mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-27 11:05:07 +07:00
a90e90b7d5
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:[<ffffffff815229f9>] [<ffffffff815229f9>] 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] [<ffffffff8121d583>] iterate_fd+0x53/0x80 [1072141.444182] [<ffffffff81522b1c>] write_classid+0x4c/0x80 [1072141.444187] [<ffffffff8111328b>] cgroup_file_write+0x9b/0x100 [1072141.444193] [<ffffffff81278bcb>] kernfs_fop_write+0x11b/0x150 [1072141.444198] [<ffffffff81201566>] __vfs_write+0x26/0x100 [1072141.444201] [<ffffffff81201bed>] vfs_write+0x9d/0x190 [1072141.444203] [<ffffffff812028c2>] SyS_write+0x42/0xa0 [1072141.444207] [<ffffffff815f58c3>] 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 <mhocko@suse.com> Signed-off-by: Tejun Heo <tj@kernel.org>
132 lines
3.0 KiB
C
132 lines
3.0 KiB
C
/*
|
|
* net/core/netclassid_cgroup.c Classid Cgroupfs Handling
|
|
*
|
|
* This program is free software; you can redistribute it and/or
|
|
* modify it under the terms of the GNU General Public License
|
|
* as published by the Free Software Foundation; either version
|
|
* 2 of the License, or (at your option) any later version.
|
|
*
|
|
* Authors: Thomas Graf <tgraf@suug.ch>
|
|
*/
|
|
|
|
#include <linux/slab.h>
|
|
#include <linux/cgroup.h>
|
|
#include <linux/fdtable.h>
|
|
#include <linux/sched/task.h>
|
|
|
|
#include <net/cls_cgroup.h>
|
|
#include <net/sock.h>
|
|
|
|
static inline struct cgroup_cls_state *css_cls_state(struct cgroup_subsys_state *css)
|
|
{
|
|
return css ? container_of(css, struct cgroup_cls_state, css) : NULL;
|
|
}
|
|
|
|
struct cgroup_cls_state *task_cls_state(struct task_struct *p)
|
|
{
|
|
return css_cls_state(task_css_check(p, net_cls_cgrp_id,
|
|
rcu_read_lock_bh_held()));
|
|
}
|
|
EXPORT_SYMBOL_GPL(task_cls_state);
|
|
|
|
static struct cgroup_subsys_state *
|
|
cgrp_css_alloc(struct cgroup_subsys_state *parent_css)
|
|
{
|
|
struct cgroup_cls_state *cs;
|
|
|
|
cs = kzalloc(sizeof(*cs), GFP_KERNEL);
|
|
if (!cs)
|
|
return ERR_PTR(-ENOMEM);
|
|
|
|
return &cs->css;
|
|
}
|
|
|
|
static int cgrp_css_online(struct cgroup_subsys_state *css)
|
|
{
|
|
struct cgroup_cls_state *cs = css_cls_state(css);
|
|
struct cgroup_cls_state *parent = css_cls_state(css->parent);
|
|
|
|
if (parent)
|
|
cs->classid = parent->classid;
|
|
|
|
return 0;
|
|
}
|
|
|
|
static void cgrp_css_free(struct cgroup_subsys_state *css)
|
|
{
|
|
kfree(css_cls_state(css));
|
|
}
|
|
|
|
static int update_classid_sock(const void *v, struct file *file, unsigned n)
|
|
{
|
|
int err;
|
|
struct socket *sock = sock_from_file(file, &err);
|
|
|
|
if (sock) {
|
|
spin_lock(&cgroup_sk_update_lock);
|
|
sock_cgroup_set_classid(&sock->sk->sk_cgrp_data,
|
|
(unsigned long)v);
|
|
spin_unlock(&cgroup_sk_update_lock);
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
static void cgrp_attach(struct cgroup_taskset *tset)
|
|
{
|
|
struct cgroup_subsys_state *css;
|
|
struct task_struct *p;
|
|
|
|
cgroup_taskset_for_each(p, css, tset) {
|
|
task_lock(p);
|
|
iterate_fd(p->files, 0, update_classid_sock,
|
|
(void *)(unsigned long)css_cls_state(css)->classid);
|
|
task_unlock(p);
|
|
}
|
|
}
|
|
|
|
static u64 read_classid(struct cgroup_subsys_state *css, struct cftype *cft)
|
|
{
|
|
return css_cls_state(css)->classid;
|
|
}
|
|
|
|
static int write_classid(struct cgroup_subsys_state *css, struct cftype *cft,
|
|
u64 value)
|
|
{
|
|
struct cgroup_cls_state *cs = css_cls_state(css);
|
|
struct css_task_iter it;
|
|
struct task_struct *p;
|
|
|
|
cgroup_sk_alloc_disable();
|
|
|
|
cs->classid = (u32)value;
|
|
|
|
css_task_iter_start(css, 0, &it);
|
|
while ((p = css_task_iter_next(&it))) {
|
|
task_lock(p);
|
|
iterate_fd(p->files, 0, update_classid_sock,
|
|
(void *)(unsigned long)cs->classid);
|
|
task_unlock(p);
|
|
cond_resched();
|
|
}
|
|
css_task_iter_end(&it);
|
|
|
|
return 0;
|
|
}
|
|
|
|
static struct cftype ss_files[] = {
|
|
{
|
|
.name = "classid",
|
|
.read_u64 = read_classid,
|
|
.write_u64 = write_classid,
|
|
},
|
|
{ } /* terminate */
|
|
};
|
|
|
|
struct cgroup_subsys net_cls_cgrp_subsys = {
|
|
.css_alloc = cgrp_css_alloc,
|
|
.css_online = cgrp_css_online,
|
|
.css_free = cgrp_css_free,
|
|
.attach = cgrp_attach,
|
|
.legacy_cftypes = ss_files,
|
|
};
|