From: shaodenghui shaodenghui@huawei.com

euleros inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I94XYA CVE: NA

-------------------------------------------------

Currently, single thread workqueue only have single pwq, all of works are queued the same workerpool. This is not optimal on NUMA machines, will cause workers jump around across node.

This patch add a new wq flags __WQ_DYNAMIC, this new kind of single thread workqueue creates a separate pwq covering the intersecting CPUS for each NUMA node which has online CPUS in @attrs->cpumask instead of mapping all entries of numa_pwq_tbl[] to the same pwq. After this, we can specify the @cpu of queue_work_on, so the work can be executed on the same NUMA node of the specified @cpu. This kind of wq only support single work, multi works can't guarantee the work's order.

Signed-off-by: shaodenghui shaodenghui@huawei.com --- kernel/workqueue.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 1888741f5edd..fc733366d5f4 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -4355,6 +4355,9 @@ apply_wqattrs_prepare(struct workqueue_struct *wq, * it even if we don't use it immediately. */ copy_workqueue_attrs(new_attrs, attrs); + if (wq->flags & __WQ_DYNAMIC) + new_attrs->ordered = false; + wqattrs_actualize_cpumask(new_attrs, unbound_cpumask); cpumask_copy(new_attrs->__pod_cpumask, new_attrs->cpumask); ctx->dfl_pwq = alloc_unbound_pwq(wq, new_attrs); @@ -4591,10 +4594,12 @@ static int alloc_and_link_pwqs(struct workqueue_struct *wq) cpus_read_lock(); if (wq->flags & __WQ_ORDERED) { ret = apply_workqueue_attrs(wq, ordered_wq_attrs[highpri]); - /* there should only be single pwq for ordering guarantee */ - WARN(!ret && (wq->pwqs.next != &wq->dfl_pwq->pwqs_node || - wq->pwqs.prev != &wq->dfl_pwq->pwqs_node), - "ordering guarantee broken for workqueue %s\n", wq->name); + if (!(wq->flags & __WQ_DYNAMIC)) { + /* there should only be single pwq for ordering guarantee */ + WARN(!ret && (wq->pwqs.next != &wq->dfl_pwq->pwqs_node || + wq->pwqs.prev != &wq->dfl_pwq->pwqs_node), + "ordering guarantee broken for workqueue %s\n", wq->name); + } } else { ret = apply_workqueue_attrs(wq, unbound_std_wq_attrs[highpri]); } @@ -5798,7 +5803,7 @@ static int workqueue_apply_unbound_cpumask(const cpumask_var_t unbound_cpumask) continue;

/* creating multiple pwqs breaks ordering guarantee */ - if (!list_empty(&wq->pwqs)) { + if (!list_empty(&wq->pwqs) && !(wq->flags & __WQ_DYNAMIC)) { if (wq->flags & __WQ_ORDERED_EXPLICIT) continue; wq->flags &= ~__WQ_ORDERED;

From: Shao Denghui shaodenghui@huawei.com

virt inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I94XYA

----------------------------------------------------------------------

Add CONFIG_SCSI_KWORKER to control scsi kworker code compile or not.

Signed-off-by: shaodenghui shaodenghui@huawei.com --- arch/arm64/configs/openeuler_defconfig | 1 + arch/x86/configs/openeuler_defconfig | 1 + drivers/scsi/Kconfig | 18 ++++++++++++++++++ drivers/scsi/iscsi_tcp.c | 4 ++++ drivers/scsi/libiscsi.c | 13 +++++++++++++ kernel/workqueue.c | 15 ++++++++++++++- 6 files changed, 51 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/configs/openeuler_defconfig b/arch/arm64/configs/openeuler_defconfig index afde4d70ee13..3845f223efab 100644 --- a/arch/arm64/configs/openeuler_defconfig +++ b/arch/arm64/configs/openeuler_defconfig @@ -2486,6 +2486,7 @@ CONFIG_CHR_DEV_SCH=m CONFIG_SCSI_ENCLOSURE=m CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_LOGGING=y +CONFIG_SCSI_KWORKER=y CONFIG_SCSI_SCAN_ASYNC=y

# diff --git a/arch/x86/configs/openeuler_defconfig b/arch/x86/configs/openeuler_defconfig index 627a08ecbf4a..9c12b2633cdf 100644 --- a/arch/x86/configs/openeuler_defconfig +++ b/arch/x86/configs/openeuler_defconfig @@ -2477,6 +2477,7 @@ CONFIG_CHR_DEV_SCH=m CONFIG_SCSI_ENCLOSURE=m CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_LOGGING=y +CONFIG_SCSI_KWORKER=y CONFIG_SCSI_SCAN_ASYNC=y

# diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig index 695a57d894cd..5dd1f2b956f9 100644 --- a/drivers/scsi/Kconfig +++ b/drivers/scsi/Kconfig @@ -218,6 +218,24 @@ config SCSI_LOGGING there should be no noticeable performance impact as long as you have logging turned off.

+config SCSI_KWORKER + tristate "kworker NUMA affinity " + default n + help + kworker: Fix the problem of ipsan performance degradation on ARM + architecture. + + When the current downstream FS tests IPSAN, it is found that the + performance on ARM is much worse than that on X86, and the test data + of IPSAN fluctuates greatly. After analysis, the reason is that when + iscsi issues IO, the task is sent to kworker for processing by + iscsi_xmitworker. + + The workqueue created by iscsi can automatically identify the CPU of + the soft interrupt currently processed by iscsi, and automatically + schedule the workqueue to the corresponding NUMA node. + + config SCSI_SCAN_ASYNC bool "Asynchronous SCSI scanning" depends on SCSI diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c index d68bf693162c..f47a0c37319f 100644 --- a/drivers/scsi/iscsi_tcp.c +++ b/drivers/scsi/iscsi_tcp.c @@ -170,7 +170,9 @@ static void iscsi_sw_tcp_data_ready(struct sock *sk) struct iscsi_sw_tcp_conn *tcp_sw_conn; struct iscsi_tcp_conn *tcp_conn; struct iscsi_conn *conn; +#ifdef CONFIG_SCSI_KWORKER int current_cpu; +#endif

trace_sk_data_ready(sk);

@@ -182,12 +184,14 @@ static void iscsi_sw_tcp_data_ready(struct sock *sk) } tcp_conn = conn->dd_data;

+#ifdef CONFIG_SCSI_KWORKER /* save intimate cpu when in softirq */ if (!sock_owned_by_user_nocheck(sk)) { current_cpu = smp_processor_id(); if (conn->intimate_cpu != current_cpu) conn->intimate_cpu = current_cpu; } +#endif

tcp_sw_conn = tcp_conn->dd_data;

diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c index 0a8aee8fd742..c5fe9003a994 100644 --- a/drivers/scsi/libiscsi.c +++ b/drivers/scsi/libiscsi.c @@ -89,6 +89,7 @@ inline void iscsi_conn_queue_xmit(struct iscsi_conn *conn) { struct Scsi_Host *shost = conn->session->host; struct iscsi_host *ihost = shost_priv(shost); +#ifdef CONFIG_SCSI_KWORKER int intimate_cpu = conn->intimate_cpu;

if (ihost->workq) { @@ -98,6 +99,10 @@ inline void iscsi_conn_queue_xmit(struct iscsi_conn *conn) else queue_work(ihost->workq, &conn->xmitwork); } +#else + if (ihost->workq) + queue_work(ihost->workq, &conn->xmitwork); +#endif } EXPORT_SYMBOL_GPL(iscsi_conn_queue_xmit);

@@ -2913,9 +2918,15 @@ struct Scsi_Host *iscsi_host_alloc(const struct scsi_host_template *sht, ihost = shost_priv(shost);

if (xmit_can_sleep) { +#ifdef CONFIG_SCSI_KWORKER /* this kind of workqueue only support single work */ ihost->workq = alloc_ordered_workqueue("iscsi_q_%d", __WQ_LEGACY | WQ_MEM_RECLAIM | __WQ_DYNAMIC, shost->host_no); +#else + ihost->workq = alloc_workqueue("iscsi_q_%d", + WQ_SYSFS | __WQ_LEGACY | WQ_MEM_RECLAIM | WQ_UNBOUND, + 1, shost->host_no); +#endif if (!ihost->workq) goto free_host; } @@ -3196,7 +3207,9 @@ iscsi_conn_setup(struct iscsi_cls_session *cls_session, int dd_size, conn->c_stage = ISCSI_CONN_INITIAL_STAGE; conn->id = conn_idx; conn->exp_statsn = 0; +#ifdef CONFIG_SCSI_KWORKER conn->intimate_cpu = -1; +#endif

timer_setup(&conn->transport_timer, iscsi_check_transport_timeouts, 0);

diff --git a/kernel/workqueue.c b/kernel/workqueue.c index cdfd4261b442..7694f2f7ef43 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -4355,8 +4355,10 @@ apply_wqattrs_prepare(struct workqueue_struct *wq, * it even if we don't use it immediately. */ copy_workqueue_attrs(new_attrs, attrs); +#ifdef CONFIG_SCSI_KWORKER if (wq->flags & __WQ_DYNAMIC) new_attrs->ordered = false; +#endif

wqattrs_actualize_cpumask(new_attrs, unbound_cpumask); cpumask_copy(new_attrs->__pod_cpumask, new_attrs->cpumask); @@ -4594,12 +4596,19 @@ static int alloc_and_link_pwqs(struct workqueue_struct *wq) cpus_read_lock(); if (wq->flags & __WQ_ORDERED) { ret = apply_workqueue_attrs(wq, ordered_wq_attrs[highpri]); +#ifdef CONFIG_SCSI_KWORKER if (!(wq->flags & __WQ_DYNAMIC)) { /* there should only be single pwq for ordering guarantee */ WARN(!ret && (wq->pwqs.next != &wq->dfl_pwq->pwqs_node || wq->pwqs.prev != &wq->dfl_pwq->pwqs_node), - "ordering guarantee broken for workqueue %s\n", wq->name); + "ordering guarantee broken for workqueue %s\n", wq->name); } +#else + /* there should only be single pwq for ordering guarantee */ + WARN(!ret && (wq->pwqs.next != &wq->dfl_pwq->pwqs_node || + wq->pwqs.prev != &wq->dfl_pwq->pwqs_node), + "ordering guarantee broken for workqueue %s\n", wq->name); +#endif } else { ret = apply_workqueue_attrs(wq, unbound_std_wq_attrs[highpri]); } @@ -5803,7 +5812,11 @@ static int workqueue_apply_unbound_cpumask(const cpumask_var_t unbound_cpumask) continue;

/* creating multiple pwqs breaks ordering guarantee */ +#ifdef CONFIG_SCSI_KWORKER if (!list_empty(&wq->pwqs) && !(wq->flags & __WQ_DYNAMIC)) { +#else + if (!list_empty(&wq->pwqs)) { +#endif if (wq->flags & __WQ_ORDERED_EXPLICIT) continue; wq->flags &= ~__WQ_ORDERED;