From 808c43b7c7f70360ed7b9e43e2cf980f388e71fa Mon Sep 17 00:00:00 2001 From: Andrey Ignatov Date: Fri, 21 Sep 2018 17:03:27 -0700 Subject: [PATCH 1/3] cgroup: Simplify cgroup_ancestor Simplify cgroup_ancestor function. This is follow-up for commit 7723628101aa ("bpf: Introduce bpf_skb_ancestor_cgroup_id helper") Suggested-by: Tejun Heo Signed-off-by: Andrey Ignatov Signed-off-by: Tejun Heo --- include/linux/cgroup.h | 15 +++------------ 1 file changed, 3 insertions(+), 12 deletions(-) diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 32c553556bbd..e03a92430383 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -567,20 +567,11 @@ static inline bool cgroup_is_descendant(struct cgroup *cgrp, static inline struct cgroup *cgroup_ancestor(struct cgroup *cgrp, int ancestor_level) { - struct cgroup *ptr; - if (cgrp->level < ancestor_level) return NULL; - - for (ptr = cgrp; - ptr && ptr->level > ancestor_level; - ptr = cgroup_parent(ptr)) - ; - - if (ptr && ptr->level == ancestor_level) - return ptr; - - return NULL; + while (cgrp && cgrp->level > ancestor_level) + cgrp = cgroup_parent(cgrp); + return cgrp; } /** From 8bc7146a5b8bb4c9bfa32697f7208c70611845f9 Mon Sep 17 00:00:00 2001 From: Rami Rosen Date: Tue, 23 Oct 2018 18:01:06 +0300 Subject: [PATCH 2/3] rdmacg: fix a typo in rdmacg documentation This patch fixes a typo in RDMA cgroup documentation. Signed-off-by: Rami Rosen Reviewed-by: Parav Pandit Signed-off-by: Tejun Heo --- Documentation/cgroup-v1/rdma.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/cgroup-v1/rdma.txt b/Documentation/cgroup-v1/rdma.txt index af618171e0eb..9bdb7fd03f83 100644 --- a/Documentation/cgroup-v1/rdma.txt +++ b/Documentation/cgroup-v1/rdma.txt @@ -27,7 +27,7 @@ cgroup. Currently user space applications can easily take away all the rdma verb specific resources such as AH, CQ, QP, MR etc. Due to which other applications in other cgroup or kernel space ULPs may not even get chance to allocate any -rdma resources. This can leads to service unavailability. +rdma resources. This can lead to service unavailability. Therefore RDMA controller is needed through which resource consumption of processes can be limited. Through this controller different rdma From a90e90b7d55e789c71d85b946ffb5c1ab2f137ca Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Thu, 18 Oct 2018 10:56:17 +0200 Subject: [PATCH 3/3] cgroup, netclassid: add a preemption point to write_classid We have seen a customer complaining about soft lockups on !PREEMPT kernel config with 4.4 based kernel [1072141.435366] NMI watchdog: BUG: soft lockup - CPU#21 stuck for 22s! [systemd:1] [1072141.444090] Modules linked in: mpt3sas raid_class binfmt_misc af_packet 8021q garp mrp stp llc xfs libcrc32c bonding iscsi_ibft iscsi_boot_sysfs msr ext4 crc16 jbd2 mbcache cdc_ether usbnet mii joydev hid_generic usbhid intel_rapl x86_pkg_temp_thermal intel_powerclamp coretemp crct10dif_pclmul crc32_pclmul ghash_clmulni_intel ipmi_ssif mgag200 i2c_algo_bit ttm ipmi_devintf drbg ixgbe drm_kms_helper vxlan ansi_cprng ip6_udp_tunnel drm aesni_intel udp_tunnel aes_x86_64 iTCO_wdt syscopyarea ptp xhci_pci lrw iTCO_vendor_support pps_core gf128mul ehci_pci glue_helper sysfillrect mdio pcspkr sb_edac ablk_helper cryptd ehci_hcd sysimgblt xhci_hcd fb_sys_fops edac_core mei_me lpc_ich ses usbcore enclosure dca mfd_core ipmi_si mei i2c_i801 scsi_transport_sas usb_common ipmi_msghandler shpchp fjes wmi processor button acpi_pad btrfs xor raid6_pq sd_mod crc32c_intel megaraid_sas sg dm_multipath dm_mod scsi_dh_rdac scsi_dh_emc scsi_dh_alua scsi_mod md_mod autofs4 [1072141.444146] Supported: Yes [1072141.444149] CPU: 21 PID: 1 Comm: systemd Not tainted 4.4.121-92.80-default #1 [1072141.444150] Hardware name: LENOVO Lenovo System x3650 M5 -[5462P4U]- -[5462P4U]-/01GR451, BIOS -[TCE136H-2.70]- 06/13/2018 [1072141.444151] task: ffff880191bd0040 ti: ffff880191bd4000 task.ti: ffff880191bd4000 [1072141.444153] RIP: 0010:[] [] update_classid_sock+0x29/0x40 [1072141.444157] RSP: 0018:ffff880191bd7d58 EFLAGS: 00000286 [1072141.444158] RAX: ffff883b177cb7c0 RBX: 0000000000000000 RCX: 0000000000000000 [1072141.444159] RDX: 00000000000009c7 RSI: ffff880191bd7d5c RDI: ffff8822e29bb200 [1072141.444160] RBP: ffff883a72230980 R08: 0000000000000101 R09: 0000000000000000 [1072141.444161] R10: 0000000000000008 R11: f000000000000000 R12: ffffffff815229d0 [1072141.444162] R13: 0000000000000000 R14: ffff881fd0a47ac0 R15: ffff880191bd7f28 [1072141.444163] FS: 00007f3e2f1eb8c0(0000) GS:ffff882000340000(0000) knlGS:0000000000000000 [1072141.444164] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [1072141.444165] CR2: 00007f3e2f200000 CR3: 0000001ffea4e000 CR4: 00000000001606f0 [1072141.444166] Stack: [1072141.444166] ffffffa800000246 00000000000009c7 ffffffff8121d583 ffff8818312a05c0 [1072141.444168] ffff8818312a1100 ffff880197c3b280 ffff881861422858 ffffffffffffffea [1072141.444170] ffffffff81522b1c ffffffff81d0ca20 ffff8817fa17b950 ffff883fdd8121e0 [1072141.444171] Call Trace: [1072141.444179] [] iterate_fd+0x53/0x80 [1072141.444182] [] write_classid+0x4c/0x80 [1072141.444187] [] cgroup_file_write+0x9b/0x100 [1072141.444193] [] kernfs_fop_write+0x11b/0x150 [1072141.444198] [] __vfs_write+0x26/0x100 [1072141.444201] [] vfs_write+0x9d/0x190 [1072141.444203] [] SyS_write+0x42/0xa0 [1072141.444207] [] entry_SYSCALL_64_fastpath+0x1e/0xca [1072141.445490] DWARF2 unwinder stuck at entry_SYSCALL_64_fastpath+0x1e/0xca If a cgroup has many tasks with many open file descriptors then we would end up in a large loop without any rescheduling point throught the operation. Add cond_resched once per task. Signed-off-by: Michal Hocko Signed-off-by: Tejun Heo --- net/core/netclassid_cgroup.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c index 5e4f04004a49..7bf833598615 100644 --- a/net/core/netclassid_cgroup.c +++ b/net/core/netclassid_cgroup.c @@ -106,6 +106,7 @@ static int write_classid(struct cgroup_subsys_state *css, struct cftype *cft, iterate_fd(p->files, 0, update_classid_sock, (void *)(unsigned long)cs->classid); task_unlock(p); + cond_resched(); } css_task_iter_end(&it);