From 3b923b3238791e6d67e9701aae9d1f79f65accbc Mon Sep 17 00:00:00 2001 From: "yang.yang29@zte.com.cn" Date: Thu, 8 Jun 2023 18:58:33 +0800 Subject: [PATCH 1/5] mm/vmalloc: Another preempt disable region which sucks commit 52c41cc94ac9ab9aa9d4ef4e5795830905b69bc4 upstream. Avoid the preempt disable version of get_cpu_var(). The inner-lock should provide enough serialisation. Signed-off-by: Thomas Gleixner --- mm/vmalloc.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/mm/vmalloc.c b/mm/vmalloc.c index bc0d148c733a..f451b31bba90 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1820,7 +1820,7 @@ static void *new_vmap_block(unsigned int order, gfp_t gfp_mask) struct vmap_block *vb; struct vmap_area *va; unsigned long vb_idx; - int node, err; + int node, err, cpu; void *vaddr; node = numa_node_id(); @@ -1857,11 +1857,12 @@ static void *new_vmap_block(unsigned int order, gfp_t gfp_mask) return ERR_PTR(err); } - vbq = &get_cpu_var(vmap_block_queue); + cpu = get_cpu_light(); + vbq = this_cpu_ptr(&vmap_block_queue); spin_lock(&vbq->lock); list_add_tail_rcu(&vb->free_list, &vbq->free); spin_unlock(&vbq->lock); - put_cpu_var(vmap_block_queue); + put_cpu_light(); return vaddr; } @@ -1926,6 +1927,7 @@ static void *vb_alloc(unsigned long size, gfp_t gfp_mask) struct vmap_block *vb; void *vaddr = NULL; unsigned int order; + int cpu; BUG_ON(offset_in_page(size)); BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC); @@ -1940,7 +1942,8 @@ static void *vb_alloc(unsigned long size, gfp_t gfp_mask) order = get_order(size); rcu_read_lock(); - vbq = &get_cpu_var(vmap_block_queue); + cpu = get_cpu_light(); + vbq = this_cpu_ptr(&vmap_block_queue); list_for_each_entry_rcu(vb, &vbq->free, free_list) { unsigned long pages_off; @@ -1963,7 +1966,7 @@ static void *vb_alloc(unsigned long size, gfp_t gfp_mask) break; } - put_cpu_var(vmap_block_queue); + put_cpu_light(); rcu_read_unlock(); /* Allocate new block if nothing was found */ -- Gitee From 907337dae078674c8885d8313af30cf36d226651 Mon Sep 17 00:00:00 2001 From: "yang.yang29@zte.com.cn" Date: Thu, 8 Jun 2023 18:58:49 +0800 Subject: [PATCH 2/5] block/mq: do not invoke preempt_disable() commit 36337c925349eca80db3c672563d292521511711 upstream. preempt_disable() and get_cpu() don't play well together with the sleeping locks it tries to allocate later. It seems to be enough to replace it with get_cpu_light() and migrate_disable(). Signed-off-by: Sebastian Andrzej Siewior --- block/blk-mq.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/block/blk-mq.c b/block/blk-mq.c index 5b3e89fac232..cfcf74e716b7 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1605,14 +1605,14 @@ static void __blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async, return; if (!async && !(hctx->flags & BLK_MQ_F_BLOCKING)) { - int cpu = get_cpu(); + int cpu = get_cpu_light(); if (cpumask_test_cpu(cpu, hctx->cpumask)) { __blk_mq_run_hw_queue(hctx); - put_cpu(); + put_cpu_light(); return; } - put_cpu(); + put_cpu_light(); } kblockd_mod_delayed_work_on(blk_mq_hctx_next_cpu(hctx), &hctx->run_work, -- Gitee From 6cf23152b7c349b10a1ab9d01e48a5c46891398b Mon Sep 17 00:00:00 2001 From: "yang.yang29@zte.com.cn" Date: Thu, 8 Jun 2023 18:59:07 +0800 Subject: [PATCH 3/5] md: raid5: Make raid5_percpu handling RT aware commit 406dc3e4e73f88b0f34e9abe6bfc5e684e9049d6 upstream. __raid_run_ops() disables preemption with get_cpu() around the access to the raid5_percpu variables. That causes scheduling while atomic spews on RT. Serialize the access to the percpu data with a lock and keep the code preemptible. Reported-by: Udo van den Heuvel Signed-off-by: Thomas Gleixner Tested-by: Udo van den Heuvel --- drivers/md/raid5.c | 7 +++++-- drivers/md/raid5.h | 1 + 2 files changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index c8cafdb094aa..112391c2b932 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -2217,8 +2217,9 @@ static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request) struct raid5_percpu *percpu; unsigned long cpu; - cpu = get_cpu(); + cpu = get_cpu_light(); percpu = per_cpu_ptr(conf->percpu, cpu); + spin_lock(&percpu->lock); if (test_bit(STRIPE_OP_BIOFILL, &ops_request)) { ops_run_biofill(sh); overlap_clear++; @@ -2277,7 +2278,8 @@ static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request) if (test_and_clear_bit(R5_Overlap, &dev->flags)) wake_up(&sh->raid_conf->wait_for_overlap); } - put_cpu(); + spin_unlock(&percpu->lock); + put_cpu_light(); } static void free_stripe(struct kmem_cache *sc, struct stripe_head *sh) @@ -7096,6 +7098,7 @@ static int raid456_cpu_up_prepare(unsigned int cpu, struct hlist_node *node) __func__, cpu); return -ENOMEM; } + spin_lock_init(&per_cpu_ptr(conf->percpu, cpu)->lock); return 0; } diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h index 5c05acf20e1f..665fe138ab4f 100644 --- a/drivers/md/raid5.h +++ b/drivers/md/raid5.h @@ -635,6 +635,7 @@ struct r5conf { int recovery_disabled; /* per cpu variables */ struct raid5_percpu { + spinlock_t lock; /* Protection for -RT */ struct page *spare_page; /* Used when checking P/Q in raid6 */ void *scribble; /* space for constructing buffer * lists and performing address -- Gitee From 6039b6f1029e5ba4f36ca47fdbe71e051440cba3 Mon Sep 17 00:00:00 2001 From: "yang.yang29@zte.com.cn" Date: Thu, 8 Jun 2023 18:59:54 +0800 Subject: [PATCH 4/5] scsi/fcoe: Make RT aware. commit 9d4e0054e62034905fe7c5ef97ebf165f9e2779f upstream. Do not disable preemption while taking sleeping locks. All user look safe for migrate_diable() only. Signed-off-by: Thomas Gleixner --- drivers/scsi/fcoe/fcoe.c | 16 ++++++++-------- drivers/scsi/fcoe/fcoe_ctlr.c | 4 ++-- drivers/scsi/libfc/fc_exch.c | 4 ++-- 3 files changed, 12 insertions(+), 12 deletions(-) diff --git a/drivers/scsi/fcoe/fcoe.c b/drivers/scsi/fcoe/fcoe.c index 0f9274960dc6..dc97e4f1f4ad 100644 --- a/drivers/scsi/fcoe/fcoe.c +++ b/drivers/scsi/fcoe/fcoe.c @@ -1452,11 +1452,11 @@ static int fcoe_rcv(struct sk_buff *skb, struct net_device *netdev, static int fcoe_alloc_paged_crc_eof(struct sk_buff *skb, int tlen) { struct fcoe_percpu_s *fps; - int rc; + int rc, cpu = get_cpu_light(); - fps = &get_cpu_var(fcoe_percpu); + fps = &per_cpu(fcoe_percpu, cpu); rc = fcoe_get_paged_crc_eof(skb, tlen, fps); - put_cpu_var(fcoe_percpu); + put_cpu_light(); return rc; } @@ -1641,11 +1641,11 @@ static inline int fcoe_filter_frames(struct fc_lport *lport, return 0; } - stats = per_cpu_ptr(lport->stats, get_cpu()); + stats = per_cpu_ptr(lport->stats, get_cpu_light()); stats->InvalidCRCCount++; if (stats->InvalidCRCCount < 5) printk(KERN_WARNING "fcoe: dropping frame with CRC error\n"); - put_cpu(); + put_cpu_light(); return -EINVAL; } @@ -1686,7 +1686,7 @@ static void fcoe_recv_frame(struct sk_buff *skb) */ hp = (struct fcoe_hdr *) skb_network_header(skb); - stats = per_cpu_ptr(lport->stats, get_cpu()); + stats = per_cpu_ptr(lport->stats, get_cpu_light()); if (unlikely(FC_FCOE_DECAPS_VER(hp) != FC_FCOE_VER)) { if (stats->ErrorFrames < 5) printk(KERN_WARNING "fcoe: FCoE version " @@ -1718,13 +1718,13 @@ static void fcoe_recv_frame(struct sk_buff *skb) goto drop; if (!fcoe_filter_frames(lport, fp)) { - put_cpu(); + put_cpu_light(); fc_exch_recv(lport, fp); return; } drop: stats->ErrorFrames++; - put_cpu(); + put_cpu_light(); kfree_skb(skb); } diff --git a/drivers/scsi/fcoe/fcoe_ctlr.c b/drivers/scsi/fcoe/fcoe_ctlr.c index bbc5d6b9be73..8f9a02912938 100644 --- a/drivers/scsi/fcoe/fcoe_ctlr.c +++ b/drivers/scsi/fcoe/fcoe_ctlr.c @@ -828,7 +828,7 @@ static unsigned long fcoe_ctlr_age_fcfs(struct fcoe_ctlr *fip) INIT_LIST_HEAD(&del_list); - stats = per_cpu_ptr(fip->lp->stats, get_cpu()); + stats = per_cpu_ptr(fip->lp->stats, get_cpu_light()); list_for_each_entry_safe(fcf, next, &fip->fcfs, list) { deadline = fcf->time + fcf->fka_period + fcf->fka_period / 2; @@ -864,7 +864,7 @@ static unsigned long fcoe_ctlr_age_fcfs(struct fcoe_ctlr *fip) sel_time = fcf->time; } } - put_cpu(); + put_cpu_light(); list_for_each_entry_safe(fcf, next, &del_list, list) { /* Removes fcf from current list */ diff --git a/drivers/scsi/libfc/fc_exch.c b/drivers/scsi/libfc/fc_exch.c index 4261380af97b..65160eaaa929 100644 --- a/drivers/scsi/libfc/fc_exch.c +++ b/drivers/scsi/libfc/fc_exch.c @@ -826,10 +826,10 @@ static struct fc_exch *fc_exch_em_alloc(struct fc_lport *lport, } memset(ep, 0, sizeof(*ep)); - cpu = get_cpu(); + cpu = get_cpu_light(); pool = per_cpu_ptr(mp->pool, cpu); spin_lock_bh(&pool->lock); - put_cpu(); + put_cpu_light(); /* peek cache of free slot */ if (pool->left != FC_XID_UNKNOWN) { -- Gitee From 2463a0a06ca050a5f2e28fa4c40f90816d447a42 Mon Sep 17 00:00:00 2001 From: "yang.yang29@zte.com.cn" Date: Thu, 8 Jun 2023 19:00:06 +0800 Subject: [PATCH 5/5] sunrpc: Make svc_xprt_do_enqueue() use get_cpu_light() commit 98671a4c47298471e9094c3dde331c8926cef288 upstream. |BUG: sleeping function called from invalid context at kernel/locking/rtmutex.c:915 |in_atomic(): 1, irqs_disabled(): 0, pid: 3194, name: rpc.nfsd |Preemption disabled at:[] svc_xprt_received+0x4b/0xc0 [sunrpc] |CPU: 6 PID: 3194 Comm: rpc.nfsd Not tainted 3.18.7-rt1 #9 |Hardware name: MEDION MS-7848/MS-7848, BIOS M7848W08.404 11/06/2014 | ffff880409630000 ffff8800d9a33c78 ffffffff815bdeb5 0000000000000002 | 0000000000000000 ffff8800d9a33c98 ffffffff81073c86 ffff880408dd6008 | ffff880408dd6000 ffff8800d9a33cb8 ffffffff815c3d84 ffff88040b3ac000 |Call Trace: | [] dump_stack+0x4f/0x9e | [] __might_sleep+0xe6/0x150 | [] rt_spin_lock+0x24/0x50 | [] svc_xprt_do_enqueue+0x80/0x230 [sunrpc] | [] svc_xprt_received+0x4b/0xc0 [sunrpc] | [] svc_add_new_perm_xprt+0x6d/0x80 [sunrpc] | [] svc_addsock+0x143/0x200 [sunrpc] | [] write_ports+0x28c/0x340 [nfsd] | [] nfsctl_transaction_write+0x4c/0x80 [nfsd] | [] vfs_write+0xb3/0x1d0 | [] SyS_write+0x49/0xb0 | [] system_call_fastpath+0x16/0x1b Signed-off-by: Mike Galbraith Signed-off-by: Sebastian Andrzej Siewior --- net/sunrpc/svc_xprt.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 06e503466c32..16bd1278a989 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -422,7 +422,7 @@ void svc_xprt_do_enqueue(struct svc_xprt *xprt) if (test_and_set_bit(XPT_BUSY, &xprt->xpt_flags)) return; - cpu = get_cpu(); + cpu = get_cpu_light(); pool = svc_pool_for_cpu(xprt->xpt_server, cpu); atomic_long_inc(&pool->sp_stats.packets); @@ -446,7 +446,7 @@ void svc_xprt_do_enqueue(struct svc_xprt *xprt) rqstp = NULL; out_unlock: rcu_read_unlock(); - put_cpu(); + put_cpu_light(); trace_svc_xprt_do_enqueue(xprt, rqstp); } EXPORT_SYMBOL_GPL(svc_xprt_do_enqueue); -- Gitee