libxfs/xfs_bmap_btree.c | 27 +- fs/xfs/libxfs/xfs_btree.c | 4 +- fs/xfs/libxfs/xfs_btree.h | 2 +- fs/xfs/libxfs/xfs_da_btree.c | 6 +- fs/xfs/libxfs/xfs_da_btree.h | 3 +- fs/xfs/libxfs/xfs_defer.c | 70 +++++- fs/xfs/libxfs/xfs_defer.h | 3 + fs/xfs/libxfs/xfs_ialloc.c | 32 ++- fs/xfs/libxfs/xfs_ialloc_btree.c | 8 +- fs/xfs/libxfs/xfs_inode_fork.c | 4 +- fs/xfs/libxfs/xfs_inode_fork.h | 2 +- fs/xfs/libxfs/xfs_refcount.c | 56 +++-- fs/xfs/libxfs/xfs_refcount.h | 7 +- fs/xfs/libxfs/xfs_refcount_btree.c | 11 +- fs/xfs/libxfs/xfs_rmap.c | 21 +- fs/xfs/libxfs/xfs_rmap.h | 7 +- fs/xfs/libxfs/xfs_rmap_btree.c | 2 +- fs/xfs/libxfs/xfs_sb.c | 56 ++++- fs/xfs/libxfs/xfs_types.c | 23 ++ fs/xfs/libxfs/xfs_types.h | 2 + fs/xfs/xfs_aops.c | 32 +-- fs/xfs/xfs_bmap_item.c | 16 +- fs/xfs/xfs_bmap_item.h | 6 +- fs/xfs/xfs_bmap_util.c | 19 +- fs/xfs/xfs_bmap_util.h | 2 +- fs/xfs/xfs_buf.c | 16 +- fs/xfs/xfs_buf_item.c | 10 +- fs/xfs/xfs_buf_item.h | 11 +- fs/xfs/xfs_buf_item_recover.c | 9 +- fs/xfs/xfs_dquot.c | 26 +- fs/xfs/xfs_extent_busy.c | 36 ++- fs/xfs/xfs_extent_busy.h | 6 +- fs/xfs/xfs_extfree_item.c | 137 +++++++--- fs/xfs/xfs_extfree_item.h | 6 +- fs/xfs/xfs_file.c | 8 - fs/xfs/xfs_icache.c | 8 +- fs/xfs/xfs_icreate_item.c | 6 +- fs/xfs/xfs_icreate_item.h | 2 +- fs/xfs/xfs_inode.c | 2 +- fs/xfs/xfs_inode.h | 2 +- fs/xfs/xfs_inode_item.c | 6 +- fs/xfs/xfs_inode_item.h | 2 +- fs/xfs/xfs_iomap.c | 292 ++++++++++++++++++--- fs/xfs/xfs_iops.c | 56 +---- fs/xfs/xfs_iops.h | 1 - fs/xfs/xfs_log.c | 72 +++--- fs/xfs/xfs_log_priv.h | 2 +- fs/xfs/xfs_log_recover.c | 6 +- fs/xfs/xfs_mount.c | 12 +- fs/xfs/xfs_mru_cache.c | 2 +- fs/xfs/xfs_pnfs.c | 3 +- fs/xfs/xfs_qm.h | 2 +- fs/xfs/xfs_refcount_item.c | 16 +- fs/xfs/xfs_refcount_item.h | 6 +- fs/xfs/xfs_reflink.c | 7 +- fs/xfs/xfs_rmap_item.c | 16 +- fs/xfs/xfs_rmap_item.h | 6 +- fs/xfs/xfs_super.c | 233 ++++++++--------- fs/xfs/xfs_trans.c | 24 +- fs/xfs/xfs_trans.h | 2 +- fs/xfs/xfs_trans_ail.c | 5 +- fs/xfs/xfs_trans_dquot.c | 4 +- mm/filemap.c | 1 + 70 files changed, 1358 insertions(+), 700 deletions(-) -- 2.31.1

2 45

[PATCH openEuler-1.0-LTS] mm: memory-failure: use rcu lock instead of tasklist_lock when collect_procs()
by Tong Tiangen 08 Oct '23

08 Oct '23

mainline inclusion from mainline-v6.6-rc1 commit d256d1cd8da1cbc4615de69df71c87ce623fec2f category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I85WL9 CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- We found a softlock issue in our test, analyzed the logs, and found that the relevant CPU call trace as follows: CPU0: _do_fork -> copy_process() -> write_lock_irq(&tasklist_lock) //Disable irq,waiting for //tasklist_lock CPU1: wp_page_copy() ->pte_offset_map_lock() -> spin_lock(&page->ptl); //Hold page->ptl -> ptep_clear_flush() -> flush_tlb_others() ... -> smp_call_function_many() -> arch_send_call_function_ipi_mask() -> csd_lock_wait() //Waiting for other CPUs respond //IPI CPU2: collect_procs_anon() -> read_lock(&tasklist_lock) //Hold tasklist_lock ->for_each_process(tsk) -> page_mapped_in_vma() -> page_vma_mapped_walk() -> map_pte() ->spin_lock(&page->ptl) //Waiting for page->ptl We can see that CPU1 waiting for CPU0 respond IPI，CPU0 waiting for CPU2 unlock tasklist_lock, CPU2 waiting for CPU1 unlock page->ptl. As a result, softlockup is triggered. For collect_procs_anon(), what we're doing is task list iteration, during the iteration, with the help of call_rcu(), the task_struct object is freed only after one or more grace periods elapse. the logic as follows: release_task() -> __exit_signal() -> __unhash_process() -> list_del_rcu() -> put_task_struct_rcu_user() -> call_rcu(&task->rcu, delayed_put_task_struct) delayed_put_task_struct() -> put_task_struct() -> if (refcount_sub_and_test()) __put_task_struct() -> free_task() Therefore, under the protection of the rcu lock, we can safely use get_task_struct() to ensure a safe reference to task_struct during the iteration. By removing the use of tasklist_lock in task list iteration, we can break the softlock chain above. The same logic can also be applied to: - collect_procs_file() - collect_procs_fsdax() - collect_procs_ksm() Link: https://lkml.kernel.org/r/20230828022527.241693-1-tongtiangen@huawei.com Signed-off-by: Tong Tiangen <tongtiangen(a)huawei.com> Acked-by: Naoya Horiguchi <naoya.horiguchi(a)nec.com> Cc: Kefeng Wang <wangkefeng.wang(a)huawei.com> Cc: Matthew Wilcox (Oracle) <willy(a)infradead.org> Cc: Miaohe Lin <linmiaohe(a)huawei.com> Cc: Paul E. McKenney <paulmck(a)kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Conflicts: mm/filemap.c mm/ksm.c mm/memory-failure.c Signed-off-by: Tong Tiangen <tongtiangen(a)huawei.com> --- mm/filemap.c | 3 --- mm/memory-failure.c | 12 ++++++------ 2 files changed, 6 insertions(+), 9 deletions(-) diff --git a/mm/filemap.c b/mm/filemap.c index f33504b784a2..5bf4645256cb 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -166,9 +166,6 @@ static void page_cache_kill(struct page *page) * bdi.wb->list_lock (zap_pte_range->set_page_dirty) * ->inode->i_lock (zap_pte_range->set_page_dirty) * ->private_lock (zap_pte_range->__set_page_dirty_buffers) - * - * ->i_mmap_rwsem - * ->tasklist_lock (memory_failure, collect_procs_ao) */ static int page_cache_tree_insert(struct address_space *mapping, diff --git a/mm/memory-failure.c b/mm/memory-failure.c index fff715a27253..8924d7d9bffa 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -427,8 +427,8 @@ static void kill_procs(struct list_head *to_kill, int forcekill, bool fail, * on behalf of the thread group. Return task_struct of the (first found) * dedicated thread if found, and return NULL otherwise. * - * We already hold read_lock(&tasklist_lock) in the caller, so we don't - * have to call rcu_read_lock/unlock() in this function. + * We already hold rcu lock in the caller, so we don't have to call + * rcu_read_lock/unlock() in this function. */ static struct task_struct *find_early_kill_thread(struct task_struct *tsk) { @@ -478,7 +478,7 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill, return; pgoff = page_to_pgoff(page); - read_lock(&tasklist_lock); + rcu_read_lock(); for_each_process (tsk) { struct anon_vma_chain *vmac; struct task_struct *t = task_early_kill(tsk, force_early); @@ -494,7 +494,7 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill, add_to_kill(t, page, vma, to_kill, tkc); } } - read_unlock(&tasklist_lock); + rcu_read_unlock(); page_unlock_anon_vma_read(av); } @@ -509,7 +509,7 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill, struct address_space *mapping = page->mapping; i_mmap_lock_read(mapping); - read_lock(&tasklist_lock); + rcu_read_lock(); for_each_process(tsk) { pgoff_t pgoff = page_to_pgoff(page); struct task_struct *t = task_early_kill(tsk, force_early); @@ -529,7 +529,7 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill, add_to_kill(t, page, vma, to_kill, tkc); } } - read_unlock(&tasklist_lock); + rcu_read_unlock(); i_mmap_unlock_read(mapping); } -- 2.25.1

2 1

[PATCH openEuler-1.0-LTS v2] x86/topology: Fix erroneous smp_num_siblings on Intel Hybrid platforms
by Yu Liao 08 Oct '23

08 Oct '23

From: Zhang Rui <rui.zhang(a)intel.com> stable inclusion from stable-v4.19.293 commit f5867e5b6a780710251318cb2047e24c49935e43 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I85XNK CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit edc0a2b5957652f4685ef3516f519f84807087db ] Traditionally, all CPUs in a system have identical numbers of SMT siblings. That changes with hybrid processors where some logical CPUs have a sibling and others have none. Today, the CPU boot code sets the global variable smp_num_siblings when every CPU thread is brought up. The last thread to boot will overwrite it with the number of siblings of *that* thread. That last thread to boot will "win". If the thread is a Pcore, smp_num_siblings == 2. If it is an Ecore, smp_num_siblings == 1. smp_num_siblings describes if the *system* supports SMT. It should specify the maximum number of SMT threads among all cores. Ensure that smp_num_siblings represents the system-wide maximum number of siblings by always increasing its value. Never allow it to decrease. On MeteorLake-P platform, this fixes a problem that the Ecore CPUs are not updated in any cpu sibling map because the system is treated as an UP system when probing Ecore CPUs. Below shows part of the CPU topology information before and after the fix, for both Pcore and Ecore CPU (cpu0 is Pcore, cpu 12 is Ecore). ... -/sys/devices/system/cpu/cpu0/topology/package_cpus:000fff -/sys/devices/system/cpu/cpu0/topology/package_cpus_list:0-11 +/sys/devices/system/cpu/cpu0/topology/package_cpus:3fffff +/sys/devices/system/cpu/cpu0/topology/package_cpus_list:0-21 ... -/sys/devices/system/cpu/cpu12/topology/package_cpus:001000 -/sys/devices/system/cpu/cpu12/topology/package_cpus_list:12 +/sys/devices/system/cpu/cpu12/topology/package_cpus:3fffff +/sys/devices/system/cpu/cpu12/topology/package_cpus_list:0-21 Notice that the "before" 'package_cpus_list' has only one CPU. This means that userspace tools like lscpu will see a little laptop like an 11-socket system: -Core(s) per socket: 1 -Socket(s): 11 +Core(s) per socket: 16 +Socket(s): 1 This is also expected to make the scheduler do rather wonky things too. [ dhansen: remove CPUID detail from changelog, add end user effects ] CC: stable(a)kernel.org Fixes: bbb65d2d365e ("x86: use cpuid vector 0xb when available for detecting cpu topology") Fixes: 95f3d39ccf7a ("x86/cpu/topology: Provide detect_extended_topology_early()") Suggested-by: Len Brown <len.brown(a)intel.com> Signed-off-by: Zhang Rui <rui.zhang(a)intel.com> Signed-off-by: Dave Hansen <dave.hansen(a)linux.intel.com> Acked-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Link: https://lore.kernel.org/all/20230323015640.27906-1-rui.zhang%40intel.com Signed-off-by: Sasha Levin <sashal(a)kernel.org> Conflicts: arch/x86/kernel/cpu/topology.c Signed-off-by: Yu Liao <liaoyu15(a)huawei.com> --- arch/x86/kernel/cpu/topology.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c index 7c130bdfd746..5c15e1329fcb 100644 --- a/arch/x86/kernel/cpu/topology.c +++ b/arch/x86/kernel/cpu/topology.c @@ -77,7 +77,7 @@ int detect_extended_topology_early(struct cpuinfo_x86 *c) * initial apic id, which also represents 32-bit extended x2apic id. */ c->initial_apicid = edx; - smp_num_siblings = LEVEL_MAX_SIBLINGS(ebx); + smp_num_siblings = max_t(int, smp_num_siblings, LEVEL_MAX_SIBLINGS(ebx)); #endif return 0; } @@ -106,7 +106,8 @@ int detect_extended_topology(struct cpuinfo_x86 *c) */ cpuid_count(leaf, SMT_LEVEL, &eax, &ebx, &ecx, &edx); c->initial_apicid = edx; - core_level_siblings = smp_num_siblings = LEVEL_MAX_SIBLINGS(ebx); + core_level_siblings = LEVEL_MAX_SIBLINGS(ebx); + smp_num_siblings = max_t(int, smp_num_siblings, LEVEL_MAX_SIBLINGS(ebx)); core_plus_mask_width = ht_mask_width = BITS_SHIFT_NEXT_LEVEL(eax); die_level_siblings = LEVEL_MAX_SIBLINGS(ebx); die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax); -- 2.25.1

2 1

[PATCH openEuler-1.0-LTS] x86/topology: Fix erroneous smp_num_siblings on Intel Hybrid platforms
by Yu Liao 07 Oct '23

07 Oct '23

From: Zhang Rui <rui.zhang(a)intel.com> stable inclusion from stable-v4.19.293 commit f5867e5b6a780710251318cb2047e24c49935e43 category: bugfix bugzilla: 188350 CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit edc0a2b5957652f4685ef3516f519f84807087db ] Traditionally, all CPUs in a system have identical numbers of SMT siblings. That changes with hybrid processors where some logical CPUs have a sibling and others have none. Today, the CPU boot code sets the global variable smp_num_siblings when every CPU thread is brought up. The last thread to boot will overwrite it with the number of siblings of *that* thread. That last thread to boot will "win". If the thread is a Pcore, smp_num_siblings == 2. If it is an Ecore, smp_num_siblings == 1. smp_num_siblings describes if the *system* supports SMT. It should specify the maximum number of SMT threads among all cores. Ensure that smp_num_siblings represents the system-wide maximum number of siblings by always increasing its value. Never allow it to decrease. On MeteorLake-P platform, this fixes a problem that the Ecore CPUs are not updated in any cpu sibling map because the system is treated as an UP system when probing Ecore CPUs. Below shows part of the CPU topology information before and after the fix, for both Pcore and Ecore CPU (cpu0 is Pcore, cpu 12 is Ecore). ... -/sys/devices/system/cpu/cpu0/topology/package_cpus:000fff -/sys/devices/system/cpu/cpu0/topology/package_cpus_list:0-11 +/sys/devices/system/cpu/cpu0/topology/package_cpus:3fffff +/sys/devices/system/cpu/cpu0/topology/package_cpus_list:0-21 ... -/sys/devices/system/cpu/cpu12/topology/package_cpus:001000 -/sys/devices/system/cpu/cpu12/topology/package_cpus_list:12 +/sys/devices/system/cpu/cpu12/topology/package_cpus:3fffff +/sys/devices/system/cpu/cpu12/topology/package_cpus_list:0-21 Notice that the "before" 'package_cpus_list' has only one CPU. This means that userspace tools like lscpu will see a little laptop like an 11-socket system: -Core(s) per socket: 1 -Socket(s): 11 +Core(s) per socket: 16 +Socket(s): 1 This is also expected to make the scheduler do rather wonky things too. [ dhansen: remove CPUID detail from changelog, add end user effects ] CC: stable(a)kernel.org Fixes: bbb65d2d365e ("x86: use cpuid vector 0xb when available for detecting cpu topology") Fixes: 95f3d39ccf7a ("x86/cpu/topology: Provide detect_extended_topology_early()") Suggested-by: Len Brown <len.brown(a)intel.com> Signed-off-by: Zhang Rui <rui.zhang(a)intel.com> Signed-off-by: Dave Hansen <dave.hansen(a)linux.intel.com> Acked-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Link: https://lore.kernel.org/all/20230323015640.27906-1-rui.zhang%40intel.com Signed-off-by: Sasha Levin <sashal(a)kernel.org> Conflicts: arch/x86/kernel/cpu/topology.c Signed-off-by: Yu Liao <liaoyu15(a)huawei.com> --- arch/x86/kernel/cpu/topology.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c index 7c130bdfd746..5c15e1329fcb 100644 --- a/arch/x86/kernel/cpu/topology.c +++ b/arch/x86/kernel/cpu/topology.c @@ -77,7 +77,7 @@ int detect_extended_topology_early(struct cpuinfo_x86 *c) * initial apic id, which also represents 32-bit extended x2apic id. */ c->initial_apicid = edx; - smp_num_siblings = LEVEL_MAX_SIBLINGS(ebx); + smp_num_siblings = max_t(int, smp_num_siblings, LEVEL_MAX_SIBLINGS(ebx)); #endif return 0; } @@ -106,7 +106,8 @@ int detect_extended_topology(struct cpuinfo_x86 *c) */ cpuid_count(leaf, SMT_LEVEL, &eax, &ebx, &ecx, &edx); c->initial_apicid = edx; - core_level_siblings = smp_num_siblings = LEVEL_MAX_SIBLINGS(ebx); + core_level_siblings = LEVEL_MAX_SIBLINGS(ebx); + smp_num_siblings = max_t(int, smp_num_siblings, LEVEL_MAX_SIBLINGS(ebx)); core_plus_mask_width = ht_mask_width = BITS_SHIFT_NEXT_LEVEL(eax); die_level_siblings = LEVEL_MAX_SIBLINGS(ebx); die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax); -- 2.25.1

2 1

[PATCH OLK-5.10 00/28] fix CVE-2023-20569
by Jialin Zhang 07 Oct '23

07 Oct '23

New architectural features and CPUID bits related to the Speculative Return Stack Overflow (SRSO) vulnerability. Arnaldo Carvalho de Melo (2): tools headers cpufeatures: Sync with the kernel sources tools arch x86: Sync the msr-index.h copy with the kernel sources Borislav Petkov (AMD) (9): x86/bugs: Increase the x86 bugs vector size to two u32s x86/srso: Add a Speculative RAS Overflow mitigation x86/srso: Add IBPB_BRTYPE support x86/srso: Add SRSO_NO support x86/srso: Add IBPB x86/srso: Add IBPB on VMEXIT x86/srso: Tie SBPB bit setting to microcode patch detection x86/srso: Disable the mitigation on unaffected configurations x86/srso: Correct the mitigation status when SMT is disabled Jialin Zhang (1): x86/cpufeatures: Fix abi breakage caused by NCAPINTS in cpufeature header file. Josh Poimboeuf (2): x86/srso: Fix return thunks in generated code objtool: Add frame-pointer-specific function ignore Kim Phillips (1): x86/cpu, kvm: Add support for CPUID_80000021_EAX Nick Desaulniers (1): x86/srso: Fix build breakage with the LLVM linker Nikolay Borisov (1): kabi: Allow extra bugsints (bsc#1213927). Peter Zijlstra (10): x86/ibt: Add ANNOTATE_NOENDBR x86/cpu: Fix __x86_return_thunk symbol type x86/cpu: Fix up srso_safe_ret() and __x86_return_thunk() x86/alternative: Make custom return thunk unconditional x86/cpu: Clean up SRSO return thunk mess x86/cpu: Rename original retbleed methods x86/cpu: Rename srso_(.*)_alias to srso_alias_\1 x86/cpu: Cleanup the untrain mess objtool/x86: Fixup frame-pointer vs rethunk objtool/x86: Fix SRSO mess Sean Christopherson (1): x86/retpoline: Don't clobber RFLAGS during srso_safe_ret() Documentation/admin-guide/hw-vuln/index.rst | 1 + Documentation/admin-guide/hw-vuln/srso.rst | 133 ++++++++++++ .../admin-guide/kernel-parameters.txt | 11 + arch/x86/Kconfig | 7 + arch/x86/include/asm/cpufeature.h | 23 +- arch/x86/include/asm/cpufeatures.h | 15 +- arch/x86/include/asm/msr-index.h | 1 + arch/x86/include/asm/nospec-branch.h | 34 ++- arch/x86/include/asm/processor.h | 7 +- arch/x86/kernel/alternative.c | 2 +- arch/x86/kernel/cpu/amd.c | 19 ++ arch/x86/kernel/cpu/bugs.c | 197 ++++++++++++++++++ arch/x86/kernel/cpu/common.c | 17 +- arch/x86/kernel/cpu/mkcapflags.sh | 2 +- arch/x86/kernel/cpu/proc.c | 2 +- arch/x86/kernel/cpu/scattered.c | 3 + arch/x86/kernel/vmlinux.lds.S | 38 +++- arch/x86/kvm/cpuid.c | 3 + arch/x86/kvm/svm/svm.c | 4 +- arch/x86/kvm/svm/vmenter.S | 3 + arch/x86/lib/retpoline.S | 135 ++++++++++-- drivers/base/cpu.c | 8 + include/linux/cpu.h | 2 + include/linux/objtool.h | 28 +++ tools/arch/x86/include/asm/cpufeatures.h | 16 +- tools/arch/x86/include/asm/msr-index.h | 1 + tools/include/linux/objtool.h | 28 +++ tools/objtool/arch.h | 1 + tools/objtool/arch/x86/decode.c | 6 + tools/objtool/check.c | 41 +++- tools/objtool/elf.h | 1 + .../perf/trace/beauty/tracepoints/x86_msr.sh | 2 +- 32 files changed, 740 insertions(+), 51 deletions(-) create mode 100644 Documentation/admin-guide/hw-vuln/srso.rst -- 2.25.1

3 30

[PATCH openEuler-1.0-LTS] ipv4: fix null-deref in ipv4_link_failure
by Lu Wei 07 Oct '23

07 Oct '23

From: Kyle Zeng <zengyhkyle(a)gmail.com> mainline inclusion from mainline-v6.6-rc3 commit 0113d9c9d1ccc07f5a3710dac4aa24b6d711278c category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I85DZB CVE: CVE-2023-42754 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Currently, we assume the skb is associated with a device before calling __ip_options_compile, which is not always the case if it is re-routed by ipvs. When skb->dev is NULL, dev_net(skb->dev) will become null-dereference. This patch adds a check for the edge case and switch to use the net_device from the rtable when skb->dev is NULL. Fixes: ed0de45a1008 ("ipv4: recompile ip options in ipv4_link_failure") Suggested-by: David Ahern <dsahern(a)kernel.org> Signed-off-by: Kyle Zeng <zengyhkyle(a)gmail.com> Cc: Stephen Suryaputra <ssuryaextr(a)gmail.com> Cc: Vadim Fedorenko <vfedorenko(a)novek.ru> Reviewed-by: David Ahern <dsahern(a)kernel.org> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Lu Wei <luwei32(a)huawei.com> --- net/ipv4/route.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 68f67bf99ed7..86096e2e43b0 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1212,6 +1212,7 @@ static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie) static void ipv4_send_dest_unreach(struct sk_buff *skb) { + struct net_device *dev; struct ip_options opt; int res; @@ -1229,7 +1230,8 @@ static void ipv4_send_dest_unreach(struct sk_buff *skb) opt.optlen = ip_hdr(skb)->ihl * 4 - sizeof(struct iphdr); rcu_read_lock(); - res = __ip_options_compile(dev_net(skb->dev), &opt, skb, NULL); + dev = skb->dev ? skb->dev : skb_rtable(skb)->dst.dev; + res = __ip_options_compile(dev_net(dev), &opt, skb, NULL); rcu_read_unlock(); if (res) -- 2.34.1

2 1

[PATCH OLK-5.10 00/28] fix CVE-2023-20569
by Jialin Zhang 07 Oct '23

07 Oct '23

New architectural features and CPUID bits related to the Speculative Return Stack Overflow (SRSO) vulnerability. Arnaldo Carvalho de Melo (2): tools headers cpufeatures: Sync with the kernel sources tools arch x86: Sync the msr-index.h copy with the kernel sources Borislav Petkov (AMD) (9): x86/bugs: Increase the x86 bugs vector size to two u32s x86/srso: Add a Speculative RAS Overflow mitigation x86/srso: Add IBPB_BRTYPE support x86/srso: Add SRSO_NO support x86/srso: Add IBPB x86/srso: Add IBPB on VMEXIT x86/srso: Tie SBPB bit setting to microcode patch detection x86/srso: Disable the mitigation on unaffected configurations x86/srso: Correct the mitigation status when SMT is disabled Jialin Zhang (1): x86/cpufeatures: Fix abi breakage caused by NCAPINTS in cpufeature header file. Josh Poimboeuf (2): x86/srso: Fix return thunks in generated code objtool: Add frame-pointer-specific function ignore Kim Phillips (1): x86/cpu, kvm: Add support for CPUID_80000021_EAX Nick Desaulniers (1): x86/srso: Fix build breakage with the LLVM linker Nikolay Borisov (1): kabi: Allow extra bugsints (bsc#1213927). Peter Zijlstra (10): x86/ibt: Add ANNOTATE_NOENDBR x86/cpu: Fix __x86_return_thunk symbol type x86/cpu: Fix up srso_safe_ret() and __x86_return_thunk() x86/alternative: Make custom return thunk unconditional x86/cpu: Clean up SRSO return thunk mess x86/cpu: Rename original retbleed methods x86/cpu: Rename srso_(.*)_alias to srso_alias_\1 x86/cpu: Cleanup the untrain mess objtool/x86: Fixup frame-pointer vs rethunk objtool/x86: Fix SRSO mess Sean Christopherson (1): x86/retpoline: Don't clobber RFLAGS during srso_safe_ret() Documentation/admin-guide/hw-vuln/index.rst | 1 + Documentation/admin-guide/hw-vuln/srso.rst | 133 ++++++++++++ .../admin-guide/kernel-parameters.txt | 11 + arch/x86/Kconfig | 7 + arch/x86/include/asm/cpufeature.h | 23 +- arch/x86/include/asm/cpufeatures.h | 15 +- arch/x86/include/asm/msr-index.h | 1 + arch/x86/include/asm/nospec-branch.h | 34 ++- arch/x86/include/asm/processor.h | 7 +- arch/x86/kernel/alternative.c | 2 +- arch/x86/kernel/cpu/amd.c | 19 ++ arch/x86/kernel/cpu/bugs.c | 197 ++++++++++++++++++ arch/x86/kernel/cpu/common.c | 17 +- arch/x86/kernel/cpu/mkcapflags.sh | 2 +- arch/x86/kernel/cpu/proc.c | 2 +- arch/x86/kernel/cpu/scattered.c | 3 + arch/x86/kernel/vmlinux.lds.S | 38 +++- arch/x86/kvm/cpuid.c | 3 + arch/x86/kvm/svm/svm.c | 4 +- arch/x86/kvm/svm/vmenter.S | 3 + arch/x86/lib/retpoline.S | 135 ++++++++++-- drivers/base/cpu.c | 8 + include/linux/cpu.h | 2 + include/linux/objtool.h | 28 +++ tools/arch/x86/include/asm/cpufeatures.h | 16 +- tools/arch/x86/include/asm/msr-index.h | 1 + tools/include/linux/objtool.h | 28 +++ tools/objtool/arch.h | 1 + tools/objtool/arch/x86/decode.c | 6 + tools/objtool/check.c | 41 +++- tools/objtool/elf.h | 1 + .../perf/trace/beauty/tracepoints/x86_msr.sh | 2 +- 32 files changed, 740 insertions(+), 51 deletions(-) create mode 100644 Documentation/admin-guide/hw-vuln/srso.rst -- 2.25.1

1 28