- Kernel - mailweb.openeuler.org

[PATCH kernel-4.19 1/2] sched/topology: Warn when NUMA diameter > 2
by Yang Yingliang 30 Sep '21

30 Sep '21

From: Valentin Schneider <valentin.schneider(a)arm.com> mainline inclusion from mainline-v5.11-rc1 commit b5b217346de85ed1b03fdecd5c5076b34fbb2f0b category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4CAA9 CVE: NA ---------------------------------------------------------- NUMA topologies where the shortest path between some two nodes requires three or more hops (i.e. diameter > 2) end up being misrepresented in the scheduler topology structures. This is currently detected when booting a kernel with CONFIG_SCHED_DEBUG=y + sched_debug on the cmdline, although this will only yield a warning about sched_group spans not matching sched_domain spans: ERROR: groups don't span domain->span Add an explicit warning for that case, triggered regardless of CONFIG_SCHED_DEBUG, and decorate it with an appropriate comment. The topology described in the comment can be booted up on QEMU by appending the following to your usual QEMU incantation: -smp cores=4 \ -numa node,cpus=0,nodeid=0 -numa node,cpus=1,nodeid=1, \ -numa node,cpus=2,nodeid=2, -numa node,cpus=3,nodeid=3, \ -numa dist,src=0,dst=1,val=20, -numa dist,src=0,dst=2,val=30, \ -numa dist,src=0,dst=3,val=40, -numa dist,src=1,dst=2,val=20, \ -numa dist,src=1,dst=3,val=30, -numa dist,src=2,dst=3,val=20 A somewhat more realistic topology (6-node mesh) with the same affliction can be conjured with: -smp cores=6 \ -numa node,cpus=0,nodeid=0 -numa node,cpus=1,nodeid=1, \ -numa node,cpus=2,nodeid=2, -numa node,cpus=3,nodeid=3, \ -numa node,cpus=4,nodeid=4, -numa node,cpus=5,nodeid=5, \ -numa dist,src=0,dst=1,val=20, -numa dist,src=0,dst=2,val=30, \ -numa dist,src=0,dst=3,val=40, -numa dist,src=0,dst=4,val=30, \ -numa dist,src=0,dst=5,val=20, \ -numa dist,src=1,dst=2,val=20, -numa dist,src=1,dst=3,val=30, \ -numa dist,src=1,dst=4,val=20, -numa dist,src=1,dst=5,val=30, \ -numa dist,src=2,dst=3,val=20, -numa dist,src=2,dst=4,val=30, \ -numa dist,src=2,dst=5,val=40, \ -numa dist,src=3,dst=4,val=20, -numa dist,src=3,dst=5,val=30, \ -numa dist,src=4,dst=5,val=20 Signed-off-by: Valentin Schneider <valentin.schneider(a)arm.com> Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Acked-by: Mel Gorman <mgorman(a)techsingularity.net> Link: https://lore.kernel.org/lkml/jhjtux5edo2.mognet@arm.com Signed-off-by: Cheng Jian <cj.chengjian(a)huawei.com> Reviewed-by: Xie XiuQi <xiexiuqi(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- kernel/sched/topology.c | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 0002b269ed3da..cd2005832d59c 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -461,6 +461,7 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu) { struct rq *rq = cpu_rq(cpu); struct sched_domain *tmp; + int numa_distance = 0; /* Remove the sched domains which do not contribute to scheduling. */ for (tmp = sd; tmp; ) { @@ -492,6 +493,38 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu) sd->child = NULL; } + for (tmp = sd; tmp; tmp = tmp->parent) + numa_distance += !!(tmp->flags & SD_NUMA); + + /* + * FIXME: Diameter >=3 is misrepresented. + * + * Smallest diameter=3 topology is: + * + * node 0 1 2 3 + * 0: 10 20 30 40 + * 1: 20 10 20 30 + * 2: 30 20 10 20 + * 3: 40 30 20 10 + * + * 0 --- 1 --- 2 --- 3 + * + * NUMA-3 0-3 N/A N/A 0-3 + * groups: {0-2},{1-3} {1-3},{0-2} + * + * NUMA-2 0-2 0-3 0-3 1-3 + * groups: {0-1},{1-3} {0-2},{2-3} {1-3},{0-1} {2-3},{0-2} + * + * NUMA-1 0-1 0-2 1-3 2-3 + * groups: {0},{1} {1},{2},{0} {2},{3},{1} {3},{2} + * + * NUMA-0 0 1 2 3 + * + * The NUMA-2 groups for nodes 0 and 3 are obviously buggered, as the + * group span isn't a subset of the domain span. + */ + WARN_ONCE(numa_distance > 2, "Shortest NUMA path spans too many nodes\n"); + sched_domain_debug(sd, cpu); rq_attach_root(rq, rd); -- 2.25.1

1 1

[PATCH kernel-4.19] ipc: replace costly bailout check in sysvipc_find_ipc()
by Yang Yingliang 30 Sep '21

30 Sep '21

From: Rafael Aquini <aquini(a)redhat.com> mainline inclusion from mainline-v5.15 commit 20401d1058f3f841f35a594ac2fc1293710e55b9 category: bugfix bugzilla: NA CVE: CVE-2021-3669 -------------------------------- sysvipc_find_ipc() was left with a costly way to check if the offset position fed to it is bigger than the total number of IPC IDs in use. So much so that the time it takes to iterate over /proc/sysvipc/* files grows exponentially for a custom benchmark that creates "N" SYSV shm segments and then times the read of /proc/sysvipc/shm (milliseconds): 12 msecs to read 1024 segs from /proc/sysvipc/shm 18 msecs to read 2048 segs from /proc/sysvipc/shm 65 msecs to read 4096 segs from /proc/sysvipc/shm 325 msecs to read 8192 segs from /proc/sysvipc/shm 1303 msecs to read 16384 segs from /proc/sysvipc/shm 5182 msecs to read 32768 segs from /proc/sysvipc/shm The root problem lies with the loop that computes the total amount of ids in use to check if the "pos" feeded to sysvipc_find_ipc() grew bigger than "ids->in_use". That is a quite inneficient way to get to the maximum index in the id lookup table, specially when that value is already provided by struct ipc_ids.max_idx. This patch follows up on the optimization introduced via commit 15df03c879836 ("sysvipc: make get_maxid O(1) again") and gets rid of the aforementioned costly loop replacing it by a simpler checkpoint based on ipc_get_maxidx() returned value, which allows for a smooth linear increase in time complexity for the same custom benchmark: 2 msecs to read 1024 segs from /proc/sysvipc/shm 2 msecs to read 2048 segs from /proc/sysvipc/shm 4 msecs to read 4096 segs from /proc/sysvipc/shm 9 msecs to read 8192 segs from /proc/sysvipc/shm 19 msecs to read 16384 segs from /proc/sysvipc/shm 39 msecs to read 32768 segs from /proc/sysvipc/shm Link: https://lkml.kernel.org/r/20210809203554.1562989-1-aquini@redhat.com Signed-off-by: Rafael Aquini <aquini(a)redhat.com> Acked-by: Davidlohr Bueso <dbueso(a)suse.de> Acked-by: Manfred Spraul <manfred(a)colorfullife.com> Cc: Waiman Long <llong(a)redhat.com> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Conflicts: ipc/util.c Signed-off-by: zhiwentao <zhiwentao(a)huawei.com> Reviewed-by: Wang Hui <john.wanghui(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- ipc/util.c | 17 +++++------------ 1 file changed, 5 insertions(+), 12 deletions(-) diff --git a/ipc/util.c b/ipc/util.c index af1b572effb14..53204b1d2e207 100644 --- a/ipc/util.c +++ b/ipc/util.c @@ -725,21 +725,14 @@ struct pid_namespace *ipc_seq_pid_ns(struct seq_file *s) static struct kern_ipc_perm *sysvipc_find_ipc(struct ipc_ids *ids, loff_t pos, loff_t *new_pos) { - struct kern_ipc_perm *ipc; - int total, id; - - total = 0; - for (id = 0; id < pos && total < ids->in_use; id++) { - ipc = idr_find(&ids->ipcs_idr, id); - if (ipc != NULL) - total++; - } - ipc = NULL; - if (total >= ids->in_use) + struct kern_ipc_perm *ipc = NULL; + int max_idx = ipc_get_maxidx(ids); + + if (max_idx == -1 || pos > max_idx) goto out; - for (; pos < IPCMNI; pos++) { + for (; pos <= max_idx; pos++) { ipc = idr_find(&ids->ipcs_idr, pos); if (ipc != NULL) { rcu_read_lock(); -- 2.25.1

1 0

[PATCH kernel-4.19 1/4] net: hns3: fix memory override when bd_num is bigger than port info size
by Yang Yingliang 30 Sep '21

30 Sep '21

From: Yonglong Liu <liuyonglong(a)huawei.com> driver inclusion category: bugfix bugzilla: NA CVE: NA ---------------------------- The bd_num is from firmware, it may be bigger than the size of struct hclge_port_info, and may cause memory override problem. Signed-off-by: Yonglong Liu <liuyonglong(a)huawei.com> Reviewed-by: Jian Shen <shenjian15(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- .../net/ethernet/hisilicon/hns3/hns3_cae/hns3_cae_port.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_cae/hns3_cae_port.c b/drivers/net/ethernet/hisilicon/hns3/hns3_cae/hns3_cae_port.c index 5404048ad60d1..ebbc25cc86940 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_cae/hns3_cae_port.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_cae/hns3_cae_port.c @@ -88,9 +88,9 @@ int hns3_get_port_info(const struct hns3_nic_priv *net_priv, desc_data = (__le32 *)(&desc.data[0]); bd_num = le32_to_cpu(*desc_data); - if (bd_num > hdev->hw.cmq.csq.desc_num) { - dev_err(&hdev->pdev->dev, "get invalid BD num %u(max %u)\n", - bd_num, hdev->hw.cmq.csq.desc_num); + if (bd_num * sizeof(struct hclge_desc) > + sizeof(struct hclge_port_info)) { + dev_err(&hdev->pdev->dev, "get invalid BD num %u\n", bd_num); return -EINVAL; } -- 2.25.1

1 3

[PATCH kernel-4.19] scsi: hisi_sas: Optimize the code flow of setting sense data when ssp I/O abnormally completed
by Yang Yingliang 30 Sep '21

30 Sep '21

From: yangxingui <yangxingui(a)huawei.com> driver inclusion category: bugfix bugzilla: NA CVE: NA --------------------------- In the data underflow scenario, if correct sense data and response frame have been written to the host memory and the CQ RSPNS_GOOD bit is 0, then driver sends the sense data to the upper layer. Signed-off-by: yangxingui <yangxingui(a)huawei.com> Reviewed-by: Xiang Chen <chenxiang66(a)hisilicon.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/scsi/hisi_sas/hisi_sas.h | 8 +++++-- drivers/scsi/hisi_sas/hisi_sas_main.c | 17 ------------- drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 33 ++++++++++++++++++++++---- 3 files changed, 34 insertions(+), 24 deletions(-) diff --git a/drivers/scsi/hisi_sas/hisi_sas.h b/drivers/scsi/hisi_sas/hisi_sas.h index 193fc960d87fd..742ffcaeaa95c 100644 --- a/drivers/scsi/hisi_sas/hisi_sas.h +++ b/drivers/scsi/hisi_sas/hisi_sas.h @@ -102,6 +102,12 @@ enum hisi_sas_dev_type { HISI_SAS_DEV_TYPE_SATA, }; +enum datapres_field { + NO_DATA = 0, + RESPONSE_DATA = 1, + SENSE_DATA = 2, +}; + struct hisi_sas_hw_error { u32 irq_msk; u32 msk; @@ -571,8 +577,6 @@ extern void hisi_sas_free(struct hisi_hba *hisi_hba); extern u8 hisi_sas_get_ata_protocol(struct host_to_dev_fis *fis, int direction); extern struct hisi_sas_port *to_hisi_sas_port(struct asd_sas_port *sas_port); -extern void hisi_sas_set_sense_data(struct sas_task *task, - struct hisi_sas_slot *slot); extern void hisi_sas_sata_done(struct sas_task *task, struct hisi_sas_slot *slot); extern int hisi_sas_get_fw_info(struct hisi_hba *hisi_hba); diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c index ea08d53c11495..67befcc033126 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_main.c +++ b/drivers/scsi/hisi_sas/hisi_sas_main.c @@ -105,23 +105,6 @@ u8 hisi_sas_get_ata_protocol(struct host_to_dev_fis *fis, int direction) } EXPORT_SYMBOL_GPL(hisi_sas_get_ata_protocol); -void hisi_sas_set_sense_data(struct sas_task *task, - struct hisi_sas_slot *slot) -{ - struct ssp_response_iu *iu = - hisi_sas_status_buf_addr_mem(slot) + - sizeof(struct hisi_sas_err_record); - if (iu->datapres == 2) { - struct task_status_struct *ts = &task->task_status; - - ts->buf_valid_size = - min_t(int, SAS_STATUS_BUF_SIZE, - be32_to_cpu(iu->sense_data_len)); - memcpy(ts->buf, iu->sense_data, ts->buf_valid_size); - } -} -EXPORT_SYMBOL_GPL(hisi_sas_set_sense_data); - void hisi_sas_sata_done(struct sas_task *task, struct hisi_sas_slot *slot) { diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c index 06b4f2db62f7b..9ce1177a8e455 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c @@ -395,6 +395,8 @@ #define CMPLT_HDR_ERROR_PHASE_MSK (0xff << CMPLT_HDR_ERROR_PHASE_OFF) #define CMPLT_HDR_RSPNS_XFRD_OFF 10 #define CMPLT_HDR_RSPNS_XFRD_MSK (0x1 << CMPLT_HDR_RSPNS_XFRD_OFF) +#define CMPLT_HDR_RSPNS_GOOD_OFF 11 +#define CMPLT_HDR_RSPNS_GOOD_MSK (0x1 << CMPLT_HDR_RSPNS_GOOD_OFF) #define CMPLT_HDR_ERX_OFF 12 #define CMPLT_HDR_ERX_MSK (0x1 << CMPLT_HDR_ERX_OFF) #define CMPLT_HDR_ABORT_STAT_OFF 13 @@ -2208,6 +2210,24 @@ static irqreturn_t fatal_axi_int_v3_hw(int irq_no, void *p) return IRQ_HANDLED; } +static void hisi_sas_set_sense_data(struct sas_task *task, + struct hisi_sas_slot *slot) +{ + struct ssp_response_iu *iu = + hisi_sas_status_buf_addr_mem(slot) + + sizeof(struct hisi_sas_err_record); + if ((iu->status == SAM_STAT_CHECK_CONDITION) && + (iu->datapres == SENSE_DATA)) { + struct task_status_struct *ts = &task->task_status; + + ts->buf_valid_size = + min_t(int, SAS_STATUS_BUF_SIZE, + be32_to_cpu(iu->sense_data_len)); + memcpy(ts->buf, iu->sense_data, ts->buf_valid_size); + ts->stat = SAM_STAT_CHECK_CONDITION; + } +} + static void slot_err_v3_hw(struct hisi_hba *hisi_hba, struct sas_task *task, struct hisi_sas_slot *slot) @@ -2224,17 +2244,20 @@ slot_err_v3_hw(struct hisi_hba *hisi_hba, struct sas_task *task, switch (task->task_proto) { case SAS_PROTOCOL_SSP: - if (complete_hdr->dw3 & CMPLT_HDR_IO_IN_TARGET_MSK) { - ts->stat = SAS_QUEUE_FULL; - slot->abort = 1; - } else if (dma_rx_err_type & RX_DATA_LEN_UNDERFLOW_MSK) { + if (dma_rx_err_type & RX_DATA_LEN_UNDERFLOW_MSK) { ts->residual = trans_tx_fail_type; ts->stat = SAS_DATA_UNDERRUN; + if ((!(complete_hdr->dw0 & CMPLT_HDR_RSPNS_GOOD_MSK)) && + (complete_hdr->dw0 & CMPLT_HDR_RSPNS_XFRD_MSK)) { + hisi_sas_set_sense_data(task, slot); + } + } else if (complete_hdr->dw3 & CMPLT_HDR_IO_IN_TARGET_MSK) { + ts->stat = SAS_QUEUE_FULL; + slot->abort = 1; } else { ts->stat = SAS_OPEN_REJECT; ts->open_rej_reason = SAS_OREJ_RSVD_RETRY; } - hisi_sas_set_sense_data(task, slot); break; case SAS_PROTOCOL_SATA: case SAS_PROTOCOL_STP: -- 2.25.1

1 0

How can I get the kernel config values in EulerOS 2.9?
by Wangpeng (Forest, ISCP SRE) 29 Sep '21

29 Sep '21

Hi Community: How can I get the kernel config values in EulerOS? For example, in other release, I can do that by "zcat /proc/config.gz" B.R.

2 1

openEuler Summit 2021 诚挚的邀请您提交演讲议题、成为共建单位、贡献展示方案
by Marketing openEuler 29 Sep '21

29 Sep '21

openEuler Summit 是由欧拉开源社区举办的开发者峰会。全新升级后的首场峰会将于 11 月10日在北京举行。 openEuler 从服务器操作系统，升级为数字基础设施的操作系统，支持 IT、CT、OT 等数字基础设施全场景，覆盖服务器、云、边、嵌入式等各种形态的需求。伴随 openEuler 21.09 的发布，openEuler 已经包含了服务器、云原生、边缘计算和嵌入式的四大应用场景。 openEuler 通过开源开放，不断探索科技创新的边界。开发者、用户、社区贡献者、软件爱好者在 openEuler Summit 汇聚，共同解读 openEuler 的最新版，探讨未来的技术路线，让技术、生态、商业在这里产生奇妙的化学反应。 *本次峰会旨在推动 openEuler 在多样性计算、云计算、边缘计算、嵌入式等技术方向的持续探索和创新。* 开源是一种态度、分享是一种精神。Call for Speaker、Call for Sponsor、Call for Demo 现已全面开放报名。大会报名通道同步开启。 *我们诚挚的邀请您提交演讲议题、发表联合演讲、成为共建单位、贡献展示方案、参与社区建设。* - *大会官网：*https://www.openeuler.org/zh/interaction/summit-list/summit2021/ - *Call for Speaker：*https://shimowendang.com/forms/X6X9jj9KPcdQwVr8/fill - *Call for Sponsor：*https://shimowendang.com/forms/k76zTLKvumYwRdsP/fill - *Call for Demo：*https://shimowendang.com/forms/LjHs8JlsLSsW92kl/fill

1 0

[PATCH] eulerfs: add the /proc/idle file.
by Hongyu Li 29 Sep '21

29 Sep '21

From: Hongyu Li <“543306408(a)qq.xn--com-9o0a> openEuler inclusion category: bugfix bugzilla: https://gitee.com/openeuler-competition/summer-2021/issues/I3EBT6 CVE: NA ---------------------------------------------------------------------- The /proc/idle can give higher precision in accounting the CPU idle time compared with the traditional /proc/stat ways. Signed-off-by: Hongyu Li <“543306408(a)qq.xn--com-9o0a> --- fs/proc/Kconfig | 7 ++++ fs/proc/Makefile | 1 + fs/proc/proc_idle.c | 82 ++++++++++++++++++++++++++++++++++++++++++ kernel/sched/cputime.c | 16 +++++++++ kernel/sched/idle.c | 21 +++++++++++ 5 files changed, 127 insertions(+) create mode 100644 fs/proc/proc_idle.c diff --git a/fs/proc/Kconfig b/fs/proc/Kconfig index c930001056f9..46620afe9cac 100644 --- a/fs/proc/Kconfig +++ b/fs/proc/Kconfig @@ -107,3 +107,10 @@ config PROC_PID_ARCH_STATUS config PROC_CPU_RESCTRL def_bool n depends on PROC_FS + +config PROC_IDLE + bool "include /proc/idle file" + depends on PROC_FS + default y + help + Provide the CPU idle time in the /proc/idle file. diff --git a/fs/proc/Makefile b/fs/proc/Makefile index 8704d41dd67c..69dd2da3a080 100644 --- a/fs/proc/Makefile +++ b/fs/proc/Makefile @@ -34,5 +34,6 @@ proc-$(CONFIG_PROC_VMCORE) += vmcore.o proc-$(CONFIG_PRINTK) += kmsg.o proc-$(CONFIG_PROC_PAGE_MONITOR) += page.o proc-$(CONFIG_BOOT_CONFIG) += bootconfig.o +proc-$(CONFIG_PROC_IDLE) += proc_idle.o obj-$(CONFIG_ETMEM_SCAN) += etmem_scan.o obj-$(CONFIG_ETMEM_SWAP) += etmem_swap.o diff --git a/fs/proc/proc_idle.c b/fs/proc/proc_idle.c new file mode 100644 index 000000000000..bbb52e247448 --- /dev/null +++ b/fs/proc/proc_idle.c @@ -0,0 +1,82 @@ +#include <linux/cpumask.h> +#include <linux/device.h> +#include <linux/fs.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/kernel.h> +#include <linux/kernel_stat.h> +#include <linux/module.h> +#include <linux/proc_fs.h> +#include <linux/sched.h> +#include <linux/sched/stat.h> +#include <linux/seq_file.h> +#include <linux/slab.h> +#include <linux/time.h> +#include <linux/irqnr.h> +#include <linux/sched/cputime.h> +#include <linux/tick.h> + +#ifdef CONFIG_PROC_IDLE + +#define PROC_NAME "idle" + +extern u64 cpu_rq_get(int cpu); + +static u64 get_idle_sum_exec_runtime(int cpu) +{ + u64 idle = cpu_rq_get(cpu); + + return idle; +} + +static int show_idle(struct seq_file *p, void *v) +{ + int i; + u64 idle; + + idle = 0; + + for_each_possible_cpu(i) { + + idle += get_idle_sum_exec_runtime(i); + + } + + seq_put_decimal_ull(p, "cpu ", nsec_to_clock_t(idle)); + seq_putc(p, '\n'); + + for_each_online_cpu(i) { + + idle = get_idle_sum_exec_runtime(i); + + seq_printf(p, "cpu%d", i); + seq_put_decimal_ull(p, " ", nsec_to_clock_t(idle)); + seq_putc(p, '\n'); + } + + return 0; +} + +static int idle_open(struct inode *inode, struct file *file) +{ + unsigned int size = 1024 + 128 * num_online_cpus(); + + return single_open_size(file, show_idle, NULL, size); +} + +static struct proc_ops idle_procs_ops = { + .proc_open = idle_open, + .proc_read_iter = seq_read_iter, + .proc_lseek = seq_lseek, + .proc_release = single_release, +}; + +static int __init kernel_module_init(void) +{ + proc_create(PROC_NAME, 0, NULL, &idle_procs_ops); + return 0; +} + +fs_initcall(kernel_module_init); + +#endif /*CONFIG_PROC_IDLE*/ diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 5a55d2300452..bb280852bb06 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -1078,3 +1078,19 @@ void kcpustat_cpu_fetch(struct kernel_cpustat *dst, int cpu) EXPORT_SYMBOL_GPL(kcpustat_cpu_fetch); #endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */ + + +#ifdef CONFIG_PROC_IDLE + + +u64 cpu_rq_get(int cpu) +{ + struct rq *rq = cpu_rq(cpu); + struct sched_entity *idle_se = &rq->idle->se; + u64 idle = idle_se->sum_exec_runtime; + + return idle; +} +EXPORT_SYMBOL_GPL(cpu_rq_get); + +#endif /* CONFIG_PROC_IDLE */ diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 36b545f17206..e3fb940a61e8 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -424,6 +424,20 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int fl static void put_prev_task_idle(struct rq *rq, struct task_struct *prev) { +#ifdef CONFIG_PROC_IDLE + struct sched_entity *idle_se = &rq->idle->se; + u64 now = sched_clock(); + u64 delta_exec; + + delta_exec = now - idle_se->exec_start; + if (unlikely((s64)delta_exec <= 0)) + return; + + schedstat_set(idle_se->statistics.exec_max, + max(delta_exec, idle_se->statistics.exec_max)); + + idle_se->sum_exec_runtime += delta_exec; +#endif } static void set_next_task_idle(struct rq *rq, struct task_struct *next, bool first) @@ -436,6 +450,13 @@ struct task_struct *pick_next_task_idle(struct rq *rq) { struct task_struct *next = rq->idle; +#ifdef CONFIG_PROC_IDLE + struct sched_entity *idle_se = &rq->idle->se; + u64 now = sched_clock(); + + idle_se->exec_start = now; +#endif + set_next_task_idle(rq, next, true); return next; -- 2.17.1

2 1

[PATCH kernel-4.19] Bluetooth: fix use-after-free error in lock_sock_nested()
by Yang Yingliang 29 Sep '21

29 Sep '21

From: Wang ShaoBo <bobo.shaobowang(a)huawei.com> mainline inclusion from mainline-v5.16 commit 1bff51ea59a9afb67d2dd78518ab0582a54a472c category: bugfix bugzilla: NA CVE: CVE-2021-3752 --------------------------- use-after-free error in lock_sock_nested is reported: [ 179.140137][ T3731] ===================================================== [ 179.142675][ T3731] BUG: KMSAN: use-after-free in lock_sock_nested+0x280/0x2c0 [ 179.145494][ T3731] CPU: 4 PID: 3731 Comm: kworker/4:2 Not tainted 5.12.0-rc6+ #54 [ 179.148432][ T3731] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1ubuntu1.1 04/01/2014 [ 179.151806][ T3731] Workqueue: events l2cap_chan_timeout [ 179.152730][ T3731] Call Trace: [ 179.153301][ T3731] dump_stack+0x24c/0x2e0 [ 179.154063][ T3731] kmsan_report+0xfb/0x1e0 [ 179.154855][ T3731] __msan_warning+0x5c/0xa0 [ 179.155579][ T3731] lock_sock_nested+0x280/0x2c0 [ 179.156436][ T3731] ? kmsan_get_metadata+0x116/0x180 [ 179.157257][ T3731] l2cap_sock_teardown_cb+0xb8/0x890 [ 179.158154][ T3731] ? __msan_metadata_ptr_for_load_8+0x10/0x20 [ 179.159141][ T3731] ? kmsan_get_metadata+0x116/0x180 [ 179.159994][ T3731] ? kmsan_get_shadow_origin_ptr+0x84/0xb0 [ 179.160959][ T3731] ? l2cap_sock_recv_cb+0x420/0x420 [ 179.161834][ T3731] l2cap_chan_del+0x3e1/0x1d50 [ 179.162608][ T3731] ? kmsan_get_metadata+0x116/0x180 [ 179.163435][ T3731] ? kmsan_get_shadow_origin_ptr+0x84/0xb0 [ 179.164406][ T3731] l2cap_chan_close+0xeea/0x1050 [ 179.165189][ T3731] ? kmsan_internal_unpoison_shadow+0x42/0x70 [ 179.166180][ T3731] l2cap_chan_timeout+0x1da/0x590 [ 179.167066][ T3731] ? __msan_metadata_ptr_for_load_8+0x10/0x20 [ 179.168023][ T3731] ? l2cap_chan_create+0x560/0x560 [ 179.168818][ T3731] process_one_work+0x121d/0x1ff0 [ 179.169598][ T3731] worker_thread+0x121b/0x2370 [ 179.170346][ T3731] kthread+0x4ef/0x610 [ 179.171010][ T3731] ? process_one_work+0x1ff0/0x1ff0 [ 179.171828][ T3731] ? kthread_blkcg+0x110/0x110 [ 179.172587][ T3731] ret_from_fork+0x1f/0x30 [ 179.173348][ T3731] [ 179.173752][ T3731] Uninit was created at: [ 179.174409][ T3731] kmsan_internal_poison_shadow+0x5c/0xf0 [ 179.175373][ T3731] kmsan_slab_free+0x76/0xc0 [ 179.176060][ T3731] kfree+0x3a5/0x1180 [ 179.176664][ T3731] __sk_destruct+0x8af/0xb80 [ 179.177375][ T3731] __sk_free+0x812/0x8c0 [ 179.178032][ T3731] sk_free+0x97/0x130 [ 179.178686][ T3731] l2cap_sock_release+0x3d5/0x4d0 [ 179.179457][ T3731] sock_close+0x150/0x450 [ 179.180117][ T3731] __fput+0x6bd/0xf00 [ 179.180787][ T3731] ____fput+0x37/0x40 [ 179.181481][ T3731] task_work_run+0x140/0x280 [ 179.182219][ T3731] do_exit+0xe51/0x3e60 [ 179.182930][ T3731] do_group_exit+0x20e/0x450 [ 179.183656][ T3731] get_signal+0x2dfb/0x38f0 [ 179.184344][ T3731] arch_do_signal_or_restart+0xaa/0xe10 [ 179.185266][ T3731] exit_to_user_mode_prepare+0x2d2/0x560 [ 179.186136][ T3731] syscall_exit_to_user_mode+0x35/0x60 [ 179.186984][ T3731] do_syscall_64+0xc5/0x140 [ 179.187681][ T3731] entry_SYSCALL_64_after_hwframe+0x44/0xae [ 179.188604][ T3731] ===================================================== In our case, there are two Thread A and B: Context: Thread A: Context: Thread B: l2cap_chan_timeout() __se_sys_shutdown() l2cap_chan_close() l2cap_sock_shutdown() l2cap_chan_del() l2cap_chan_close() l2cap_sock_teardown_cb() l2cap_sock_teardown_cb() Once l2cap_sock_teardown_cb() excuted, this sock will be marked as SOCK_ZAPPED, and can be treated as killable in l2cap_sock_kill() if sock_orphan() has excuted, at this time we close sock through sock_close() which end to call l2cap_sock_kill() like Thread C: Context: Thread C: sock_close() l2cap_sock_release() sock_orphan() l2cap_sock_kill() #free sock if refcnt is 1 If C completed, Once A or B reaches l2cap_sock_teardown_cb() again, use-after-free happened. We should set chan->data to NULL if sock is destructed, for telling teardown operation is not allowed in l2cap_sock_teardown_cb(), and also we should avoid killing an already killed socket in l2cap_sock_close_cb(). Signed-off-by: Wang ShaoBo <bobo.shaobowang(a)huawei.com> Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz(a)intel.com> Signed-off-by: Marcel Holtmann <marcel(a)holtmann.org> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- net/bluetooth/l2cap_sock.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index d1d5fa35dcc9a..b4f6b74c40038 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -1308,6 +1308,9 @@ static void l2cap_sock_close_cb(struct l2cap_chan *chan) { struct sock *sk = chan->data; + if (!sk) + return; + l2cap_sock_kill(sk); } @@ -1316,6 +1319,9 @@ static void l2cap_sock_teardown_cb(struct l2cap_chan *chan, int err) struct sock *sk = chan->data; struct sock *parent; + if (!sk) + return; + BT_DBG("chan %p state %s", chan, state_to_string(chan->state)); /* This callback can be called both for server (BT_LISTEN) @@ -1498,8 +1504,10 @@ static void l2cap_sock_destruct(struct sock *sk) { BT_DBG("sk %p", sk); - if (l2cap_pi(sk)->chan) + if (l2cap_pi(sk)->chan) { + l2cap_pi(sk)->chan->data = NULL; l2cap_chan_put(l2cap_pi(sk)->chan); + } if (l2cap_pi(sk)->rx_busy_skb) { kfree_skb(l2cap_pi(sk)->rx_busy_skb); -- 2.25.1

1 0

[PATCH openEuler-5.10 01/17] slub: fix unreclaimable slab stat for bulk free
by Zheng Zengkai 29 Sep '21

29 Sep '21

From: Shakeel Butt <shakeelb(a)google.com> mainline inclusion from mainline-v5.14-rc4 commit f227f0faf63b46a113c4d1aca633c80195622dd2 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4C12I CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… ---------------------------------------------------------------------- SLUB uses page allocator for higher order allocations and update unreclaimable slab stat for such allocations. At the moment, the bulk free for SLUB does not share code with normal free code path for these type of allocations and have missed the stat update. So, fix the stat update by common code. The user visible impact of the bug is the potential of inconsistent unreclaimable slab stat visible through meminfo and vmstat. Link: https://lkml.kernel.org/r/20210728155354.3440560-1-shakeelb@google.com Fixes: 6a486c0ad4dc ("mm, sl[ou]b: improve memory accounting") Signed-off-by: Shakeel Butt <shakeelb(a)google.com> Acked-by: Michal Hocko <mhocko(a)suse.com> Acked-by: Roman Gushchin <guro(a)fb.com> Reviewed-by: Muchun Song <songmuchun(a)bytedance.com> Cc: Christoph Lameter <cl(a)linux.com> Cc: Pekka Enberg <penberg(a)kernel.org> Cc: David Rientjes <rientjes(a)google.com> Cc: Joonsoo Kim <iamjoonsoo.kim(a)lge.com> Cc: Vlastimil Babka <vbabka(a)suse.cz> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Chen Huang <chenhuang5(a)huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- mm/slub.c | 22 ++++++++++++---------- 1 file changed, 12 insertions(+), 10 deletions(-) diff --git a/mm/slub.c b/mm/slub.c index f06f002bb098..4a83fa347672 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -3164,6 +3164,16 @@ struct detached_freelist { struct kmem_cache *s; }; +static inline void free_nonslab_page(struct page *page) +{ + unsigned int order = compound_order(page); + + VM_BUG_ON_PAGE(!PageCompound(page), page); + kfree_hook(page_address(page)); + mod_lruvec_page_state(page, NR_SLAB_UNRECLAIMABLE_B, -(PAGE_SIZE << order)); + __free_pages(page, order); +} + /* * This function progressively scans the array with free objects (with * a limited look ahead) and extract objects belonging to the same @@ -3200,9 +3210,7 @@ int build_detached_freelist(struct kmem_cache *s, size_t size, if (!s) { /* Handle kalloc'ed objects */ if (unlikely(!PageSlab(page))) { - BUG_ON(!PageCompound(page)); - kfree_hook(object); - __free_pages(page, compound_order(page)); + free_nonslab_page(page); p[size] = NULL; /* mark object processed */ return size; } @@ -4102,13 +4110,7 @@ void kfree(const void *x) page = virt_to_head_page(x); if (unlikely(!PageSlab(page))) { - unsigned int order = compound_order(page); - - BUG_ON(!PageCompound(page)); - kfree_hook(object); - mod_lruvec_page_state(page, NR_SLAB_UNRECLAIMABLE_B, - -(PAGE_SIZE << order)); - __free_pages(page, order); + free_nonslab_page(page); return; } slab_free(page->slab_cache, page, object, NULL, 1, _RET_IP_); -- 2.20.1

1 16

[PATCH openEuler-21.09] eulerfs: add the /proc/idle file.
by Hongyu Li 29 Sep '21

29 Sep '21

From: Hongyu Li <“543306408(a)qq.xn--com-9o0a> openEuler inclusion category: bugfix bugzilla: https://gitee.com/openeuler-competition/summer-2021/issues/I3EBT6 CVE: NA ---------------------------------------------------------------------- The /proc/idle can give higher precision in accounting the CPU idle time compared with the traditional /proc/stat ways. Signed-off-by: Hongyu Li <“543306408(a)qq.xn--com-9o0a> --- fs/proc/Kconfig | 7 ++++ fs/proc/Makefile | 1 + fs/proc/proc_idle.c | 82 ++++++++++++++++++++++++++++++++++++++++++ kernel/sched/cputime.c | 16 +++++++++ kernel/sched/idle.c | 21 +++++++++++ 5 files changed, 127 insertions(+) create mode 100644 fs/proc/proc_idle.c diff --git a/fs/proc/Kconfig b/fs/proc/Kconfig index c930001056f9..46620afe9cac 100644 --- a/fs/proc/Kconfig +++ b/fs/proc/Kconfig @@ -107,3 +107,10 @@ config PROC_PID_ARCH_STATUS config PROC_CPU_RESCTRL def_bool n depends on PROC_FS + +config PROC_IDLE + bool "include /proc/idle file" + depends on PROC_FS + default y + help + Provide the CPU idle time in the /proc/idle file. diff --git a/fs/proc/Makefile b/fs/proc/Makefile index 8704d41dd67c..69dd2da3a080 100644 --- a/fs/proc/Makefile +++ b/fs/proc/Makefile @@ -34,5 +34,6 @@ proc-$(CONFIG_PROC_VMCORE) += vmcore.o proc-$(CONFIG_PRINTK) += kmsg.o proc-$(CONFIG_PROC_PAGE_MONITOR) += page.o proc-$(CONFIG_BOOT_CONFIG) += bootconfig.o +proc-$(CONFIG_PROC_IDLE) += proc_idle.o obj-$(CONFIG_ETMEM_SCAN) += etmem_scan.o obj-$(CONFIG_ETMEM_SWAP) += etmem_swap.o diff --git a/fs/proc/proc_idle.c b/fs/proc/proc_idle.c new file mode 100644 index 000000000000..bbb52e247448 --- /dev/null +++ b/fs/proc/proc_idle.c @@ -0,0 +1,82 @@ +#include <linux/cpumask.h> +#include <linux/device.h> +#include <linux/fs.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/kernel.h> +#include <linux/kernel_stat.h> +#include <linux/module.h> +#include <linux/proc_fs.h> +#include <linux/sched.h> +#include <linux/sched/stat.h> +#include <linux/seq_file.h> +#include <linux/slab.h> +#include <linux/time.h> +#include <linux/irqnr.h> +#include <linux/sched/cputime.h> +#include <linux/tick.h> + +#ifdef CONFIG_PROC_IDLE + +#define PROC_NAME "idle" + +extern u64 cpu_rq_get(int cpu); + +static u64 get_idle_sum_exec_runtime(int cpu) +{ + u64 idle = cpu_rq_get(cpu); + + return idle; +} + +static int show_idle(struct seq_file *p, void *v) +{ + int i; + u64 idle; + + idle = 0; + + for_each_possible_cpu(i) { + + idle += get_idle_sum_exec_runtime(i); + + } + + seq_put_decimal_ull(p, "cpu ", nsec_to_clock_t(idle)); + seq_putc(p, '\n'); + + for_each_online_cpu(i) { + + idle = get_idle_sum_exec_runtime(i); + + seq_printf(p, "cpu%d", i); + seq_put_decimal_ull(p, " ", nsec_to_clock_t(idle)); + seq_putc(p, '\n'); + } + + return 0; +} + +static int idle_open(struct inode *inode, struct file *file) +{ + unsigned int size = 1024 + 128 * num_online_cpus(); + + return single_open_size(file, show_idle, NULL, size); +} + +static struct proc_ops idle_procs_ops = { + .proc_open = idle_open, + .proc_read_iter = seq_read_iter, + .proc_lseek = seq_lseek, + .proc_release = single_release, +}; + +static int __init kernel_module_init(void) +{ + proc_create(PROC_NAME, 0, NULL, &idle_procs_ops); + return 0; +} + +fs_initcall(kernel_module_init); + +#endif /*CONFIG_PROC_IDLE*/ diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 5a55d2300452..bb280852bb06 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -1078,3 +1078,19 @@ void kcpustat_cpu_fetch(struct kernel_cpustat *dst, int cpu) EXPORT_SYMBOL_GPL(kcpustat_cpu_fetch); #endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */ + + +#ifdef CONFIG_PROC_IDLE + + +u64 cpu_rq_get(int cpu) +{ + struct rq *rq = cpu_rq(cpu); + struct sched_entity *idle_se = &rq->idle->se; + u64 idle = idle_se->sum_exec_runtime; + + return idle; +} +EXPORT_SYMBOL_GPL(cpu_rq_get); + +#endif /* CONFIG_PROC_IDLE */ diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 36b545f17206..e3fb940a61e8 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -424,6 +424,20 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int fl static void put_prev_task_idle(struct rq *rq, struct task_struct *prev) { +#ifdef CONFIG_PROC_IDLE + struct sched_entity *idle_se = &rq->idle->se; + u64 now = sched_clock(); + u64 delta_exec; + + delta_exec = now - idle_se->exec_start; + if (unlikely((s64)delta_exec <= 0)) + return; + + schedstat_set(idle_se->statistics.exec_max, + max(delta_exec, idle_se->statistics.exec_max)); + + idle_se->sum_exec_runtime += delta_exec; +#endif } static void set_next_task_idle(struct rq *rq, struct task_struct *next, bool first) @@ -436,6 +450,13 @@ struct task_struct *pick_next_task_idle(struct rq *rq) { struct task_struct *next = rq->idle; +#ifdef CONFIG_PROC_IDLE + struct sched_entity *idle_se = &rq->idle->se; + u64 now = sched_clock(); + + idle_se->exec_start = now; +#endif + set_next_task_idle(rq, next, true); return next; -- 2.17.1

1 0