May 2024 - Kernel - mailweb.openeuler.org

[PATCH openEuler-1.0-LTS 0/1] net-memcg: Fix scope of sockmem pressure indicators
by Chen Ridong 22 May '24

22 May '24

*** BLURB HERE *** Abel Wu (1): net-memcg: Fix scope of sockmem pressure indicators include/linux/memcontrol.h | 9 +++++++-- mm/vmpressure.c | 13 ++++++++++++- 2 files changed, 19 insertions(+), 3 deletions(-) -- 2.34.1

2 2

[openeuler:OLK-6.6 9677/9701] arch/arm64/kernel/cpufeature.c:2129:13: warning: 'enable_pseudo_nmi' defined but not used
by kernel test robot 22 May '24

22 May '24

tree: https://gitee.com/openeuler/kernel.git OLK-6.6 head: a06dd08e9351e0389df4f63a9b400e134ed0c168 commit: c6ce2becb89528f83c1ad3c0607ad05baecebc0a [9677/9701] arm64/cpufeature: Fix pseudo nmi identifier undeclaration complilation error config: arm64-defconfig (https://download.01.org/0day-ci/archive/20240522/202405221540.3vBxARIZ-lkp@…) compiler: aarch64-linux-gcc (GCC) 13.2.0 reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20240522/202405221540.3vBxARIZ-lkp@…) If you fix the issue in a separate patch/commit (i.e. not just a new version of the same patch/commit), kindly add following tags | Reported-by: kernel test robot <lkp(a)intel.com> | Closes: https://lore.kernel.org/oe-kbuild-all/202405221540.3vBxARIZ-lkp@intel.com/ All warnings (new ones prefixed by >>): >> arch/arm64/kernel/cpufeature.c:2129:13: warning: 'enable_pseudo_nmi' defined but not used [-Wunused-variable] 2129 | static bool enable_pseudo_nmi; | ^~~~~~~~~~~~~~~~~ vim +/enable_pseudo_nmi +2129 arch/arm64/kernel/cpufeature.c 3e6c69a058deaa Mark Brown 2019-12-09 2127 f72387e1f8bc99 Mark Brown 2022-11-03 2128 #if IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI) || IS_ENABLED(CONFIG_ARM64_NMI) bc3c03ccb4641f Julien Thierry 2019-01-31 @2129 static bool enable_pseudo_nmi; f72387e1f8bc99 Mark Brown 2022-11-03 2130 #endif bc3c03ccb4641f Julien Thierry 2019-01-31 2131 :::::: The code at line 2129 was first introduced by commit :::::: bc3c03ccb4641fb940b27a0d369431876923a8fe arm64: Enable the support of pseudo-NMIs :::::: TO: Julien Thierry <julien.thierry(a)arm.com> :::::: CC: Catalin Marinas <catalin.marinas(a)arm.com> -- 0-DAY CI Kernel Test Service https://github.com/intel/lkp-tests/wiki

1 0

[PATCH OLK-6.6] ext4: default enable iomap for buffered IO and large folio
by Zhang Yi 22 May '24

22 May '24

hulk inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I9PXA8 CVE: NA -------------------------------- Enable iomap path for buffered IO and large folio on 4k pagesize by default, and allow switching iomap path and buffered_head path through remount. The path switch doesn't take effect until the activing inodes destroyed. Signed-off-by: Zhang Yi <yi.zhang(a)huawei.com> --- fs/ext4/super.c | 21 +++++++++------------ 1 file changed, 9 insertions(+), 12 deletions(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 292143ce354c..0ef4b804e18e 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1738,7 +1738,8 @@ enum { Opt_dioread_nolock, Opt_dioread_lock, Opt_discard, Opt_nodiscard, Opt_init_itable, Opt_noinit_itable, Opt_max_dir_size_kb, Opt_nojournal_checksum, Opt_nombcache, - Opt_no_prefetch_block_bitmaps, Opt_mb_optimize_scan, Opt_buffered_iomap, + Opt_no_prefetch_block_bitmaps, Opt_mb_optimize_scan, + Opt_buffered_iomap, Opt_nobuffered_iomap, Opt_errors, Opt_data, Opt_data_err, Opt_jqfmt, Opt_dax_type, #ifdef CONFIG_EXT4_DEBUG Opt_fc_debug_max_replay, Opt_fc_debug_force @@ -1882,6 +1883,7 @@ static const struct fs_parameter_spec ext4_param_specs[] = { Opt_no_prefetch_block_bitmaps), fsparam_s32 ("mb_optimize_scan", Opt_mb_optimize_scan), fsparam_flag ("buffered_iomap", Opt_buffered_iomap), + fsparam_flag ("nobuffered_iomap", Opt_nobuffered_iomap), fsparam_string ("check", Opt_removed), /* mount option from ext2/3 */ fsparam_flag ("nocheck", Opt_removed), /* mount option from ext2/3 */ fsparam_flag ("reservation", Opt_removed), /* mount option from ext2/3 */ @@ -1978,6 +1980,8 @@ static const struct mount_opts { MOPT_SET}, {Opt_buffered_iomap, EXT4_MOUNT2_BUFFERED_IOMAP, MOPT_SET | MOPT_2 | MOPT_EXT4_ONLY}, + {Opt_nobuffered_iomap, EXT4_MOUNT2_BUFFERED_IOMAP, + MOPT_CLEAR | MOPT_2 | MOPT_EXT4_ONLY}, #ifdef CONFIG_EXT4_DEBUG {Opt_fc_debug_force, EXT4_MOUNT2_JOURNAL_FAST_COMMIT, MOPT_SET | MOPT_2 | MOPT_EXT4_ONLY}, @@ -2464,11 +2468,6 @@ static int ext4_parse_param(struct fs_context *fc, struct fs_parameter *param) return -EINVAL; } return 0; - case Opt_buffered_iomap: - ext4_msg(NULL, KERN_WARNING, - "iomap for buffered enabled. Warning: EXPERIMENTAL, use at your own risk"); - ctx_set_mount_opt2(ctx, EXT4_MOUNT2_BUFFERED_IOMAP); - return 0; } /* @@ -2908,12 +2907,6 @@ static int ext4_check_opt_consistency(struct fs_context *fc, !(sbi->s_mount_opt2 & EXT4_MOUNT2_DAX_INODE))) { goto fail_dax_change_remount; } - - if (ctx_test_mount_opt2(ctx, EXT4_MOUNT2_BUFFERED_IOMAP) && - !test_opt2(sb, BUFFERED_IOMAP)) { - ext4_msg(NULL, KERN_ERR, "can't enable iomap for buffered IO on remount"); - return -EINVAL; - } } return ext4_check_quota_consistency(fc, sb); @@ -4481,6 +4474,10 @@ static void ext4_set_def_opts(struct super_block *sb, if (sb->s_blocksize == PAGE_SIZE) set_opt(sb, DIOREAD_NOLOCK); + + /* Use iomap for buffered IO path on 4k pagesize */ + if (PAGE_SIZE == SZ_4K) + set_opt2(sb, BUFFERED_IOMAP); } static int ext4_handle_clustersize(struct super_block *sb) -- 2.39.2

2 1

[PATCH openEuler-1.0-LTS] drm/amd/pm: fix a double-free in si_dpm_init
by Xia Fukun 22 May '24

22 May '24

From: Zhipeng Lu <alexious(a)zju.edu.cn> stable inclusion from stable-v4.19.314 commit afe9f5b871f86d58ecdc45b217b662227d7890d0 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I9Q9IJ CVE: CVE-2023-52691 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?h=… -------------------------------- [ Upstream commit ac16667237a82e2597e329eb9bc520d1cf9dff30 ] When the allocation of adev->pm.dpm.dyn_state.vddc_dependency_on_dispclk.entries fails, amdgpu_free_extended_power_table is called to free some fields of adev. However, when the control flow returns to si_dpm_sw_init, it goes to label dpm_failed and calls si_dpm_fini, which calls amdgpu_free_extended_power_table again and free those fields again. Thus a double-free is triggered. Fixes: 841686df9f7d ("drm/amdgpu: add SI DPM support (v4)") Signed-off-by: Zhipeng Lu <alexious(a)zju.edu.cn> Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Xia Fukun <xiafukun(a)huawei.com> --- drivers/gpu/drm/amd/amdgpu/si_dpm.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/si_dpm.c b/drivers/gpu/drm/amd/amdgpu/si_dpm.c index 1de96995e690..7c724d3de111 100644 --- a/drivers/gpu/drm/amd/amdgpu/si_dpm.c +++ b/drivers/gpu/drm/amd/amdgpu/si_dpm.c @@ -7348,10 +7348,9 @@ static int si_dpm_init(struct amdgpu_device *adev) kcalloc(4, sizeof(struct amdgpu_clock_voltage_dependency_entry), GFP_KERNEL); - if (!adev->pm.dpm.dyn_state.vddc_dependency_on_dispclk.entries) { - amdgpu_free_extended_power_table(adev); + if (!adev->pm.dpm.dyn_state.vddc_dependency_on_dispclk.entries) return -ENOMEM; - } + adev->pm.dpm.dyn_state.vddc_dependency_on_dispclk.count = 4; adev->pm.dpm.dyn_state.vddc_dependency_on_dispclk.entries[0].clk = 0; adev->pm.dpm.dyn_state.vddc_dependency_on_dispclk.entries[0].v = 0; -- 2.34.1

2 1

[PATCH OLK-5.10] netfilter: nf_tables: use timestamp to check for set element timeout
by Liu Jian 22 May '24

22 May '24

mainline inclusion from mainline-v6.8-rc4 commit 7395dfacfff65e9938ac0889dafa1ab01e987d15 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I9O0MR CVE: CVE-2024-27397 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… --------------------------- Add a timestamp field at the beginning of the transaction, store it in the nftables per-netns area. Update set backend .insert, .deactivate and sync gc path to use the timestamp, this avoids that an element expires while control plane transaction is still unfinished. .lookup and .update, which are used from packet path, still use the current time to check if the element has expired. And .get path and dump also since this runs lockless under rcu read size lock. Then, there is async gc which also needs to check the current time since it runs asynchronously from a workqueue. Fixes: c3e1b005ed1c ("netfilter: nf_tables: add set element timeout support") Signed-off-by: Pablo Neira Ayuso <pablo(a)netfilter.org> Conflicts: include/net/netfilter/nf_tables.h net/netfilter/nf_tables_api.c net/netfilter/nft_set_pipapo.c net/netfilter/nft_set_rbtree.c [Do not backport nft_rbtree_gc() part, it is a async gc in our repository. Others caused by we did not backport commit ab482c6b66a4, b2d306542ff9, 8837ba3e58ea, 5f68718b34a5, d59d2f82f984.] Signed-off-by: Liu Jian <liujian56(a)huawei.com> --- include/net/netfilter/nf_tables.h | 24 ++++++++++++++++++++++-- net/netfilter/nf_tables_api.c | 1 + net/netfilter/nft_set_hash.c | 8 +++++++- net/netfilter/nft_set_pipapo.c | 18 +++++++++++------- net/netfilter/nft_set_rbtree.c | 6 ++++-- 5 files changed, 45 insertions(+), 12 deletions(-) diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 5e3529c73e61..11b619ceca7c 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -13,6 +13,7 @@ #include <net/netfilter/nf_flow_table.h> #include <net/netlink.h> #include <net/flow_offload.h> +#include <net/netns/generic.h> #define NFT_MAX_HOOKS (NF_INET_INGRESS + 1) @@ -695,10 +696,16 @@ static inline struct nft_expr *nft_set_ext_expr(const struct nft_set_ext *ext) return nft_set_ext(ext, NFT_SET_EXT_EXPR); } -static inline bool nft_set_elem_expired(const struct nft_set_ext *ext) +static inline bool __nft_set_elem_expired(const struct nft_set_ext *ext, + u64 tstamp) { return nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION) && - time_is_before_eq_jiffies64(*nft_set_ext_expiration(ext)); + time_after_eq64(tstamp, *nft_set_ext_expiration(ext)); +} + +static inline bool nft_set_elem_expired(const struct nft_set_ext *ext) +{ + return __nft_set_elem_expired(ext, get_jiffies_64()); } static inline struct nft_set_ext *nft_set_elem_ext(const struct nft_set *set, @@ -1587,9 +1594,22 @@ struct nftables_pernet { struct list_head module_list; struct list_head notify_list; struct mutex commit_mutex; + u64 tstamp; unsigned int base_seq; u8 validate_state; unsigned int gc_seq; }; +extern unsigned int nf_tables_net_id; + +static inline struct nftables_pernet *nft_pernet(const struct net *net) +{ + return net_generic(net, nf_tables_net_id); +} + +static inline u64 nft_net_tstamp(const struct net *net) +{ + return nft_pernet(net)->tstamp; +} + #endif /* _NET_NF_TABLES_H */ diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 7c102a4ce930..794c3fdac563 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -9014,6 +9014,7 @@ static bool nf_tables_valid_genid(struct net *net, u32 genid) bool genid_ok; mutex_lock(&nft_net->commit_mutex); + nft_net->tstamp = get_jiffies_64(); genid_ok = genid == 0 || nft_net->base_seq == genid; if (!genid_ok) diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index f0a9ad1c4ea4..2499d25a5c85 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -38,6 +38,7 @@ struct nft_rhash_cmp_arg { const struct nft_set *set; const u32 *key; u8 genmask; + u64 tstamp; }; static inline u32 nft_rhash_key(const void *data, u32 len, u32 seed) @@ -64,7 +65,7 @@ static inline int nft_rhash_cmp(struct rhashtable_compare_arg *arg, return 1; if (nft_set_elem_is_dead(&he->ext)) return 1; - if (nft_set_elem_expired(&he->ext)) + if (__nft_set_elem_expired(&he->ext, x->tstamp)) return 1; if (!nft_set_elem_active(&he->ext, x->genmask)) return 1; @@ -88,6 +89,7 @@ static bool nft_rhash_lookup(const struct net *net, const struct nft_set *set, .genmask = nft_genmask_cur(net), .set = set, .key = key, + .tstamp = get_jiffies_64(), }; he = rhashtable_lookup(&priv->ht, &arg, nft_rhash_params); @@ -106,6 +108,7 @@ static void *nft_rhash_get(const struct net *net, const struct nft_set *set, .genmask = nft_genmask_cur(net), .set = set, .key = elem->key.val.data, + .tstamp = get_jiffies_64(), }; he = rhashtable_lookup(&priv->ht, &arg, nft_rhash_params); @@ -129,6 +132,7 @@ static bool nft_rhash_update(struct nft_set *set, const u32 *key, .genmask = NFT_GENMASK_ANY, .set = set, .key = key, + .tstamp = get_jiffies_64(), }; he = rhashtable_lookup(&priv->ht, &arg, nft_rhash_params); @@ -172,6 +176,7 @@ static int nft_rhash_insert(const struct net *net, const struct nft_set *set, .genmask = nft_genmask_next(net), .set = set, .key = elem->key.val.data, + .tstamp = nft_net_tstamp(net), }; struct nft_rhash_elem *prev; @@ -214,6 +219,7 @@ static void *nft_rhash_deactivate(const struct net *net, .genmask = nft_genmask_next(net), .set = set, .key = elem->key.val.data, + .tstamp = nft_net_tstamp(net), }; rcu_read_lock(); diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 9c311b6f37af..831cbff77773 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -504,6 +504,7 @@ bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set, * @set: nftables API set representation * @data: Key data to be matched against existing elements * @genmask: If set, check that element is active in given genmask + * @tstamp: timestamp to check for expired elements * * This is essentially the same as the lookup function, except that it matches * key data against the uncommitted copy and doesn't use preallocated maps for @@ -513,7 +514,8 @@ bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set, */ static struct nft_pipapo_elem *pipapo_get(const struct net *net, const struct nft_set *set, - const u8 *data, u8 genmask) + const u8 *data, u8 genmask, + u64 tstamp) { struct nft_pipapo_elem *ret = ERR_PTR(-ENOENT); struct nft_pipapo *priv = nft_set_priv(set); @@ -566,7 +568,7 @@ static struct nft_pipapo_elem *pipapo_get(const struct net *net, goto out; if (last) { - if (nft_set_elem_expired(&f->mt[b].e->ext)) + if (__nft_set_elem_expired(&f->mt[b].e->ext, tstamp)) goto next_match; if ((genmask && !nft_set_elem_active(&f->mt[b].e->ext, genmask))) @@ -603,7 +605,7 @@ static void *nft_pipapo_get(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem, unsigned int flags) { return pipapo_get(net, set, (const u8 *)elem->key.val.data, - nft_genmask_cur(net)); + nft_genmask_cur(net), get_jiffies_64()); } /** @@ -1197,6 +1199,7 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set, struct nft_pipapo *priv = nft_set_priv(set); struct nft_pipapo_match *m = priv->clone; u8 genmask = nft_genmask_next(net); + u64 tstamp = nft_net_tstamp(net); struct nft_pipapo_field *f; const u8 *start_p, *end_p; int i, bsize_max, err = 0; @@ -1206,7 +1209,7 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set, else end = start; - dup = pipapo_get(net, set, start, genmask); + dup = pipapo_get(net, set, start, genmask, tstamp); if (!IS_ERR(dup)) { /* Check if we already have the same exact entry */ const struct nft_data *dup_key, *dup_end; @@ -1228,7 +1231,7 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set, if (PTR_ERR(dup) == -ENOENT) { /* Look for partially overlapping entries */ - dup = pipapo_get(net, set, end, nft_genmask_next(net)); + dup = pipapo_get(net, set, end, nft_genmask_next(net), tstamp); } if (PTR_ERR(dup) != -ENOENT) { @@ -1580,6 +1583,7 @@ static void pipapo_gc(const struct nft_set *_set, struct nft_pipapo_match *m) struct nft_set *set = (struct nft_set *) _set; struct nft_pipapo *priv = nft_set_priv(set); struct net *net = read_pnet(&set->net); + u64 tstamp = nft_net_tstamp(net); int rules_f0, first_rule = 0; struct nft_trans_gc *gc; @@ -1613,7 +1617,7 @@ static void pipapo_gc(const struct nft_set *_set, struct nft_pipapo_match *m) /* synchronous gc never fails, there is no need to set on * NFT_SET_ELEM_DEAD_BIT. */ - if (nft_set_elem_expired(&e->ext)) { + if (__nft_set_elem_expired(&e->ext, tstamp)) { priv->dirty = true; gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC); @@ -1772,7 +1776,7 @@ static void *pipapo_deactivate(const struct net *net, const struct nft_set *set, { struct nft_pipapo_elem *e; - e = pipapo_get(net, set, data, nft_genmask_next(net)); + e = pipapo_get(net, set, data, nft_genmask_next(net), nft_net_tstamp(net)); if (IS_ERR(e)) return NULL; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 8b1daca932e0..3f2e39988ab2 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -314,6 +314,7 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, struct rb_node *node, *next, *parent, **p, *first = NULL; struct nft_rbtree *priv = nft_set_priv(set); u8 genmask = nft_genmask_next(net); + u64 tstamp = nft_net_tstamp(net); int d, err; /* Descend the tree to search for an existing element greater than the @@ -359,7 +360,7 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, continue; /* perform garbage collection to avoid bogus overlap reports. */ - if (nft_set_elem_expired(&rbe->ext)) { + if (__nft_set_elem_expired(&rbe->ext, tstamp)) { err = nft_rbtree_gc_elem(set, priv, rbe); if (err < 0) return err; @@ -533,6 +534,7 @@ static void *nft_rbtree_deactivate(const struct net *net, const struct rb_node *parent = priv->root.rb_node; struct nft_rbtree_elem *rbe, *this = elem->priv; u8 genmask = nft_genmask_next(net); + u64 tstamp = nft_net_tstamp(net); int d; while (parent != NULL) { @@ -553,7 +555,7 @@ static void *nft_rbtree_deactivate(const struct net *net, nft_rbtree_interval_end(this)) { parent = parent->rb_right; continue; - } else if (nft_set_elem_expired(&rbe->ext)) { + } else if (__nft_set_elem_expired(&rbe->ext, tstamp)) { break; } else if (!nft_set_elem_active(&rbe->ext, genmask)) { parent = parent->rb_left; -- 2.34.1

2 1

[PATCH openEuler-22.03-LTS-SP1] net/smc: reduce rtnl pressure in smc_pnet_create_pnetids_list()
by Zhengchao Shao 22 May '24

22 May '24

From: Eric Dumazet <edumazet(a)google.com> stable inclusion from stable-v5.10.215 commit bc4d1ebca11b4f194e262326bd45938e857c59d2 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I9QGJZ CVE: CVE-2024-35934 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 00af2aa93b76b1bade471ad0d0525d4d29ca5cc0 ] Many syzbot reports show extreme rtnl pressure, and many of them hint that smc acquires rtnl in netns creation for no good reason [1] This patch returns early from smc_pnet_net_init() if there is no netdevice yet. I am not even sure why smc_pnet_create_pnetids_list() even exists, because smc_pnet_netdev_event() is also calling smc_pnet_add_base_pnetid() when handling NETDEV_UP event. [1] extract of typical syzbot reports 2 locks held by syz-executor.3/12252: #0: ffffffff8f369610 (pernet_ops_rwsem){++++}-{3:3}, at: copy_net_ns+0x4c7/0x7b0 net/core/net_namespace.c:491 #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_create_pnetids_list net/smc/smc_pnet.c:809 [inline] #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_net_init+0x10a/0x1e0 net/smc/smc_pnet.c:878 2 locks held by syz-executor.4/12253: #0: ffffffff8f369610 (pernet_ops_rwsem){++++}-{3:3}, at: copy_net_ns+0x4c7/0x7b0 net/core/net_namespace.c:491 #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_create_pnetids_list net/smc/smc_pnet.c:809 [inline] #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_net_init+0x10a/0x1e0 net/smc/smc_pnet.c:878 2 locks held by syz-executor.1/12257: #0: ffffffff8f369610 (pernet_ops_rwsem){++++}-{3:3}, at: copy_net_ns+0x4c7/0x7b0 net/core/net_namespace.c:491 #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_create_pnetids_list net/smc/smc_pnet.c:809 [inline] #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_net_init+0x10a/0x1e0 net/smc/smc_pnet.c:878 2 locks held by syz-executor.2/12261: #0: ffffffff8f369610 (pernet_ops_rwsem){++++}-{3:3}, at: copy_net_ns+0x4c7/0x7b0 net/core/net_namespace.c:491 #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_create_pnetids_list net/smc/smc_pnet.c:809 [inline] #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_net_init+0x10a/0x1e0 net/smc/smc_pnet.c:878 2 locks held by syz-executor.0/12265: #0: ffffffff8f369610 (pernet_ops_rwsem){++++}-{3:3}, at: copy_net_ns+0x4c7/0x7b0 net/core/net_namespace.c:491 #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_create_pnetids_list net/smc/smc_pnet.c:809 [inline] #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_net_init+0x10a/0x1e0 net/smc/smc_pnet.c:878 2 locks held by syz-executor.3/12268: #0: ffffffff8f369610 (pernet_ops_rwsem){++++}-{3:3}, at: copy_net_ns+0x4c7/0x7b0 net/core/net_namespace.c:491 #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_create_pnetids_list net/smc/smc_pnet.c:809 [inline] #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_net_init+0x10a/0x1e0 net/smc/smc_pnet.c:878 2 locks held by syz-executor.4/12271: #0: ffffffff8f369610 (pernet_ops_rwsem){++++}-{3:3}, at: copy_net_ns+0x4c7/0x7b0 net/core/net_namespace.c:491 #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_create_pnetids_list net/smc/smc_pnet.c:809 [inline] #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_net_init+0x10a/0x1e0 net/smc/smc_pnet.c:878 2 locks held by syz-executor.1/12274: #0: ffffffff8f369610 (pernet_ops_rwsem){++++}-{3:3}, at: copy_net_ns+0x4c7/0x7b0 net/core/net_namespace.c:491 #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_create_pnetids_list net/smc/smc_pnet.c:809 [inline] #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_net_init+0x10a/0x1e0 net/smc/smc_pnet.c:878 2 locks held by syz-executor.2/12280: #0: ffffffff8f369610 (pernet_ops_rwsem){++++}-{3:3}, at: copy_net_ns+0x4c7/0x7b0 net/core/net_namespace.c:491 #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_create_pnetids_list net/smc/smc_pnet.c:809 [inline] #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_net_init+0x10a/0x1e0 net/smc/smc_pnet.c:878 Signed-off-by: Eric Dumazet <edumazet(a)google.com> Cc: Wenjia Zhang <wenjia(a)linux.ibm.com> Cc: Jan Karcher <jaka(a)linux.ibm.com> Cc: "D. Wythe" <alibuda(a)linux.alibaba.com> Cc: Tony Lu <tonylu(a)linux.alibaba.com> Cc: Wen Gu <guwen(a)linux.alibaba.com> Reviewed-by: Wenjia Zhang <wenjia(a)linux.ibm.com> Link: https://lore.kernel.org/r/20240302100744.3868021-1-edumazet@google.com Signed-off-by: Paolo Abeni <pabeni(a)redhat.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Zhengchao Shao <shaozhengchao(a)huawei.com> --- net/smc/smc_pnet.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index 30bae60d626c..ed9cfa11b589 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -797,6 +797,16 @@ static void smc_pnet_create_pnetids_list(struct net *net) u8 ndev_pnetid[SMC_MAX_PNETID_LEN]; struct net_device *dev; + /* Newly created netns do not have devices. + * Do not even acquire rtnl. + */ + if (list_empty(&net->dev_base_head)) + return; + + /* Note: This might not be needed, because smc_pnet_netdev_event() + * is also calling smc_pnet_add_base_pnetid() when handling + * NETDEV_UP event. + */ rtnl_lock(); for_each_netdev(net, dev) smc_pnet_add_base_pnetid(net, dev, ndev_pnetid); -- 2.34.1

2 1

[PATCH OLK-6.6] irqchip/loongson-eiointc: fix gsi register error
by Hongchen Zhang 22 May '24

22 May '24

LoongArch inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I9RAP5 ------------------------------------------ When we boot a 3C5000-7A2000 2Node server using "nr_cpus=1 maxcpus=1", we get the following Call Trace: 4.807397] ------------[ cut here ]------------ [ 4.811996] WARNING: CPU: 0 PID: 1 at drivers/acpi/irq.c:63 acpi_register_gsi+0xe0/0x100 [ 4.820048] Modules linked in: [ 4.823082] CPU: 0 PID: 1 Comm: swapper/0 Not tainted 6.9.0-rc7-next-20240509+ #26 [ 4.830604] Hardware name: LOONGSON Dabieshan/Loongson-LS2C50C2, BIOS Loongson UEFI (3C50007A2000_Ls2c5lc2) V4.0.13-Dual 12/06/23 17:33:54 [ 4.842964] pc 9000000000bdc6e0 ra 9000000000bdc66c tp 90000002051d4000 sp 90000002051d7ae0 [ 4.851269] a0 0000000000000000 a1 00000000000000a0 a2 0000000000000000 a3 0000000000000000 [ 4.859567] a4 9000000200014518 a5 000000000000003c a6 90000000018876b0 a7 00302e39303a3030 [ 4.867866] t0 0000000000000000 t1 0000000000000080 t2 0000000000000040 t3 0000000000036800 [ 4.876165] t4 0000000000036800 t5 0000000000000004 t6 0000000000000000 t7 0000000000000000 [ 4.884464] t8 900000000800d910 u0 0000000000000000 s9 90000000014bf9e8 s0 00000000000000a0 [ 4.892763] s1 0000000000000000 s2 0000000000000000 s3 9000000001985000 s4 90000002051d7b88 [ 4.901063] s5 0000000000000001 s6 90000002055470b8 s7 90000000014400ac s8 0000000000000008 [ 4.909362] ra: 9000000000bdc66c acpi_register_gsi+0x6c/0x100 [ 4.915330] ERA: 9000000000bdc6e0 acpi_register_gsi+0xe0/0x100 [ 4.921297] CRMD: 000000b0 (PLV0 -IE -DA +PG DACF=CC DACM=CC -WE) [ 4.927446] PRMD: 00000004 (PPLV0 +PIE -PWE) [ 4.931777] EUEN: 00000000 (-FPE -SXE -ASXE -BTE) [ 4.936538] ECFG: 00071c1d (LIE=0,2-4,10-12 VS=7) [ 4.941301] ESTAT: 000c0000 [BRK] (IS= ECode=12 EsubCode=0) [ 4.946838] PRID: 0014c011 (Loongson-64bit, Loongson-3C5000) [ 4.952545] CPU: 0 PID: 1 Comm: swapper/0 Not tainted 6.9.0-rc7-next-20240509+ #26 [ 4.960066] Hardware name: LOONGSON Dabieshan/Loongson-LS2C50C2, BIOS Loongson UEFI (3C50007A2000_Ls2c5lc2) V4.0.13-Dual 12/06/23 17:33:54 [ 4.972425] Stack : 9000000001985000 0000000000000000 9000000000223524 90000002051d4000 [ 4.980382] 90000002051d7740 90000002051d7748 0000000000000000 90000002051d7888 [ 4.988338] 90000002051d7880 90000002051d7880 90000002051d7690 0000000000000001 [ 4.996294] 0000000000000001 90000002051d7748 420a070366b7e75d 90000002054f4500 [ 5.004251] 0000000000000001 0000000000000000 4137303030354333 c0000000ffffdfff [ 5.012206] 0000000000000003 00000000000ea642 0000000006b3c000 90000000014bf9e8 [ 5.020163] 0000000000000000 0000000000000000 90000000017f7e80 9000000001985000 [ 5.028119] 0000000000000001 0000000000000000 ffffffffffd7f549 90000000014400ac [ 5.036075] 0000000000000008 0000000000000000 900000000022353c 00007ffff1354000 [ 5.044031] 00000000000000b0 0000000000000004 0000000000000000 0000000000071c1d [ 5.051987] ... [ 5.054410] Call Trace: [ 5.054412] [<900000000022353c>] show_stack+0x5c/0x1a0 [ 5.061940] [<900000000141e86c>] dump_stack_lvl+0x9c/0xc4 [ 5.067305] [<900000000140170c>] __warn+0x94/0xcc [ 5.071977] [<90000000013cd900>] report_bug+0x160/0x220 [ 5.077170] [<900000000141facc>] do_bp+0x26c/0x2e0 [ 5.081929] [<0000000000000000>] 0x0 [ 5.085475] [<9000000000bdc6e0>] acpi_register_gsi+0xe0/0x100 [ 5.091182] [<9000000000bd5350>] acpi_pci_irq_enable+0xd0/0x220 [ 5.097061] [<9000000000b5e8d4>] pci_device_probe+0x54/0x260 [ 5.102683] [<9000000000d1fefc>] really_probe+0xbc/0x320 [ 5.107960] [<9000000000d201f0>] __driver_probe_device+0x90/0x160 [ 5.114012] [<9000000000d202f8>] driver_probe_device+0x38/0x120 [ 5.119892] [<9000000000d205d4>] __driver_attach+0x94/0x1c0 [ 5.125426] [<9000000000d1d7ac>] bus_for_each_dev+0x8c/0x100 [ 5.131046] [<9000000000d1ee30>] bus_add_driver+0xf0/0x240 [ 5.136494] [<9000000000d21688>] driver_register+0x68/0x140 [ 5.142028] [<9000000000220158>] do_one_initcall+0x78/0x200 [ 5.147561] [<9000000001440fcc>] kernel_init_freeable+0x23c/0x2b0 [ 5.153614] [<900000000142123c>] kernel_init+0x1c/0x120 [ 5.158802] [<9000000000221348>] ret_from_kernel_thread+0xc/0xa4 [ 5.166244] ---[ end trace 0000000000000000 ]--- [ 5.170998] GSI: No registered irqchip, giving up The root cause is that when the CPU boot from flat mode, it is unreliable to use cpu_to node to calculate the node number. Therefore, we use NODES_PER_FLATMODE_NODE to calculate the physical node number. According to the 3C5000 user manual, the value of NODES_PER_FLATMODE_NODE should be 4. Cc: <stable(a)vger.kernel.org> Signed-off-by: Ming Wang <wangming01(a)loongson.cn> Signed-off-by: Hongchen Zhang <zhanghongchen(a)loongson.cn> --- arch/loongarch/include/asm/numa.h | 1 + drivers/irqchip/irq-loongson-eiointc.c | 4 ++-- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/loongarch/include/asm/numa.h b/arch/loongarch/include/asm/numa.h index 27f319b49862..564c27d2de72 100644 --- a/arch/loongarch/include/asm/numa.h +++ b/arch/loongarch/include/asm/numa.h @@ -12,6 +12,7 @@ #include <linux/nodemask.h> #define NODE_ADDRSPACE_SHIFT 44 +#define NODES_PER_FLATMODE_NODE 4 #define pa_to_nid(addr) (((addr) & 0xf00000000000) >> NODE_ADDRSPACE_SHIFT) #define nid_to_addrbase(nid) (_ULCAST_(nid) << NODE_ADDRSPACE_SHIFT) diff --git a/drivers/irqchip/irq-loongson-eiointc.c b/drivers/irqchip/irq-loongson-eiointc.c index c5c26b8e8d0c..488951a740cd 100644 --- a/drivers/irqchip/irq-loongson-eiointc.c +++ b/drivers/irqchip/irq-loongson-eiointc.c @@ -375,7 +375,7 @@ int __init pch_msi_parse_madt(union acpi_subtable_headers *header, int node; if (cpu_has_flatmode) - node = cpu_to_node(eiointc_priv[nr_pics - 1]->node * CORES_PER_EIO_NODE); + node = eiointc_priv[nr_pics - 1]->node / NODES_PER_FLATMODE_NODE; else node = eiointc_priv[nr_pics - 1]->node; @@ -478,7 +478,7 @@ int __init eiointc_acpi_init(struct irq_domain *parent, goto out_free_handle; if (cpu_has_flatmode) - node = cpu_to_node(acpi_eiointc->node * CORES_PER_EIO_NODE); + node = acpi_eiointc->node / NODES_PER_FLATMODE_NODE; else node = acpi_eiointc->node; acpi_set_vec_parent(node, priv->eiointc_domain, pch_group); -- 2.33.0

2 1

[PATCH OLK-6.6 v2 00/37] mm: Some bugfix and optimization
by Liu Shixin 22 May '24

22 May '24

Patch [1-21] is series "Rearrange batched folio freeing" and three bugfix. Patch [22-26] is series "Clean up __folio_put()". Patch [27] add trace of alloc_contig_migrate_range. Patch [28-30] is three bugfix about hugetlb. Patch [31] is an performance optimization of pcp draining. Patch [32] is a minor improve of _deferred_list which benefit from debug. This patch is from series "Various significant MM patches". Other patches are not related to this patch, so don't backport together. Patch "mm: Free up PG_slab" may also benefit for us, but have compile problem need to fix, so not in this series. Patch [33-36] is part of series "Improve anon_vma scalability for anon VMAs". Patch "mm: Fix some minor per-VMA lock issues in userfaultfd" is not in backport because it depends on patch "userfaultfd: use per-vma locks in userfaultfd operations" Patch [37] fix a bug introduced by patch "mm: turn folio_test_hugetlb into a PageType" which is from the previous backport. v1->v2: Add patch [37]. Liu Shixin (1): mm/dynamic_pool: clear PG_hugetlb when demote hugepages Lucas Stach (1): mm: page_alloc: control latency caused by zone PCP draining Matthew Wilcox (Oracle) (30): mm: make folios_put() the basis of release_pages() mm: convert free_unref_page_list() to use folios mm: add free_unref_folios() mm: use folios_put() in __folio_batch_release() memcg: add mem_cgroup_uncharge_folios() mm: remove use of folio list from folios_put() mm: use free_unref_folios() in put_pages_list() mm: use __page_cache_release() in folios_put() mm: handle large folios in free_unref_folios() mm: allow non-hugetlb large folios to be batch processed mm: free folios in a batch in shrink_folio_list() mm: free folios directly in move_folios_to_lru() memcg: remove mem_cgroup_uncharge_list() mm: remove free_unref_page_list() mm: remove lru_to_page() mm: convert free_pages_and_swap_cache() to use folios_put() mm: use a folio in __collapse_huge_page_copy_succeeded() mm: convert free_swap_cache() to take a folio mm: remove folio from deferred split list before uncharging it mm: fix list corruption in put_pages_list mm: increase folio batch size mm: free non-hugetlb large folios in a batch mm: combine free_the_page() and free_unref_page() mm: inline destroy_large_folio() into __folio_put_large() mm: combine __folio_put_small, __folio_put_large and __folio_put mm: convert free_zone_device_page to free_zone_device_folio mm: always initialise folio->_deferred_list mm: assert the mmap_lock is held in __anon_vma_prepare() mm: delay the check for a NULL anon_vma mm: optimise vmf_anon_prepare() for VMAs without an anon_vma Miaohe Lin (1): mm/hugetlb: fix DEBUG_LOCKS_WARN_ON(1) when dissolve_free_hugetlb_folio() Mike Kravetz (2): hugetlb: set hugetlb page flag before optimizing vmemmap hugetlb: check for hugetlb folio before vmemmap_restore Richard Chang (1): mm: add alloc_contig_migrate_range allocation statistics Vishal Moola (Oracle) (1): mm/memory: change vmf_anon_prepare() to be non-static include/linux/memcontrol.h | 26 ++-- include/linux/mm.h | 19 +-- include/linux/pagevec.h | 4 +- include/linux/swap.h | 8 +- include/trace/events/kmem.h | 38 ++++++ mm/dynamic_pool.c | 1 + mm/huge_memory.c | 8 +- mm/hugetlb.c | 60 ++++++---- mm/hugetlb_vmemmap.c | 3 + mm/internal.h | 12 +- mm/khugepaged.c | 30 +++-- mm/memcontrol.c | 19 ++- mm/memory.c | 46 +++++--- mm/memremap.c | 30 ++--- mm/mlock.c | 3 +- mm/page_alloc.c | 169 ++++++++++++++------------ mm/page_isolation.c | 2 +- mm/rmap.c | 3 +- mm/swap.c | 230 +++++++++++++++++++----------------- mm/swap_state.c | 31 +++-- mm/vmscan.c | 58 +++++---- 21 files changed, 449 insertions(+), 351 deletions(-) -- 2.25.1

2 38

[PATCH OLK-5.10 00/10] Introduce NUMA isolation and consolidation
by Hui Tang 22 May '24

22 May '24

Introduce NUMA isolation and consolidation. Guan Jing (1): sched: Add can_migrate_task hook Hui Tang (10): sched: Introduce CONFIG_TASK_PLACEMENT_BY_CPU_RANGE sched: Some fixes for select_rq hook bpf:programmable: Add nodemask operation collection sched: Introduce task relationship by net and memory bpf:programmable: Add helper to get memory and net relationship sched: Add ioctl to get relationship sched: Update numa group preferred node periodically bpf:programmable: Add helper to set preferred node sched: Introduce CONFIG_QOS_SCHED_NUMA_ICON config: Enable NUMA isolation and consolidation by default arch/arm64/configs/openeuler_defconfig | 4 +- arch/x86/configs/openeuler_defconfig | 2 + fs/exec.c | 2 + include/linux/sched.h | 58 +++- include/linux/sched/relationship.h | 202 ++++++++++++ include/linux/sched_hook_defs.h | 4 + include/uapi/linux/bpf.h | 50 +++ include/uapi/linux/sched_ctrl.h | 57 ++++ init/Kconfig | 28 ++ init/init_task.c | 3 + kernel/fork.c | 13 + kernel/sched/Makefile | 2 + kernel/sched/bpf_sched.c | 149 +++++++++ kernel/sched/core.c | 7 + kernel/sched/debug.c | 2 + kernel/sched/fair.c | 302 +++++++++++++++-- kernel/sched/numa_icon.c | 144 ++++++++ kernel/sched/numa_icon.h | 43 +++ kernel/sched/relationship.c | 436 +++++++++++++++++++++++++ kernel/sched/relationship_ioctl.c | 142 ++++++++ kernel/sched/sched.h | 2 + scripts/bpf_helpers_doc.py | 12 + tools/include/uapi/linux/bpf.h | 50 +++ tools/lib/bpf/libbpf_sched.h | 160 ++++++++- 24 files changed, 1848 insertions(+), 26 deletions(-) create mode 100644 include/linux/sched/relationship.h create mode 100644 include/uapi/linux/sched_ctrl.h create mode 100644 kernel/sched/numa_icon.c create mode 100644 kernel/sched/numa_icon.h create mode 100644 kernel/sched/relationship.c create mode 100644 kernel/sched/relationship_ioctl.c -- 2.34.1

2 12

[PATCH OLK-5.10] netfilter: nf_tables: discard table flag update with pending basechain deletion
by Liu Jian 22 May '24

22 May '24

From: Pablo Neira Ayuso <pablo(a)netfilter.org> stable inclusion from stable-v5.10.215 commit b58d0ac35f6d75ec1db8650a29dfd6f292c11362 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I9QG9F CVE: CVE-2024-35897 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… --------------------------- commit 1bc83a019bbe268be3526406245ec28c2458a518 upstream. Hook unregistration is deferred to the commit phase, same occurs with hook updates triggered by the table dormant flag. When both commands are combined, this results in deleting a basechain while leaving its hook still registered in the core. Fixes: 179d9ba5559a ("netfilter: nf_tables: fix table flag updates") Signed-off-by: Pablo Neira Ayuso <pablo(a)netfilter.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Liu Jian <liujian56(a)huawei.com> --- net/netfilter/nf_tables_api.c | 20 +++++++++++++++++++- 1 file changed, 19 insertions(+), 1 deletion(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 2fd0ecb2e89f..7c102a4ce930 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1084,6 +1084,24 @@ static void nf_tables_table_disable(struct net *net, struct nft_table *table) #define __NFT_TABLE_F_UPDATE (__NFT_TABLE_F_WAS_DORMANT | \ __NFT_TABLE_F_WAS_AWAKEN) +static bool nft_table_pending_update(const struct nft_ctx *ctx) +{ + struct nftables_pernet *nft_net = net_generic(ctx->net, nf_tables_net_id); + struct nft_trans *trans; + + if (ctx->table->flags & __NFT_TABLE_F_UPDATE) + return true; + + list_for_each_entry(trans, &nft_net->commit_list, list) { + if (trans->ctx.table == ctx->table && + trans->msg_type == NFT_MSG_DELCHAIN && + nft_is_base_chain(trans->ctx.chain)) + return true; + } + + return false; +} + static int nf_tables_updtable(struct nft_ctx *ctx) { struct nft_trans *trans; @@ -1101,7 +1119,7 @@ static int nf_tables_updtable(struct nft_ctx *ctx) return 0; /* No dormant off/on/off/on games in single transaction */ - if (ctx->table->flags & __NFT_TABLE_F_UPDATE) + if (nft_table_pending_update(ctx)) return -EINVAL; trans = nft_trans_alloc(ctx, NFT_MSG_NEWTABLE, -- 2.34.1

2 1

2024

2023

2022

2021

2020

2019

Kernel May 2024