- Kernel - mailweb.openeuler.org

[PATCH OLK-5.10 V1] sched/fair: Prefer physical cores when migrating tasks
by Cheng Yu 12 Aug '24

12 Aug '24

hulk inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/IAJEHU CVE: NA -------------------------------- When cpu hyperthreading is enabled, one physical core can virtualize multiple logical cpus. Assume that physical core0 virtualizes two logical cpus, cpu0 and cpu1. Only when the load of cpu0 exceeds the set threshold, the task will be migrated to the cpu1, otherwise the task will not be migrated and cpu0 will still be used. External impacts: 1) default config in arm64,x86: CONFIG_SCHED_KEEP_ON_CORE=y 2) sysctl: /proc/sys/kernel/sched_util_keep_on_core 3) sched features: KEEP_ON_CORE (default NO_KEEP_ON_CORE) Signed-off-by: Cheng Yu <serein.chengyu(a)huawei.com> --- arch/arm64/configs/openeuler_defconfig | 1 + arch/x86/configs/openeuler_defconfig | 1 + include/linux/sched/sysctl.h | 4 +++ init/Kconfig | 11 ++++++++ kernel/sched/fair.c | 36 ++++++++++++++++++++++++++ kernel/sched/features.h | 4 +++ kernel/sysctl.c | 10 +++++++ 7 files changed, 67 insertions(+) diff --git a/arch/arm64/configs/openeuler_defconfig b/arch/arm64/configs/openeuler_defconfig index 69ff0b64ba59..8c95a5332b40 100644 --- a/arch/arm64/configs/openeuler_defconfig +++ b/arch/arm64/configs/openeuler_defconfig @@ -189,6 +189,7 @@ CONFIG_USER_NS=y CONFIG_PID_NS=y CONFIG_NET_NS=y CONFIG_SCHED_STEAL=y +CONFIG_SCHED_KEEP_ON_CORE=y CONFIG_CHECKPOINT_RESTORE=y CONFIG_SCHED_AUTOGROUP=y # CONFIG_SYSFS_DEPRECATED is not set diff --git a/arch/x86/configs/openeuler_defconfig b/arch/x86/configs/openeuler_defconfig index f3b810d0cf47..65ef2f183b02 100644 --- a/arch/x86/configs/openeuler_defconfig +++ b/arch/x86/configs/openeuler_defconfig @@ -194,6 +194,7 @@ CONFIG_USER_NS=y CONFIG_PID_NS=y CONFIG_NET_NS=y CONFIG_SCHED_STEAL=y +CONFIG_SCHED_KEEP_ON_CORE=y CONFIG_CHECKPOINT_RESTORE=y CONFIG_SCHED_AUTOGROUP=y # CONFIG_SYSFS_DEPRECATED is not set diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 5cd5b3c579d3..fb1436286994 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -35,6 +35,10 @@ extern unsigned int sysctl_sched_child_runs_first; extern int sysctl_sched_util_low_pct; #endif +#ifdef CONFIG_SCHED_KEEP_ON_CORE +extern int sysctl_sched_util_keep_on_core; +#endif + #ifdef CONFIG_QOS_SCHED_SMART_GRID extern unsigned int sysctl_smart_grid_strategy_ctrl; extern int sysctl_affinity_adjust_delay_ms; diff --git a/init/Kconfig b/init/Kconfig index e552194efbea..16a1d7ac726b 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1370,6 +1370,17 @@ config SCHED_STEAL If unsure, say N here. +config SCHED_KEEP_ON_CORE + bool "Prefer physical cores when migrating tasks" + depends on SMP + default n + help + When cpu hyperthreading is enabled, one physical core can virtualize + multiple logical cpus. Assume that physical core0 virtualizes two + logical cpus, cpu0 and cpu1. Only when the load of cpu0 exceeds the + set threshold, the task will be migrated to the cpu1, otherwise the + task will not be migrated and cpu0 will still be used. + config CHECKPOINT_RESTORE bool "Checkpoint/restore support" select PROC_CHILDREN diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 95d1841f8a20..4f3d81537bab 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -4497,6 +4497,12 @@ static inline void overload_clear(struct rq *rq) {} static inline void overload_set(struct rq *rq) {} #endif +#ifdef CONFIG_SCHED_KEEP_ON_CORE +static int core_has_spare(int cpu); +#else +static inline int core_has_spare(int cpu) { return 0; } +#endif + #else /* CONFIG_SMP */ #define UPDATE_TG 0x0 @@ -4523,6 +4529,7 @@ static inline int newidle_balance(struct rq *rq, struct rq_flags *rf) static inline void rq_idle_stamp_update(struct rq *rq) {} static inline void rq_idle_stamp_clear(struct rq *rq) {} static inline int try_steal(struct rq *this_rq, struct rq_flags *rf) { return 0; } +static inline int core_has_spare(int cpu) { return 0; } static inline void overload_clear(struct rq *rq) {} static inline void overload_set(struct rq *rq) {} @@ -8210,6 +8217,13 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f } #endif +#ifdef CONFIG_SCHED_KEEP_ON_CORE + if (static_branch_likely(&sched_smt_present) && + sched_feat(KEEP_ON_CORE)) + if (core_has_spare(new_cpu)) + new_cpu = cpumask_first(cpu_smt_mask((new_cpu))); +#endif + rcu_read_unlock(); #ifdef CONFIG_QOS_SCHED_DYNAMIC_AFFINITY @@ -9701,6 +9715,14 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) } #endif +#ifdef CONFIG_SCHED_KEEP_ON_CORE + if (static_branch_likely(&sched_smt_present) && + sched_feat(KEEP_ON_CORE)) + if (core_has_spare(env->dst_cpu) && + cpumask_first(cpu_smt_mask((env->dst_cpu))) != env->dst_cpu) + return 0; +#endif + /* * We do not migrate tasks that are: * 1) throttled_lb_pair, or @@ -13189,6 +13211,20 @@ static int try_steal(struct rq *dst_rq, struct rq_flags *dst_rf) } #endif +#ifdef CONFIG_SCHED_KEEP_ON_CORE +int sysctl_sched_util_keep_on_core = 100; + +static int core_has_spare(int cpu) +{ + int core_id = cpumask_first(cpu_smt_mask(cpu)); + struct rq *rq = cpu_rq(core_id); + unsigned long util = rq->cfs.avg.util_avg; + unsigned long capacity = rq->cpu_capacity; + + return util * 100 < capacity * sysctl_sched_util_keep_on_core; +} +#endif + static void rq_online_fair(struct rq *rq) { update_sysctl(); diff --git a/kernel/sched/features.h b/kernel/sched/features.h index 76fade025c4b..fb885b20ba34 100644 --- a/kernel/sched/features.h +++ b/kernel/sched/features.h @@ -70,6 +70,10 @@ SCHED_FEAT(SIS_UTIL, false) SCHED_FEAT(STEAL, false) #endif +#ifdef CONFIG_SCHED_KEEP_ON_CORE +SCHED_FEAT(KEEP_ON_CORE, false) +#endif + /* * Issue a WARN when we do multiple update_rq_clock() calls * in a single rq->lock section. Default disabled because the diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 3941856c19d1..9abc01982645 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2817,6 +2817,16 @@ static struct ctl_table kern_table[] = { .extra2 = &one_hundred, }, #endif +#ifdef CONFIG_SCHED_KEEP_ON_CORE + { + .procname = "sched_util_keep_on_core", + .data = &sysctl_sched_util_keep_on_core, + .maxlen = sizeof(sysctl_sched_util_keep_on_core), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + }, +#endif #ifdef CONFIG_QOS_SCHED_SMART_GRID { .procname = "smart_grid_strategy_ctrl", -- 2.25.1

2 1

[PATCH openEuler-1.0-LTS] USB: serial: mos7840: fix crash on resume
by Yi Yang 12 Aug '24

12 Aug '24

From: Dmitry Smirnov <d.smirnov(a)inbox.lv> stable inclusion from stable-v5.10.222 commit 932a86a711c722b45ed47ba2103adca34d225b33 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAILG4 CVE: CVE-2024-42244 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit c15a688e49987385baa8804bf65d570e362f8576 upstream. Since commit c49cfa917025 ("USB: serial: use generic method if no alternative is provided in usb serial layer"), USB serial core calls the generic resume implementation when the driver has not provided one. This can trigger a crash on resume with mos7840 since support for multiple read URBs was added back in 2011. Specifically, both port read URBs are now submitted on resume for open ports, but the context pointer of the second URB is left set to the core rather than mos7840 port structure. Fix this by implementing dedicated suspend and resume functions for mos7840. Tested with Delock 87414 USB 2.0 to 4x serial adapter. Signed-off-by: Dmitry Smirnov <d.smirnov(a)inbox.lv> [ johan: analyse crash and rewrite commit message; set busy flag on resume; drop bulk-in check; drop unnecessary usb_kill_urb() ] Fixes: d83b405383c9 ("USB: serial: add support for multiple read urbs") Cc: stable(a)vger.kernel.org # 3.3 Signed-off-by: Johan Hovold <johan(a)kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Conflicts: drivers/usb/serial/mos7840.c [Context conflict] Signed-off-by: Yi Yang <yiyang13(a)huawei.com> --- drivers/usb/serial/mos7840.c | 45 ++++++++++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+) diff --git a/drivers/usb/serial/mos7840.c b/drivers/usb/serial/mos7840.c index 4a7bd26841af..1d391565dbc6 100644 --- a/drivers/usb/serial/mos7840.c +++ b/drivers/usb/serial/mos7840.c @@ -2364,6 +2364,49 @@ static int mos7840_port_remove(struct usb_serial_port *port) return 0; } +static int mos7840_suspend(struct usb_serial *serial, pm_message_t message) +{ + struct moschip_port *mos7840_port; + struct usb_serial_port *port; + int i; + + for (i = 0; i < serial->num_ports; ++i) { + port = serial->port[i]; + if (!tty_port_initialized(&port->port)) + continue; + + mos7840_port = usb_get_serial_port_data(port); + + usb_kill_urb(mos7840_port->read_urb); + mos7840_port->read_urb_busy = false; + } + + return 0; +} + +static int mos7840_resume(struct usb_serial *serial) +{ + struct moschip_port *mos7840_port; + struct usb_serial_port *port; + int res; + int i; + + for (i = 0; i < serial->num_ports; ++i) { + port = serial->port[i]; + if (!tty_port_initialized(&port->port)) + continue; + + mos7840_port = usb_get_serial_port_data(port); + + mos7840_port->read_urb_busy = true; + res = usb_submit_urb(mos7840_port->read_urb, GFP_NOIO); + if (res) + mos7840_port->read_urb_busy = false; + } + + return 0; +} + static struct usb_serial_driver moschip7840_4port_device = { .driver = { .owner = THIS_MODULE, @@ -2392,6 +2435,8 @@ static struct usb_serial_driver moschip7840_4port_device = { .port_remove = mos7840_port_remove, .read_bulk_callback = mos7840_bulk_in_callback, .read_int_callback = mos7840_interrupt_callback, + .suspend = mos7840_suspend, + .resume = mos7840_resume, }; static struct usb_serial_driver * const serial_drivers[] = { -- 2.25.1

2 1

[PATCH OLK-5.10 V1] sched/fair: Prefer physical cores when migrating tasks
by Cheng Yu 12 Aug '24

12 Aug '24

Only when the load of the physical core exceeds the set threshold, the task will be migrated, otherwise the task will keep on the physical core. External impacts: 1) default config in arm64,x86: CONFIG_SCHED_KEEP_ON_CORE=y 2) sysctl: /proc/sys/kernel/sched_util_keep_on_core 3) sched features: KEEP_ON_CORE (default NO_KEEP_ON_CORE) Signed-off-by: Cheng Yu <serein.chengyu(a)huawei.com> --- arch/arm64/configs/openeuler_defconfig | 1 + arch/x86/configs/openeuler_defconfig | 1 + include/linux/sched/sysctl.h | 4 +++ init/Kconfig | 9 +++++++ kernel/sched/fair.c | 36 ++++++++++++++++++++++++++ kernel/sched/features.h | 4 +++ kernel/sysctl.c | 10 +++++++ 7 files changed, 65 insertions(+) diff --git a/arch/arm64/configs/openeuler_defconfig b/arch/arm64/configs/openeuler_defconfig index 69ff0b64ba59..8c95a5332b40 100644 --- a/arch/arm64/configs/openeuler_defconfig +++ b/arch/arm64/configs/openeuler_defconfig @@ -189,6 +189,7 @@ CONFIG_USER_NS=y CONFIG_PID_NS=y CONFIG_NET_NS=y CONFIG_SCHED_STEAL=y +CONFIG_SCHED_KEEP_ON_CORE=y CONFIG_CHECKPOINT_RESTORE=y CONFIG_SCHED_AUTOGROUP=y # CONFIG_SYSFS_DEPRECATED is not set diff --git a/arch/x86/configs/openeuler_defconfig b/arch/x86/configs/openeuler_defconfig index f3b810d0cf47..65ef2f183b02 100644 --- a/arch/x86/configs/openeuler_defconfig +++ b/arch/x86/configs/openeuler_defconfig @@ -194,6 +194,7 @@ CONFIG_USER_NS=y CONFIG_PID_NS=y CONFIG_NET_NS=y CONFIG_SCHED_STEAL=y +CONFIG_SCHED_KEEP_ON_CORE=y CONFIG_CHECKPOINT_RESTORE=y CONFIG_SCHED_AUTOGROUP=y # CONFIG_SYSFS_DEPRECATED is not set diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 5cd5b3c579d3..fb1436286994 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -35,6 +35,10 @@ extern unsigned int sysctl_sched_child_runs_first; extern int sysctl_sched_util_low_pct; #endif +#ifdef CONFIG_SCHED_KEEP_ON_CORE +extern int sysctl_sched_util_keep_on_core; +#endif + #ifdef CONFIG_QOS_SCHED_SMART_GRID extern unsigned int sysctl_smart_grid_strategy_ctrl; extern int sysctl_affinity_adjust_delay_ms; diff --git a/init/Kconfig b/init/Kconfig index e552194efbea..ee94515b2f04 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1370,6 +1370,15 @@ config SCHED_STEAL If unsure, say N here. +config SCHED_KEEP_ON_CORE + bool "Prefer physical cores when migrating tasks" + depends on SMP + default n + help + Only when the load of the physical core exceeds the set threshold, + the task will be migrated, otherwise the task will keep on the + physical core. + config CHECKPOINT_RESTORE bool "Checkpoint/restore support" select PROC_CHILDREN diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 95d1841f8a20..4f3d81537bab 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -4497,6 +4497,12 @@ static inline void overload_clear(struct rq *rq) {} static inline void overload_set(struct rq *rq) {} #endif +#ifdef CONFIG_SCHED_KEEP_ON_CORE +static int core_has_spare(int cpu); +#else +static inline int core_has_spare(int cpu) { return 0; } +#endif + #else /* CONFIG_SMP */ #define UPDATE_TG 0x0 @@ -4523,6 +4529,7 @@ static inline int newidle_balance(struct rq *rq, struct rq_flags *rf) static inline void rq_idle_stamp_update(struct rq *rq) {} static inline void rq_idle_stamp_clear(struct rq *rq) {} static inline int try_steal(struct rq *this_rq, struct rq_flags *rf) { return 0; } +static inline int core_has_spare(int cpu) { return 0; } static inline void overload_clear(struct rq *rq) {} static inline void overload_set(struct rq *rq) {} @@ -8210,6 +8217,13 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f } #endif +#ifdef CONFIG_SCHED_KEEP_ON_CORE + if (static_branch_likely(&sched_smt_present) && + sched_feat(KEEP_ON_CORE)) + if (core_has_spare(new_cpu)) + new_cpu = cpumask_first(cpu_smt_mask((new_cpu))); +#endif + rcu_read_unlock(); #ifdef CONFIG_QOS_SCHED_DYNAMIC_AFFINITY @@ -9701,6 +9715,14 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) } #endif +#ifdef CONFIG_SCHED_KEEP_ON_CORE + if (static_branch_likely(&sched_smt_present) && + sched_feat(KEEP_ON_CORE)) + if (core_has_spare(env->dst_cpu) && + cpumask_first(cpu_smt_mask((env->dst_cpu))) != env->dst_cpu) + return 0; +#endif + /* * We do not migrate tasks that are: * 1) throttled_lb_pair, or @@ -13189,6 +13211,20 @@ static int try_steal(struct rq *dst_rq, struct rq_flags *dst_rf) } #endif +#ifdef CONFIG_SCHED_KEEP_ON_CORE +int sysctl_sched_util_keep_on_core = 100; + +static int core_has_spare(int cpu) +{ + int core_id = cpumask_first(cpu_smt_mask(cpu)); + struct rq *rq = cpu_rq(core_id); + unsigned long util = rq->cfs.avg.util_avg; + unsigned long capacity = rq->cpu_capacity; + + return util * 100 < capacity * sysctl_sched_util_keep_on_core; +} +#endif + static void rq_online_fair(struct rq *rq) { update_sysctl(); diff --git a/kernel/sched/features.h b/kernel/sched/features.h index 76fade025c4b..fb885b20ba34 100644 --- a/kernel/sched/features.h +++ b/kernel/sched/features.h @@ -70,6 +70,10 @@ SCHED_FEAT(SIS_UTIL, false) SCHED_FEAT(STEAL, false) #endif +#ifdef CONFIG_SCHED_KEEP_ON_CORE +SCHED_FEAT(KEEP_ON_CORE, false) +#endif + /* * Issue a WARN when we do multiple update_rq_clock() calls * in a single rq->lock section. Default disabled because the diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 3941856c19d1..9abc01982645 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2817,6 +2817,16 @@ static struct ctl_table kern_table[] = { .extra2 = &one_hundred, }, #endif +#ifdef CONFIG_SCHED_KEEP_ON_CORE + { + .procname = "sched_util_keep_on_core", + .data = &sysctl_sched_util_keep_on_core, + .maxlen = sizeof(sysctl_sched_util_keep_on_core), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + }, +#endif #ifdef CONFIG_QOS_SCHED_SMART_GRID { .procname = "smart_grid_strategy_ctrl", -- 2.25.1

2 1

[PATCH OLK-5.10 v2] net, sunrpc: Remap EPERM in case of connection failure in xs_tcp_setup_socket
by Liu Jian 12 Aug '24

12 Aug '24

From: Daniel Borkmann <daniel(a)iogearbox.net> mainline inclusion from mainline-v6.10 commit 626dfed5fa3bfb41e0dffd796032b555b69f9cde category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAILGI CVE: CVE-2024-42246 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… ------------------------------------------------- When using a BPF program on kernel_connect(), the call can return -EPERM. This causes xs_tcp_setup_socket() to loop forever, filling up the syslog and causing the kernel to potentially freeze up. Neil suggested: This will propagate -EPERM up into other layers which might not be ready to handle it. It might be safer to map EPERM to an error we would be more likely to expect from the network system - such as ECONNREFUSED or ENETDOWN. ECONNREFUSED as error seems reasonable. For programs setting a different error can be out of reach (see handling in 4fbac77d2d09) in particular on kernels which do not have f10d05966196 ("bpf: Make BPF_PROG_RUN_ARRAY return -err instead of allow boolean"), thus given that it is better to simply remap for consistent behavior. UDP does handle EPERM in xs_udp_send_request(). Fixes: d74bad4e74ee ("bpf: Hooks for sys_connect") Fixes: 4fbac77d2d09 ("bpf: Hooks for sys_bind") Co-developed-by: Lex Siegel <usiegl00(a)gmail.com> Signed-off-by: Lex Siegel <usiegl00(a)gmail.com> Signed-off-by: Daniel Borkmann <daniel(a)iogearbox.net> Cc: Neil Brown <neilb(a)suse.de> Cc: Trond Myklebust <trondmy(a)kernel.org> Cc: Anna Schumaker <anna(a)kernel.org> Link: https://github.com/cilium/cilium/issues/33395 Link: https://lore.kernel.org/bpf/171374175513.12877.8993642908082014881@noble.ne… Link: https://patch.msgid.link/9069ec1d59e4b2129fc23433349fd5580ad43921.172007507… Signed-off-by: Paolo Abeni <pabeni(a)redhat.com> Conflicts: net/sunrpc/xprtsock.c [Did not backport 280254b605ff ("SUNRPC: Clean up xs_tcp_setup_sock()").] Signed-off-by: Liu Jian <liujian56(a)huawei.com> --- net/sunrpc/xprtsock.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 31b1ab97140b..134a90b2216c 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -2337,6 +2337,13 @@ static void xs_tcp_setup_socket(struct work_struct *work) case -EALREADY: xprt_unlock_connect(xprt, transport); return; + case -EPERM: + /* Happens, for instance, if a BPF program is preventing + * the connect. Remap the error so upper layers can better + * deal with it. + */ + status = -ECONNREFUSED; + fallthrough; case -EINVAL: /* Happens, for instance, if the user specified a link * local IPv6 address without a scope-id. -- 2.34.1

2 1

[PATCH openEuler-22.03-LTS-SP1 v2] net, sunrpc: Remap EPERM in case of connection failure in xs_tcp_setup_socket
by Liu Jian 12 Aug '24

12 Aug '24

From: Daniel Borkmann <daniel(a)iogearbox.net> mainline inclusion from mainline-v6.10 commit 626dfed5fa3bfb41e0dffd796032b555b69f9cde category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAILGI CVE: CVE-2024-42246 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… ------------------------------------------------- When using a BPF program on kernel_connect(), the call can return -EPERM. This causes xs_tcp_setup_socket() to loop forever, filling up the syslog and causing the kernel to potentially freeze up. Neil suggested: This will propagate -EPERM up into other layers which might not be ready to handle it. It might be safer to map EPERM to an error we would be more likely to expect from the network system - such as ECONNREFUSED or ENETDOWN. ECONNREFUSED as error seems reasonable. For programs setting a different error can be out of reach (see handling in 4fbac77d2d09) in particular on kernels which do not have f10d05966196 ("bpf: Make BPF_PROG_RUN_ARRAY return -err instead of allow boolean"), thus given that it is better to simply remap for consistent behavior. UDP does handle EPERM in xs_udp_send_request(). Fixes: d74bad4e74ee ("bpf: Hooks for sys_connect") Fixes: 4fbac77d2d09 ("bpf: Hooks for sys_bind") Co-developed-by: Lex Siegel <usiegl00(a)gmail.com> Signed-off-by: Lex Siegel <usiegl00(a)gmail.com> Signed-off-by: Daniel Borkmann <daniel(a)iogearbox.net> Cc: Neil Brown <neilb(a)suse.de> Cc: Trond Myklebust <trondmy(a)kernel.org> Cc: Anna Schumaker <anna(a)kernel.org> Link: https://github.com/cilium/cilium/issues/33395 Link: https://lore.kernel.org/bpf/171374175513.12877.8993642908082014881@noble.ne… Link: https://patch.msgid.link/9069ec1d59e4b2129fc23433349fd5580ad43921.172007507… Signed-off-by: Paolo Abeni <pabeni(a)redhat.com> Conflicts: net/sunrpc/xprtsock.c [Did not backport 280254b605ff ("SUNRPC: Clean up xs_tcp_setup_sock()").] Signed-off-by: Liu Jian <liujian56(a)huawei.com> --- net/sunrpc/xprtsock.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 31b1ab97140b..134a90b2216c 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -2337,6 +2337,13 @@ static void xs_tcp_setup_socket(struct work_struct *work) case -EALREADY: xprt_unlock_connect(xprt, transport); return; + case -EPERM: + /* Happens, for instance, if a BPF program is preventing + * the connect. Remap the error so upper layers can better + * deal with it. + */ + status = -ECONNREFUSED; + fallthrough; case -EINVAL: /* Happens, for instance, if the user specified a link * local IPv6 address without a scope-id. -- 2.34.1

2 1

[openeuler:openEuler-1.0-LTS 7838/23480] drivers/gpu/drm/nouveau/nvkm/subdev/mmu/base.o: warning: objtool: nvkm_mmu_oneinit()+0x7b2: unreachable instruction
by kernel test robot 10 Aug '24

10 Aug '24

tree: https://gitee.com/openeuler/kernel.git openEuler-1.0-LTS head: 1ee05443d1dbf5cf95dcc762bb2baa828e2ccbcc commit: d4bdc26bcd632cee393b5171345d5fa6293fe42b [7838/23480] include/asm-generic/bug.h: fix "cut here" for WARN_ON for __WARN_TAINT architectures config: x86_64-randconfig-161-20240810 (https://download.01.org/0day-ci/archive/20240810/202408101202.aWgNk9Gj-lkp@…) compiler: clang version 18.1.5 (https://github.com/llvm/llvm-project 617a15a9eac96088ae5e9134248d8236e34b91b1) reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20240810/202408101202.aWgNk9Gj-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/202408101202.aWgNk9Gj-lkp@intel.com/ All warnings (new ones prefixed by >>): drivers/gpu/drm/nouveau/nvkm/subdev/mmu/base.c:65:1: warning: no previous prototype for function 'nvkm_mmu_ptp_get' [-Wmissing-prototypes] 65 | nvkm_mmu_ptp_get(struct nvkm_mmu *mmu, u32 size, bool zero) | ^ drivers/gpu/drm/nouveau/nvkm/subdev/mmu/base.c:64:1: note: declare 'static' if the function is not intended to be used outside of this translation unit 64 | struct nvkm_mmu_pt * | ^ | static 1 warning generated. >> drivers/gpu/drm/nouveau/nvkm/subdev/mmu/base.o: warning: objtool: nvkm_mmu_oneinit()+0x7b2: unreachable instruction -- 0-DAY CI Kernel Test Service https://github.com/intel/lkp-tests/wiki

1 0

[openeuler:openEuler-1.0-LTS] BUILD SUCCESS 1ee05443d1dbf5cf95dcc762bb2baa828e2ccbcc
by kernel test robot 10 Aug '24

10 Aug '24

tree/branch: https://gitee.com/openeuler/kernel.git openEuler-1.0-LTS branch HEAD: 1ee05443d1dbf5cf95dcc762bb2baa828e2ccbcc !10825 Revert "mm/writeback: fix possible divide-by-zero in wb_dirty_limits(), again" elapsed time: 725m configs tested: 31 configs skipped: 111 The following configs have been built successfully. More configs may be tested in the coming days. tested configs: arm64 allmodconfig gcc-14.1.0 arm64 allnoconfig gcc-14.1.0 arm64 randconfig-001-20240810 gcc-14.1.0 arm64 randconfig-002-20240810 gcc-14.1.0 arm64 randconfig-003-20240810 gcc-14.1.0 arm64 randconfig-004-20240810 gcc-14.1.0 x86_64 allnoconfig clang-18 x86_64 allyesconfig clang-18 x86_64 buildonly-randconfig-001-20240810 gcc-12 x86_64 buildonly-randconfig-002-20240810 clang-18 x86_64 buildonly-randconfig-003-20240810 clang-18 x86_64 buildonly-randconfig-004-20240810 clang-18 x86_64 buildonly-randconfig-005-20240810 clang-18 x86_64 buildonly-randconfig-006-20240810 clang-18 x86_64 defconfig gcc-11 x86_64 randconfig-001-20240810 clang-18 x86_64 randconfig-002-20240810 clang-18 x86_64 randconfig-003-20240810 gcc-12 x86_64 randconfig-004-20240810 clang-18 x86_64 randconfig-005-20240810 clang-18 x86_64 randconfig-006-20240810 gcc-12 x86_64 randconfig-011-20240810 clang-18 x86_64 randconfig-012-20240810 gcc-12 x86_64 randconfig-013-20240810 clang-18 x86_64 randconfig-014-20240810 clang-18 x86_64 randconfig-015-20240810 clang-18 x86_64 randconfig-016-20240810 clang-18 x86_64 randconfig-071-20240810 clang-18 x86_64 randconfig-072-20240810 gcc-12 x86_64 randconfig-073-20240810 clang-18 x86_64 rhel-8.3-rust clang-18 -- 0-DAY CI Kernel Test Service https://github.com/intel/lkp-tests/wiki

1 0

[openeuler:OLK-6.6] BUILD REGRESSION b863a7488a15e24e9caf81b204af36cf7ae75ebc
by kernel test robot 10 Aug '24

10 Aug '24

tree/branch: https://gitee.com/openeuler/kernel.git OLK-6.6 branch HEAD: b863a7488a15e24e9caf81b204af36cf7ae75ebc !10796 Revert "ARM: spectre-v2: turn off the mitigation via boot cmdline param" Error/Warning ids grouped by kconfigs: recent_errors |-- arm64-allmodconfig | |-- arch-arm64-kvm-arm.c:warning:variable-r-is-used-uninitialized-whenever-if-condition-is-false | |-- arch-arm64-kvm-tmi.c:warning:no-previous-prototype-for-function-tmi_tmm_inf_test | |-- arch-arm64-kvm-virtcca_cvm.c:warning:no-previous-prototype-for-function-kvm_cvm_create_ttt_levels | |-- arch-arm64-kvm-virtcca_cvm.c:warning:no-previous-prototype-for-function-kvm_cvm_get_num_brps | |-- arch-arm64-kvm-virtcca_cvm.c:warning:no-previous-prototype-for-function-kvm_cvm_get_num_wrps | |-- arch-arm64-kvm-virtcca_cvm.c:warning:no-previous-prototype-for-function-kvm_cvm_ipa_limit | |-- arch-arm64-kvm-virtcca_cvm.c:warning:no-previous-prototype-for-function-kvm_cvm_populate_par_region | |-- arch-arm64-kvm-virtcca_cvm.c:warning:no-previous-prototype-for-function-kvm_cvm_supports_pmu | `-- arch-arm64-kvm-virtcca_cvm.c:warning:no-previous-prototype-for-function-kvm_cvm_supports_sve |-- loongarch-allmodconfig | `-- arch-loongarch-kvm-..-..-..-virt-kvm-kvm_main.c:warning:kvmalloc_array-sizes-specified-with-sizeof-in-the-earlier-argument-and-not-in-the-later-argument |-- loongarch-randconfig-001-20240809 | `-- drivers-char-virtio_console.c:warning:u-directive-output-may-be-truncated-writing-between-and-bytes-into-a-region-of-size-between-and |-- x86_64-allyesconfig | `-- drivers-gpu-drm-amd-amdgpu-..-amdkfd-kfd_topology.c:warning:stack-frame-size-()-exceeds-limit-()-in-kfd_topology_add_device |-- x86_64-buildonly-randconfig-002-20240810 | `-- kernel-sched-isolation.c:error:use-of-undeclared-identifier-setup_max_cpus |-- x86_64-buildonly-randconfig-003-20240810 | `-- kernel-sched-isolation.c:error:use-of-undeclared-identifier-setup_max_cpus |-- x86_64-buildonly-randconfig-005-20240810 | `-- kernel-sched-isolation.c:error:use-of-undeclared-identifier-setup_max_cpus `-- x86_64-randconfig-004-20240810 `-- drivers-net-ethernet-yunsilicon-xsc-net-main.c:error:no-member-named-physfn-in-struct-pci_dev elapsed time: 723m configs tested: 35 configs skipped: 107 tested configs: arm64 allmodconfig clang-20 arm64 allnoconfig gcc-14.1.0 arm64 randconfig-001-20240809 clang-20 arm64 randconfig-002-20240809 clang-15 arm64 randconfig-003-20240809 clang-15 arm64 randconfig-004-20240809 clang-20 loongarch allmodconfig gcc-14.1.0 loongarch allnoconfig gcc-14.1.0 loongarch randconfig-001-20240809 gcc-14.1.0 loongarch randconfig-002-20240809 gcc-14.1.0 x86_64 allnoconfig clang-18 x86_64 allyesconfig clang-18 x86_64 buildonly-randconfig-001-20240810 gcc-12 x86_64 buildonly-randconfig-002-20240810 clang-18 x86_64 buildonly-randconfig-003-20240810 clang-18 x86_64 buildonly-randconfig-004-20240810 clang-18 x86_64 buildonly-randconfig-005-20240810 clang-18 x86_64 buildonly-randconfig-006-20240810 clang-18 x86_64 defconfig gcc-11 x86_64 randconfig-001-20240810 clang-18 x86_64 randconfig-002-20240810 clang-18 x86_64 randconfig-003-20240810 gcc-12 x86_64 randconfig-004-20240810 clang-18 x86_64 randconfig-005-20240810 clang-18 x86_64 randconfig-006-20240810 gcc-12 x86_64 randconfig-011-20240810 clang-18 x86_64 randconfig-012-20240810 gcc-12 x86_64 randconfig-013-20240810 clang-18 x86_64 randconfig-014-20240810 clang-18 x86_64 randconfig-015-20240810 clang-18 x86_64 randconfig-016-20240810 clang-18 x86_64 randconfig-071-20240810 clang-18 x86_64 randconfig-072-20240810 gcc-12 x86_64 randconfig-073-20240810 clang-18 x86_64 rhel-8.3-rust clang-18 -- 0-DAY CI Kernel Test Service https://github.com/intel/lkp-tests/wiki

1 0

[PATCH openEuler-1.0-LTS] Revert "NFS: Don't interrupt file writeout due to fatal errors"
by Li Lingfeng 09 Aug '24

09 Aug '24

hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IAJ2ZJ -------------------------------- This reverts commit 812ffba3b83c86bba38fd087fa41fe2f08f7acb6. Commit 812ffba3b83c ("NFS: Don't interrupt file writeout due to fatal errors") tries to keep writing back when hit fatal errors. However, since page->mapping will be set as NULL in nfs_write_error_remove_page() and it will be used in nfs_create_request(), null-ptr-deref will be triggered if we don't stop it immediately. Fixes: 812ffba3b83c ("NFS: Don't interrupt file writeout due to fatal errors") Signed-off-by: Li Lingfeng <lilingfeng3(a)huawei.com> --- fs/nfs/write.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/nfs/write.c b/fs/nfs/write.c index e4b1ce488637..706ed79e23e2 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -662,7 +662,7 @@ static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio, return ret; out_launder: nfs_write_error_remove_page(req); - return 0; + return ret; } static int nfs_do_writepage(struct page *page, struct writeback_control *wbc, -- 2.31.1

2 1

[PATCH openEuler-22.03-LTS-SP1 v3] ext4: flexibly control whether to enable dioread_nolock by default
by Yang Erkun 09 Aug '24

09 Aug '24

hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IAAPPE -------------------------------- After commit 244adf6426ee ("ext4: make dioread_nolock the default"), writeback for ext4 mounted with dioread_nolock will first start journal, then get a unwritten extent, change i_size and mark inode dirty. Besides, we won't call ext4_jbd2_inode_add_write since the extent is unwritten, so when jbd2 try do commit journal, we will not wait stable data. And combine with a poweroff before data writepage success, we will find a file with size has already been update but the content still keep zero since the extent is unwritten. This is really intolerable for some production. So we need give a choice to decided does we really need default enable dioread_nolock. Back to why we default enable dioread_nolock, the upper commit give some description, the most import problem is that dioread parallel with fault write(and writepage for fault write has alloc the block) will read some stale data. But the case dioread parallel with fault write is really rarely used, so it seems little impact now. We now give a more flexible way to control how to default enable dioread_nolock or not: - set CONFIG_EXT4_DIOREAD_NOLOCK_PARAM to N, still default enable dioread_nlock - set CONFIG_EXT4_DIOREAD_NOLOCK_PARAM to Y, default disable dioread_nolock, also we give a module param default_dioread_nolock to control it, it you want default enable dioread_nlock, set default_dioread_nolock to 1. Fixes: 244adf6426ee ("ext4: make dioread_nolock the default") Signed-off-by: Yang Erkun <yangerkun(a)huawei.com> --- arch/arm64/configs/openeuler_defconfig | 1 + arch/x86/configs/openeuler_defconfig | 1 + fs/ext4/Kconfig | 8 ++++++++ fs/ext4/super.c | 19 +++++++++++++++++++ 4 files changed, 29 insertions(+) diff --git a/arch/arm64/configs/openeuler_defconfig b/arch/arm64/configs/openeuler_defconfig index 86f6cfaafa85..2d6b37def3fb 100644 --- a/arch/arm64/configs/openeuler_defconfig +++ b/arch/arm64/configs/openeuler_defconfig @@ -6207,6 +6207,7 @@ CONFIG_EXT4_USE_FOR_EXT2=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y # CONFIG_EXT4_DEBUG is not set +# CONFIG_EXT4_DIOREAD_NOLOCK_PARAM is not set CONFIG_JBD2=m # CONFIG_JBD2_DEBUG is not set CONFIG_FS_MBCACHE=m diff --git a/arch/x86/configs/openeuler_defconfig b/arch/x86/configs/openeuler_defconfig index 686e5cdfc801..27b1f9def28d 100644 --- a/arch/x86/configs/openeuler_defconfig +++ b/arch/x86/configs/openeuler_defconfig @@ -7292,6 +7292,7 @@ CONFIG_EXT4_USE_FOR_EXT2=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y # CONFIG_EXT4_DEBUG is not set +# CONFIG_EXT4_DIOREAD_NOLOCK_PARAM is not set CONFIG_JBD2=m # CONFIG_JBD2_DEBUG is not set CONFIG_FS_MBCACHE=m diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig index 86699c8cab28..72913ea5343f 100644 --- a/fs/ext4/Kconfig +++ b/fs/ext4/Kconfig @@ -117,3 +117,11 @@ config EXT4_KUNIT_TESTS to the KUnit documentation in Documentation/dev-tools/kunit/. If unsure, say N. + +config EXT4_DIOREAD_NOLOCK_PARAM + bool "Ext4 default_dioread_nolock module param support" + depends on EXT4_FS + default n + help + Support to enable default_dioread_nolock module param, be attention to + that we default disable dioread_nolock with this config set to Y. diff --git a/fs/ext4/super.c b/fs/ext4/super.c index ac032f517a60..5dbe420487e4 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -62,6 +62,20 @@ #define CREATE_TRACE_POINTS #include <trace/events/ext4.h> +#ifdef CONFIG_EXT4_DIOREAD_NOLOCK_PARAM +/* + * After 244adf6426ee ("ext4: make dioread_nolock the default"), we will enable + * dioread_nolock by default, but this options may lead data lose combine with + * poweroff(Since we may first update i_size, and then unwritten extent convert + * to written extent). For this case, we give a param to help control does we + * really default enable dioread_nolock and we default disable dioread_nolock, + * enable it with ext4.default_dioread_nolock=1 if you want. + */ +int default_dioread_nolock; +module_param_named(default_dioread_nolock, default_dioread_nolock, int, 0644); +MODULE_PARM_DESC(default_dioread_nolock, "Default enable dioread_nolock"); +#endif + static struct ext4_lazy_init *ext4_li_info; static struct mutex ext4_li_mtx; static struct ratelimit_state ext4_mount_msg_ratelimit; @@ -4272,8 +4286,13 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) blocksize = EXT4_MIN_BLOCK_SIZE << le32_to_cpu(es->s_log_block_size); +#ifdef CONFIG_EXT4_DIOREAD_NOLOCK_PARAM + if (blocksize == PAGE_SIZE && default_dioread_nolock) + set_opt(sb, DIOREAD_NOLOCK); +#else if (blocksize == PAGE_SIZE) set_opt(sb, DIOREAD_NOLOCK); +#endif if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV) { sbi->s_inode_size = EXT4_GOOD_OLD_INODE_SIZE; -- 2.39.2

2 1