- Kernel - mailweb.openeuler.org

[PATCH OLK-6.6] procfs: move dropping pde and pid from ->evict_inode() to ->free_inode()
by Zhou Minqiang 12 Oct '26

12 Oct '26

mainline inclusion from mainline-v6.8-rc6 commit 47458802f6606f652cd0f6dc38cd52ce60ec0145 category: bugfix bugzilla: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- that keeps both around until struct inode is freed, making access to them safe from rcu-pathwalk Acked-by: Christian Brauner <brauner(a)kernel.org> Signed-off-by: Al Viro <viro(a)zeniv.linux.org.uk> Signed-off-by: Zhou Minqiang <zhouminqiang2(a)huawei.com> --- fs/proc/base.c | 2 -- fs/proc/inode.c | 19 ++++++++----------- 2 files changed, 8 insertions(+), 13 deletions(-) diff --git a/fs/proc/base.c b/fs/proc/base.c index 7ee2285910bb..f34e357e9f97 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1932,8 +1932,6 @@ void proc_pid_evict_inode(struct proc_inode *ei) hlist_del_init_rcu(&ei->sibling_inodes); spin_unlock(&pid->lock); } - - put_pid(pid); } struct inode *proc_pid_make_inode(struct super_block *sb, diff --git a/fs/proc/inode.c b/fs/proc/inode.c index 92772702d369..85a09918507e 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -30,7 +30,6 @@ static void proc_evict_inode(struct inode *inode) { - struct proc_dir_entry *de; struct ctl_table_header *head; struct proc_inode *ei = PROC_I(inode); @@ -38,17 +37,8 @@ static void proc_evict_inode(struct inode *inode) clear_inode(inode); /* Stop tracking associated processes */ - if (ei->pid) { + if (ei->pid) proc_pid_evict_inode(ei); - ei->pid = NULL; - } - - /* Let go of any associated proc directory entry */ - de = ei->pde; - if (de) { - pde_put(de); - ei->pde = NULL; - } head = ei->sysctl; if (head) { @@ -80,6 +70,13 @@ static struct inode *proc_alloc_inode(struct super_block *sb) static void proc_free_inode(struct inode *inode) { + struct proc_inode *ei = PROC_I(inode); + + if (ei->pid) + put_pid(ei->pid); + /* Let go of any associated proc directory entry */ + if (ei->pde) + pde_put(ei->pde); kmem_cache_free(proc_inode_cachep, PROC_I(inode)); } -- 2.52.0

2 1

[PATCH OLK-6.6 0/2] Fix KASAN: slab-use-after-free Read in r1buf_pool_alloc
by Zhou Minqiang 12 Oct '26

12 Oct '26

Fix KASAN: slab-use-after-free Read in r1buf_pool_alloc Zhou Minqiang (2): md/raid1: change r1conf->r1bio_pool to a pointer type md/raid1: remove struct pool_info and related code drivers/md/raid1.c | 86 +++++++++++++++++----------------------------- drivers/md/raid1.h | 22 +----------- 2 files changed, 32 insertions(+), 76 deletions(-) -- 2.52.0

2 3

[PATCH OLK-5.10] procfs: move dropping pde and pid from ->evict_inode() to ->free_inode()
by Zhou Minqiang 12 Oct '26

12 Oct '26

mainline inclusion from mainline-v6.8-rc6 commit 47458802f6606f652cd0f6dc38cd52ce60ec0145 category: bugfix bugzilla: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- that keeps both around until struct inode is freed, making access to them safe from rcu-pathwalk Acked-by: Christian Brauner <brauner(a)kernel.org> Signed-off-by: Al Viro <viro(a)zeniv.linux.org.uk> Signed-off-by: Zhou Minqiang <zhouminqiang2(a)huawei.com> --- fs/proc/base.c | 2 -- fs/proc/inode.c | 19 ++++++++----------- 2 files changed, 8 insertions(+), 13 deletions(-) diff --git a/fs/proc/base.c b/fs/proc/base.c index 845897ca7e54..7fa69a84899d 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -2082,8 +2082,6 @@ void proc_pid_evict_inode(struct proc_inode *ei) hlist_del_init_rcu(&ei->sibling_inodes); spin_unlock(&pid->lock); } - - put_pid(pid); } struct inode *proc_pid_make_inode(struct super_block *sb, diff --git a/fs/proc/inode.c b/fs/proc/inode.c index ba35ffc426ea..df934ded1bf2 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -32,7 +32,6 @@ static void proc_evict_inode(struct inode *inode) { - struct proc_dir_entry *de; struct ctl_table_header *head; struct proc_inode *ei = PROC_I(inode); @@ -40,17 +39,8 @@ static void proc_evict_inode(struct inode *inode) clear_inode(inode); /* Stop tracking associated processes */ - if (ei->pid) { + if (ei->pid) proc_pid_evict_inode(ei); - ei->pid = NULL; - } - - /* Let go of any associated proc directory entry */ - de = ei->pde; - if (de) { - pde_put(de); - ei->pde = NULL; - } head = ei->sysctl; if (head) { @@ -82,6 +72,13 @@ static struct inode *proc_alloc_inode(struct super_block *sb) static void proc_free_inode(struct inode *inode) { + struct proc_inode *ei = PROC_I(inode); + + if (ei->pid) + put_pid(ei->pid); + /* Let go of any associated proc directory entry */ + if (ei->pde) + pde_put(ei->pde); kmem_cache_free(proc_inode_cachep, PROC_I(inode)); } -- 2.52.0

2 1

[PATCH OLK-5.10 0/2] Fix KASAN: slab-use-after-free Read in r1buf_pool_alloc
by Zhou Minqiang 12 Oct '26

12 Oct '26

Fix KASAN: slab-use-after-free Read in r1buf_pool_alloc Zhou Minqiang (2): md/raid1: change r1conf->r1bio_pool to a pointer type md/raid1: remove struct pool_info and related code drivers/md/raid1.c | 84 +++++++++++++++++----------------------------- drivers/md/raid1.h | 22 +----------- 2 files changed, 31 insertions(+), 75 deletions(-) -- 2.52.0

2 3

[PATCH OLK-5.10] bpf: Don't predict JMP32 pointer vs zero comparisons
by Chen Yuxi 12 Oct '26

12 Oct '26

From: Eduard Zingerman <eddyz87(a)gmail.com> mainline inclusion from mainline-v7.3-rc2 commit e51179a4e09846f8fd0f26a05068520de2b301bf category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/19773 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Consider the following program: r1 = map_value; /* low 32 bits are zero at runtime */ r6 = 0xdead000000000000; if w1 != 0 goto l1; l0: r1 += r6; r2 = *(u64 *)(r1 + 0); exit; l1: r6 = 0; goto l0; At the moment is_branch_taken() reports the jump as always taken, because it does not distinguish between BPF_JMP and BPF_JMP32 comparisons when processing 'if w1 != 0 ...'. Fixes: cac616db39c2 ("bpf: Verifier track null pointer branch_taken with JNE and JEQ") Reported-by: Nicholas Carlini <npc(a)anthropic.com> Suggested-by: Nicholas Carlini <npc(a)anthropic.com> Signed-off-by: Eduard Zingerman <eddyz87(a)gmail.com> Link: https://lore.kernel.org/bpf/20260904083325.2083493-5-eddyz87@gmail.com Signed-off-by: Kumar Kartikeya Dwivedi <memxor(a)gmail.com> Conflicts: kernel/bpf/verifier.c [commit b254c6d816e53ca02856b6f46b4dc56caf6e7713 not backport] Signed-off-by: Chen Yuxi <chenyuxi19(a)huawei.com> --- kernel/bpf/verifier.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index d75b3aa76dfc..80fe5730da51 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -7909,6 +7909,13 @@ static int is_branch_taken(struct bpf_reg_state *reg, u64 val, u8 opcode, bool is_jmp32) { if (__is_pointer_value(false, reg)) { + /* + * The low 32 bits of a valid pointer may well be zero, hence + * nothing below applies to a 32-bit comparison. + */ + if (is_jmp32) + return -1; + if (!reg_type_not_null(reg->type)) return -1; -- 2.34.1

2 1

[PATCH OLK-5.10] bpf: mark a NULL call argument precise
by Chen Yuxi 12 Oct '26

12 Oct '26

From: Eduard Zingerman <eddyz87(a)gmail.com> mainline inclusion from mainline-v7.3-rc2 commit 1a3a10b030c96ea88868ccc060a16827c01eaa5a category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/19832 CVE: CVE-2026-98019 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- check_func_arg() allows bpf_register_is_null() for nullable arguments w/o marking the underlying scalar register precise. Hence a checkpoint created on such a path would prune against arbitrary scalar value. check_helper_call() enforces second parameter of the bpf_get_local_storage() to be zero, w/o marking the underlying scalar register precise. Hence a checkpoint created on such a path would prune against arbitrary scalar value. Grouping these two into one patch, as they share the same fixes tag. Fixes: b5dc0163d8fd ("bpf: precise scalar_value tracking") Signed-off-by: Eduard Zingerman <eddyz87(a)gmail.com> Link: https://lore.kernel.org/r/20260904-register-is-null-precise-fixes-v1-1-0f5a… Signed-off-by: Alexei Starovoitov <ast(a)kernel.org> Conflicts: kernel/bpf/verifier.c, tools/testing/selftests/bpf/progs/verifier_subprog_precision.c [verifier_subprog_precision.c does not exist in 5.10.] Signed-off-by: Chen Yuxi <chenyuxi19(a)huawei.com> --- kernel/bpf/verifier.c | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index d75b3aa76dfc..3af71ac0da16 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -4926,11 +4926,15 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg, return err; } - if (register_is_null(reg) && type_may_be_null(arg_type)) + if (register_is_null(reg) && type_may_be_null(arg_type)) { /* A NULL register has a SCALAR_VALUE type, so skip * type checking. */ + err = mark_chain_precision(env, regno); + if (err) + return err; goto skip_type_check; + } /* arg_btf_id and arg_size are in a union. */ if (base_type(arg_type) == ARG_PTR_TO_BTF_ID) @@ -5891,10 +5895,14 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn /* check that flags argument in get_local_storage(map, flags) is 0, * this is required because get_local_storage() can't return an error. */ - if (func_id == BPF_FUNC_get_local_storage && - !register_is_null(&regs[BPF_REG_2])) { - verbose(env, "get_local_storage() doesn't support non-zero flags\n"); - return -EINVAL; + if (func_id == BPF_FUNC_get_local_storage) { + if (!register_is_null(&regs[BPF_REG_2])) { + verbose(env, "get_local_storage() doesn't support non-zero flags\n"); + return -EINVAL; + } + err = mark_chain_precision(env, BPF_REG_2); + if (err) + return err; } /* reset caller saved regs */ -- 2.34.1

2 1

[PATCH OLK-6.6] bpf: mark a NULL call argument precise
by Chen Yuxi 12 Oct '26

12 Oct '26

From: Eduard Zingerman <eddyz87(a)gmail.com> mainline inclusion from mainline-v7.3-rc2 commit 1a3a10b030c96ea88868ccc060a16827c01eaa5a category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/19832 CVE: CVE-2026-98019 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- check_func_arg() allows bpf_register_is_null() for nullable arguments w/o marking the underlying scalar register precise. Hence a checkpoint created on such a path would prune against arbitrary scalar value. check_helper_call() enforces second parameter of the bpf_get_local_storage() to be zero, w/o marking the underlying scalar register precise. Hence a checkpoint created on such a path would prune against arbitrary scalar value. Grouping these two into one patch, as they share the same fixes tag. Fixes: b5dc0163d8fd ("bpf: precise scalar_value tracking") Signed-off-by: Eduard Zingerman <eddyz87(a)gmail.com> Link: https://lore.kernel.org/r/20260904-register-is-null-precise-fixes-v1-1-0f5a… Signed-off-by: Alexei Starovoitov <ast(a)kernel.org> Conflicts: kernel/bpf/verifier.c [ctx conflict] Signed-off-by: Chen Yuxi <chenyuxi19(a)huawei.com> --- kernel/bpf/verifier.c | 9 ++++++++- .../selftests/bpf/progs/verifier_subprog_precision.c | 12 ++++++------ 2 files changed, 14 insertions(+), 7 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 6150ee2a1633..b27408fec62a 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -8692,11 +8692,15 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg, return err; } - if (register_is_null(reg) && type_may_be_null(arg_type)) + if (register_is_null(reg) && type_may_be_null(arg_type)) { /* A NULL register has a SCALAR_VALUE type, so skip * type checking. */ + err = mark_chain_precision(env, regno); + if (err) + return err; goto skip_type_check; + } /* arg_btf_id and arg_size are in a union. */ if (base_type(arg_type) == ARG_PTR_TO_BTF_ID || @@ -10369,6 +10373,9 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn verbose(env, "get_local_storage() doesn't support non-zero flags\n"); return -EINVAL; } + err = mark_chain_precision(env, BPF_REG_2); + if (err) + return err; break; case BPF_FUNC_for_each_map_elem: err = push_callback_call(env, insn, insn_idx, meta.subprogno, diff --git a/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c index 83d187de7f6b..d444b32d0af3 100644 --- a/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c +++ b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c @@ -150,9 +150,9 @@ __msg("17: (b7) r0 = 0") __msg("18: (95) exit") __msg("returning from callee:") __msg("to caller at 9:") -__msg("frame 0: propagating r1,r4") +__msg("frame 0: propagating r1,r3,r4") __msg("mark_precise: frame0: last_idx 9 first_idx 9 subseq_idx -1") -__msg("mark_precise: frame0: regs=r1,r4 stack= before 18: (95) exit") +__msg("mark_precise: frame0: regs=r1,r3,r4 stack= before 18: (95) exit") __msg("from 18 to 9: safe") __naked int callback_result_precise(void) { @@ -282,9 +282,9 @@ __msg("to caller at 9:") /* r1, r4 are always precise for bpf_loop(), * r6 was marked before backtracking to callback body. */ -__msg("frame 0: propagating r1,r4,r6") +__msg("frame 0: propagating r1,r3,r4,r6") __msg("mark_precise: frame0: last_idx 9 first_idx 9 subseq_idx -1") -__msg("mark_precise: frame0: regs=r1,r4,r6 stack= before 16: (95) exit") +__msg("mark_precise: frame0: regs=r1,r3,r4,r6 stack= before 16: (95) exit") __msg("mark_precise: frame1: regs= stack= before 15: (b7) r0 = 0") __msg("mark_precise: frame1: regs= stack= before 9: (85) call bpf_loop") __msg("mark_precise: frame0: parent state regs= stack=:") @@ -438,9 +438,9 @@ __msg("to caller at 10:") /* r1, r4 are always precise for bpf_loop(), * fp-8 was marked before backtracking to callback body. */ -__msg("frame 0: propagating r1,r4,fp-8") +__msg("frame 0: propagating r1,r3,r4,fp-8") __msg("mark_precise: frame0: last_idx 10 first_idx 10 subseq_idx -1") -__msg("mark_precise: frame0: regs=r1,r4 stack=-8 before 18: (95) exit") +__msg("mark_precise: frame0: regs=r1,r3,r4 stack=-8 before 18: (95) exit") __msg("mark_precise: frame1: regs= stack= before 17: (b7) r0 = 0") __msg("mark_precise: frame1: regs= stack= before 10: (85) call bpf_loop#181") __msg("mark_precise: frame0: parent state regs= stack=:") -- 2.34.1

2 1

[PATCH OLK-6.6 0/9] cache: Support cache maintenance for HiSilicon
by Yushan Wang 12 Oct '26

12 Oct '26

From: Hongye Lin <linhongye(a)h-partners.com> driver inclusion category: feature bugzilla: https://atomgit.com/openeuler/kernel/issues/10043 ---------------------------------------------------------------------- Jonathan Cameron (4): memregion: Drop unused IORES_DESC_* parameter from cpu_cache_invalidate_memregion() arm64: Select GENERIC_CPU_CACHE_MAINTENANCE MAINTAINERS: Add Jonathan Cameron to drivers/cache and add lib/cache_maint.c + header cache: Make top level Kconfig menu a boolean dependent on RISCV Yicong Yang (2): memregion: Support fine grained invalidate by cpu_cache_invalidate_memregion() lib: Support ARCH_HAS_CPU_CACHE_INVALIDATE_MEMREGION Yushan Wang (3): soc cache: remove old cache maintain cache: Support cache maintenance for HiSilicon SoC Hydra Home Agent defconfig: Add cache maintain related config MAINTAINERS | 4 +- arch/arm64/Kconfig | 2 + arch/arm64/configs/openeuler_defconfig | 9 +- arch/x86/mm/pat/set_memory.c | 2 +- drivers/cache/Kconfig | 28 +++- drivers/cache/Makefile | 2 + .../{soc/hisilicon => cache}/hisi_soc_hha.c | 152 +++++++++--------- drivers/cxl/core/region.c | 5 +- drivers/nvdimm/region.c | 2 +- drivers/nvdimm/region_devs.c | 2 +- drivers/soc/hisilicon/Kconfig | 12 -- drivers/soc/hisilicon/Makefile | 1 - .../soc/hisilicon/hisi_soc_cache_framework.c | 112 ------------- .../soc/hisilicon/hisi_soc_cache_framework.h | 10 -- include/linux/cache_coherency.h | 61 +++++++ include/linux/memregion.h | 16 +- .../uapi/misc/hisi_soc_cache/hisi_soc_cache.h | 37 ----- lib/Kconfig | 3 + lib/Makefile | 2 + lib/cache_maint.c | 138 ++++++++++++++++ 20 files changed, 338 insertions(+), 262 deletions(-) rename drivers/{soc/hisilicon => cache}/hisi_soc_hha.c (50%) create mode 100644 include/linux/cache_coherency.h delete mode 100644 include/uapi/misc/hisi_soc_cache/hisi_soc_cache.h create mode 100644 lib/cache_maint.c -- 2.33.0

2 10

[PATCH OLK-6.6 00/10] cache: Support cache maintenance for HiSilicon
by Yushan Wang 12 Oct '26

12 Oct '26

From: Hongye Lin <linhongye(a)h-partners.com> driver inclusion category: feature bugzilla: https://atomgit.com/openeuler/kernel/issues/10043 ---------------------------------------------------------------------- Jonathan Cameron (4): memregion: Drop unused IORES_DESC_* parameter from cpu_cache_invalidate_memregion() arm64: Select GENERIC_CPU_CACHE_MAINTENANCE MAINTAINERS: Add Jonathan Cameron to drivers/cache and add lib/cache_maint.c + header cache: Make top level Kconfig menu a boolean dependent on RISCV Yicong Yang (2): memregion: Support fine grained invalidate by cpu_cache_invalidate_memregion() lib: Support ARCH_HAS_CPU_CACHE_INVALIDATE_MEMREGION Yushan Wang (4): mm: reclaim_notify: move struct reclaim_notify_data out of CONFIG_RECLAIM_NOTIFY soc cache: remove old cache maintain cache: Support cache maintenance for HiSilicon SoC Hydra Home Agent defconfig: Add cache maintain related config MAINTAINERS | 4 +- arch/arm64/Kconfig | 2 + arch/arm64/configs/openeuler_defconfig | 9 +- arch/x86/mm/pat/set_memory.c | 2 +- drivers/cache/Kconfig | 28 +++- drivers/cache/Makefile | 2 + .../{soc/hisilicon => cache}/hisi_soc_hha.c | 152 +++++++++--------- drivers/cxl/core/region.c | 5 +- drivers/nvdimm/region.c | 2 +- drivers/nvdimm/region_devs.c | 2 +- drivers/soc/hisilicon/Kconfig | 12 -- drivers/soc/hisilicon/Makefile | 1 - .../soc/hisilicon/hisi_soc_cache_framework.c | 112 ------------- .../soc/hisilicon/hisi_soc_cache_framework.h | 10 -- include/linux/cache_coherency.h | 61 +++++++ include/linux/memregion.h | 16 +- include/linux/mm.h | 3 +- .../uapi/misc/hisi_soc_cache/hisi_soc_cache.h | 37 ----- lib/Kconfig | 3 + lib/Makefile | 2 + lib/cache_maint.c | 138 ++++++++++++++++ 21 files changed, 339 insertions(+), 264 deletions(-) rename drivers/{soc/hisilicon => cache}/hisi_soc_hha.c (50%) create mode 100644 include/linux/cache_coherency.h delete mode 100644 include/uapi/misc/hisi_soc_cache/hisi_soc_cache.h create mode 100644 lib/cache_maint.c -- 2.33.0

2 11

[PATCH OLK-5.10] openvswitch: Fix CT limit teardown use-after-free
by Gu Bowen 10 Oct '26

10 Oct '26

From: Yuqi Xu <xuyuqiabc(a)gmail.com> stable inclusion from stable-v5.10.270 commit 239f26589a6926db28c436e14f28517581ef1385 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/18852 CVE: CVE-2026-89488 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 403f96c32c9e24600093d7d0c61c17daeedca957 ] Packet processing uses CT limit state under RCU, while netns teardown frees that state under ovs_mutex. The CT limit pointer was neither removed from readers nor protected by a grace period, allowing packet processing to dereference the freed state. An unprivileged user can trigger this bug from a user and network namespace, causing a slab-use-after-free in ovs_ct_execute() when the netns is torn down. Publish the CT limit pointer through RCU, remove it before teardown, and wait for readers before freeing its contents. Keep ovs_mutex around individual CT limit updates, and use the RCU read-side lock while GET traverses the RCU-protected limit lists. Netns teardown detaches the RCU-protected CT limit state in the pernet .pre_exit callback while holding ovs_mutex. The pernet core guarantees an RCU grace period between the .pre_exit and .exit callbacks, so the .exit callback completes the teardown without adding any extra synchronization. The netlink command handlers do not need NULL checks because the userspace netlink socket holds an active reference to its network namespace while a request is processed. The per-netns exit path therefore cannot run concurrently with SET, DEL, or GET for that socket's namespace. Fixes: 11efd5cb04a1 ("openvswitch: Support conntrack zone limit") Cc: stable(a)vger.kernel.org Reported-by: Vega <vega(a)nebusec.ai> Link: https://lore.kernel.org/all/cover.1784711445.git.xuyuqiabc@gmail.com Co-developed-by: Nan Li <tonanli66(a)gmail.com> Signed-off-by: Nan Li <tonanli66(a)gmail.com> Signed-off-by: Yuqi Xu <xuyuqiabc(a)gmail.com> Reviewed-by: Ren Wei <enjou1224z(a)gmail.com> Reviewed-by: Ilya Maximets <i.maximets(a)ovn.org> Link: https://patch.msgid.link/288fbd5459d92b9dd0dcc6faf625f04819161ff3.178728029… Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> [ 7.0+ uses kmalloc_obj[s] while older versions use kmalloc[_array] 6.12+ doesn't have a 'family' argument in nf_conncount_init/destroy ] Signed-off-by: Ilya Maximets <i.maximets(a)ovn.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Conflicts: net/openvswitch/conntrack.c net/openvswitch/datapath.h [Context conflicts.] Signed-off-by: Gu Bowen <gubowen5(a)huawei.com> --- net/openvswitch/conntrack.c | 122 +++++++++++++++++++++++------------- net/openvswitch/conntrack.h | 6 +- net/openvswitch/datapath.c | 10 ++- net/openvswitch/datapath.h | 7 ++- 4 files changed, 98 insertions(+), 47 deletions(-) diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 30f5e414018b..c52818a9f38d 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -1156,10 +1156,14 @@ static int ovs_ct_check_limit(struct net *net, const struct nf_conntrack_tuple *tuple) { struct ovs_net *ovs_net = net_generic(net, ovs_net_id); - const struct ovs_ct_limit_info *ct_limit_info = ovs_net->ct_limit_info; + const struct ovs_ct_limit_info *ct_limit_info; u32 per_zone_limit, connections; u32 conncount_key; + ct_limit_info = rcu_dereference(ovs_net->ct_limit_info); + if (!ct_limit_info) + return 0; + conncount_key = info->zone.id; per_zone_limit = ct_limit_get(ct_limit_info, info->zone.id); @@ -1861,43 +1865,56 @@ static void __ovs_ct_free_action(struct ovs_conntrack_info *ct_info) #if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT) static int ovs_ct_limit_init(struct net *net, struct ovs_net *ovs_net) { + struct ovs_ct_limit_info *info; int i, err; - ovs_net->ct_limit_info = kmalloc(sizeof(*ovs_net->ct_limit_info), - GFP_KERNEL); - if (!ovs_net->ct_limit_info) + info = kmalloc(sizeof(*info), GFP_KERNEL); + if (!info) return -ENOMEM; - ovs_net->ct_limit_info->default_limit = OVS_CT_LIMIT_DEFAULT; - ovs_net->ct_limit_info->limits = + info->default_limit = OVS_CT_LIMIT_DEFAULT; + info->limits = kmalloc_array(CT_LIMIT_HASH_BUCKETS, sizeof(struct hlist_head), GFP_KERNEL); - if (!ovs_net->ct_limit_info->limits) { - kfree(ovs_net->ct_limit_info); + if (!info->limits) { + kfree(info); return -ENOMEM; } for (i = 0; i < CT_LIMIT_HASH_BUCKETS; i++) - INIT_HLIST_HEAD(&ovs_net->ct_limit_info->limits[i]); + INIT_HLIST_HEAD(&info->limits[i]); - ovs_net->ct_limit_info->data = - nf_conncount_init(net, NFPROTO_INET, sizeof(u32)); + info->data = nf_conncount_init(net, NFPROTO_INET, sizeof(u32)); - if (IS_ERR(ovs_net->ct_limit_info->data)) { - err = PTR_ERR(ovs_net->ct_limit_info->data); - kfree(ovs_net->ct_limit_info->limits); - kfree(ovs_net->ct_limit_info); + if (IS_ERR(info->data)) { + err = PTR_ERR(info->data); + kfree(info->limits); + kfree(info); pr_err("openvswitch: failed to init nf_conncount %d\n", err); return err; } + rcu_assign_pointer(ovs_net->ct_limit_info, info); return 0; } -static void ovs_ct_limit_exit(struct net *net, struct ovs_net *ovs_net) +static void *ovs_ct_limit_exit_start(struct ovs_net *ovs_net) +{ + return rcu_replace_pointer(ovs_net->ct_limit_info, NULL, + lockdep_ovsl_is_held()); +} + +/* The CT limit state must be detached by ovs_ct_limit_exit_start() and an + * RCU grace period must elapse before this function runs. The pernet core + * guarantees the grace period between the .pre_exit and .exit callbacks. + */ +static void ovs_ct_limit_exit_finish(struct net *net, void *data) { - const struct ovs_ct_limit_info *info = ovs_net->ct_limit_info; + const struct ovs_ct_limit_info *info = data; int i; + if (!info) + return; + nf_conncount_destroy(net, NFPROTO_INET, info->data); for (i = 0; i < CT_LIMIT_HASH_BUCKETS; ++i) { struct hlist_head *head = &info->limits[i]; @@ -1905,7 +1922,7 @@ static void ovs_ct_limit_exit(struct net *net, struct ovs_net *ovs_net) struct hlist_node *next; hlist_for_each_entry_safe(ct_limit, next, head, hlist_node) - kfree_rcu(ct_limit, rcu); + kfree(ct_limit); } kfree(info->limits); kfree(info); @@ -1944,12 +1961,13 @@ static bool check_zone_id(int zone_id, u16 *pzone) return false; } -static int ovs_ct_limit_set_zone_limit(struct nlattr *nla_zone_limit, - struct ovs_ct_limit_info *info) +static int ovs_ct_limit_set_zone_limit(struct ovs_net *ovs_net, + struct nlattr *nla_zone_limit) { struct ovs_zone_limit *zone_limit; - int rem; + struct ovs_ct_limit_info *info; u16 zone; + int rem; rem = NLA_ALIGN(nla_len(nla_zone_limit)); zone_limit = (struct ovs_zone_limit *)nla_data(nla_zone_limit); @@ -1958,6 +1976,7 @@ static int ovs_ct_limit_set_zone_limit(struct nlattr *nla_zone_limit, if (unlikely(zone_limit->zone_id == OVS_ZONE_LIMIT_DEFAULT_ZONE)) { ovs_lock(); + info = ovsl_dereference(ovs_net->ct_limit_info); info->default_limit = zone_limit->limit; ovs_unlock(); } else if (unlikely(!check_zone_id( @@ -1974,6 +1993,7 @@ static int ovs_ct_limit_set_zone_limit(struct nlattr *nla_zone_limit, ct_limit->limit = zone_limit->limit; ovs_lock(); + info = ovsl_dereference(ovs_net->ct_limit_info); ct_limit_set(info, ct_limit); ovs_unlock(); } @@ -1988,12 +2008,13 @@ static int ovs_ct_limit_set_zone_limit(struct nlattr *nla_zone_limit, return 0; } -static int ovs_ct_limit_del_zone_limit(struct nlattr *nla_zone_limit, - struct ovs_ct_limit_info *info) +static int ovs_ct_limit_del_zone_limit(struct ovs_net *ovs_net, + struct nlattr *nla_zone_limit) { struct ovs_zone_limit *zone_limit; - int rem; + struct ovs_ct_limit_info *info; u16 zone; + int rem; rem = NLA_ALIGN(nla_len(nla_zone_limit)); zone_limit = (struct ovs_zone_limit *)nla_data(nla_zone_limit); @@ -2002,6 +2023,7 @@ static int ovs_ct_limit_del_zone_limit(struct nlattr *nla_zone_limit, if (unlikely(zone_limit->zone_id == OVS_ZONE_LIMIT_DEFAULT_ZONE)) { ovs_lock(); + info = ovsl_dereference(ovs_net->ct_limit_info); info->default_limit = OVS_CT_LIMIT_DEFAULT; ovs_unlock(); } else if (unlikely(!check_zone_id( @@ -2009,6 +2031,7 @@ static int ovs_ct_limit_del_zone_limit(struct nlattr *nla_zone_limit, OVS_NLERR(true, "zone id is out of range"); } else { ovs_lock(); + info = ovsl_dereference(ovs_net->ct_limit_info); ct_limit_del(info, zone); ovs_unlock(); } @@ -2052,6 +2075,7 @@ static int __ovs_ct_limit_get_zone_limit(struct net *net, return nla_put_nohdr(reply, sizeof(zone_limit), &zone_limit); } +/* Called with RCU read lock held. */ static int ovs_ct_limit_get_zone_limit(struct net *net, struct nlattr *nla_zone_limit, struct ovs_ct_limit_info *info, @@ -2075,9 +2099,7 @@ static int ovs_ct_limit_get_zone_limit(struct net *net, &zone))) { OVS_NLERR(true, "zone id is out of range"); } else { - rcu_read_lock(); limit = ct_limit_get(info, zone); - rcu_read_unlock(); err = __ovs_ct_limit_get_zone_limit( net, info->data, zone, limit, reply); @@ -2095,6 +2117,7 @@ static int ovs_ct_limit_get_zone_limit(struct net *net, return 0; } +/* Called with RCU read lock held. */ static int ovs_ct_limit_get_all_zone_limit(struct net *net, struct ovs_ct_limit_info *info, struct sk_buff *reply) @@ -2107,19 +2130,16 @@ static int ovs_ct_limit_get_all_zone_limit(struct net *net, if (err) return err; - rcu_read_lock(); for (i = 0; i < CT_LIMIT_HASH_BUCKETS; ++i) { head = &info->limits[i]; hlist_for_each_entry_rcu(ct_limit, head, hlist_node) { err = __ovs_ct_limit_get_zone_limit(net, info->data, ct_limit->zone, ct_limit->limit, reply); if (err) - goto exit_err; + return err; } } -exit_err: - rcu_read_unlock(); return err; } @@ -2129,7 +2149,6 @@ static int ovs_ct_limit_cmd_set(struct sk_buff *skb, struct genl_info *info) struct sk_buff *reply; struct ovs_header *ovs_reply_header; struct ovs_net *ovs_net = net_generic(sock_net(skb->sk), ovs_net_id); - struct ovs_ct_limit_info *ct_limit_info = ovs_net->ct_limit_info; int err; reply = ovs_ct_limit_cmd_reply_start(info, OVS_CT_LIMIT_CMD_SET, @@ -2142,8 +2161,8 @@ static int ovs_ct_limit_cmd_set(struct sk_buff *skb, struct genl_info *info) goto exit_err; } - err = ovs_ct_limit_set_zone_limit(a[OVS_CT_LIMIT_ATTR_ZONE_LIMIT], - ct_limit_info); + err = ovs_ct_limit_set_zone_limit(ovs_net, + a[OVS_CT_LIMIT_ATTR_ZONE_LIMIT]); if (err) goto exit_err; @@ -2163,7 +2182,6 @@ static int ovs_ct_limit_cmd_del(struct sk_buff *skb, struct genl_info *info) struct sk_buff *reply; struct ovs_header *ovs_reply_header; struct ovs_net *ovs_net = net_generic(sock_net(skb->sk), ovs_net_id); - struct ovs_ct_limit_info *ct_limit_info = ovs_net->ct_limit_info; int err; reply = ovs_ct_limit_cmd_reply_start(info, OVS_CT_LIMIT_CMD_DEL, @@ -2176,8 +2194,8 @@ static int ovs_ct_limit_cmd_del(struct sk_buff *skb, struct genl_info *info) goto exit_err; } - err = ovs_ct_limit_del_zone_limit(a[OVS_CT_LIMIT_ATTR_ZONE_LIMIT], - ct_limit_info); + err = ovs_ct_limit_del_zone_limit(ovs_net, + a[OVS_CT_LIMIT_ATTR_ZONE_LIMIT]); if (err) goto exit_err; @@ -2197,7 +2215,7 @@ static int ovs_ct_limit_cmd_get(struct sk_buff *skb, struct genl_info *info) struct ovs_header *ovs_reply_header; struct net *net = sock_net(skb->sk); struct ovs_net *ovs_net = net_generic(net, ovs_net_id); - struct ovs_ct_limit_info *ct_limit_info = ovs_net->ct_limit_info; + struct ovs_ct_limit_info *ct_limit_info; int err; reply = ovs_ct_limit_cmd_reply_start(info, OVS_CT_LIMIT_CMD_GET, @@ -2211,18 +2229,19 @@ static int ovs_ct_limit_cmd_get(struct sk_buff *skb, struct genl_info *info) goto exit_err; } + rcu_read_lock(); + ct_limit_info = rcu_dereference(ovs_net->ct_limit_info); if (a[OVS_CT_LIMIT_ATTR_ZONE_LIMIT]) { err = ovs_ct_limit_get_zone_limit( net, a[OVS_CT_LIMIT_ATTR_ZONE_LIMIT], ct_limit_info, reply); - if (err) - goto exit_err; } else { err = ovs_ct_limit_get_all_zone_limit(net, ct_limit_info, reply); - if (err) - goto exit_err; } + rcu_read_unlock(); + if (err) + goto exit_err; nla_nest_end(reply, nla_reply); genlmsg_end(reply, ovs_reply_header); @@ -2292,12 +2311,29 @@ int ovs_ct_init(struct net *net) #endif } -void ovs_ct_exit(struct net *net) +/* Must be called with ovs_mutex held. Detaches the RCU-protected + * ct_limit_info and stores it in ovs_net->ct_limit_exit_data for + * ovs_ct_exit_finish() to complete the teardown after an RCU grace period. + */ +void ovs_ct_exit_start(struct net *net __maybe_unused) +{ +#if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT) + struct ovs_net *ovs_net = net_generic(net, ovs_net_id); + + ovs_net->ct_limit_exit_data = ovs_ct_limit_exit_start(ovs_net); +#endif +} + +/* Completes the CT limit teardown. The pernet core guarantees an RCU + * grace period between detaching the state in ovs_ct_exit_start() and + * this call, so no RCU readers remain. + */ +void ovs_ct_exit_finish(struct net *net) { struct ovs_net *ovs_net = net_generic(net, ovs_net_id); #if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT) - ovs_ct_limit_exit(net, ovs_net); + ovs_ct_limit_exit_finish(net, ovs_net->ct_limit_exit_data); #endif if (ovs_net->xt_label) diff --git a/net/openvswitch/conntrack.h b/net/openvswitch/conntrack.h index 59dc32761b91..ad9081d7023d 100644 --- a/net/openvswitch/conntrack.h +++ b/net/openvswitch/conntrack.h @@ -14,7 +14,8 @@ enum ovs_key_attr; #if IS_ENABLED(CONFIG_NF_CONNTRACK) int ovs_ct_init(struct net *); -void ovs_ct_exit(struct net *); +void ovs_ct_exit_start(struct net *net); +void ovs_ct_exit_finish(struct net *net); bool ovs_ct_verify(struct net *, enum ovs_key_attr attr); int ovs_ct_copy_action(struct net *, const struct nlattr *, const struct sw_flow_key *, struct sw_flow_actions **, @@ -39,7 +40,8 @@ void ovs_ct_free_action(const struct nlattr *a); static inline int ovs_ct_init(struct net *net) { return 0; } -static inline void ovs_ct_exit(struct net *net) { } +static inline void ovs_ct_exit_start(struct net *net) { } +static inline void ovs_ct_exit_finish(struct net *net) { } static inline bool ovs_ct_verify(struct net *net, int attr) { diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index ec1e4af1dec0..34170c744cc3 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -2575,6 +2575,13 @@ static void __net_exit list_vports_from_net(struct net *net, struct net *dnet, } } +static void __net_exit ovs_pre_exit_net(struct net *dnet) +{ + ovs_lock(); + ovs_ct_exit_start(dnet); + ovs_unlock(); +} + static void __net_exit ovs_exit_net(struct net *dnet) { struct datapath *dp, *dp_next; @@ -2585,7 +2592,7 @@ static void __net_exit ovs_exit_net(struct net *dnet) ovs_lock(); - ovs_ct_exit(dnet); + ovs_ct_exit_finish(dnet); list_for_each_entry_safe(dp, dp_next, &ovs_net->dps, list_node) __dp_destroy(dp); @@ -2609,6 +2616,7 @@ static void __net_exit ovs_exit_net(struct net *dnet) static struct pernet_operations ovs_net_ops = { .init = ovs_init_net, + .pre_exit = ovs_pre_exit_net, .exit = ovs_exit_net, .id = &ovs_net_id, .size = sizeof(struct ovs_net), diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h index 62e7ad32f837..a796a60fea2f 100644 --- a/net/openvswitch/datapath.h +++ b/net/openvswitch/datapath.h @@ -131,13 +131,18 @@ struct dp_upcall_info { * struct ovs_net - Per net-namespace data for ovs. * @dps: List of datapaths to enable dumping them all out. * Protected by genl_mutex. + * @ct_limit_info: Hash table of conntrack zone connection limits. Protected + * by RCU; updates and teardown are serialized by ovs_mutex. May be NULL during + * netns teardown. + * @ct_limit_exit_data: CT limit state detached at .pre_exit, freed at .exit. */ struct ovs_net { struct list_head dps; struct work_struct dp_notify_work; struct delayed_work masks_rebalance; #if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT) - struct ovs_ct_limit_info *ct_limit_info; + struct ovs_ct_limit_info __rcu *ct_limit_info; + struct ovs_ct_limit_info *ct_limit_exit_data; #endif /* Module reference for configuring conntrack. */ -- 2.43.0

2 1