A softlockup occurs in scan free swap slot under huge memory pressure. The test scenario is: 64 CPU cores, 64GB memory, and 28 zram devices, the disksize of each zram device is 50MB. LATENCY_LIMIT is used to prevent softlockups in scan_swap_map_slots(), but the real loop number would more than LATENCY_LIMIT because of "goto checks and goto scan" repeatly without decreasing latency limit. In order to fix it, decrease latency_ration in advance. There is also a suspicious place that will cause softlockups in get_swap_pages(). In this function, the "goto start_over" may result in continuous scanning of the swap partition. If there is no cond_sched in scan_swap_map_slots(), it would cause a softlockup (I am not sure about this). WARN: soft lockup - CPU#11 stuck for 11s! [kswapd0:466] CPU: 11 PID: 466 Comm: kswapd@ Kdump: loaded Tainted: G dump backtrace+0x0/0x1le4 show stack+0x20/@x2c dump_stack+0xd8/0x140 watchdog print_info+0x48/0x54 watchdog_process_before_softlockup+0x98/0xa0 watchdog_timer_fn+0xlac/0x2d0 hrtimer_rum_queues+0xb0/0x130 hrtimer_interrupt+0x13c/0x3c0 arch_timer_handler_virt+0x3c/0x50 handLe_percpu_devid_irq+0x90/0x1f4 handle domain irq+0x84/0x100 gic_handle_irq+0x88/0x2b0 e11 ira+0xhB/Bx140 scan_swap_map_slots+0x678/0x890 get_swap_pages+0x29c/0x440 get_swap_page+0x120/0x2e0 add_to_swap+UX2U/0XyC shrink_page_list+0x5d0/0x152c shrink_inactive_list+0xl6c/Bx500 shrink_lruvec+0x270/0x304 WARN: soft lockup - CPU#32 stuck for 11s! [stress-ng:309915] watchdog_timer_fn+0x1ac/0x2d0 __run_hrtimer+0x98/0x2a0 __hrtimer_run_queues+0xb0/0x130 hrtimer_interrupt+0x13c/0x3c0 arch_timer_handler_virt+0x3c/0x50 handle_percpu_devid_irq+0x90/0x1f4 __handle_domain_irq+0x84/0x100 gic_handle_irq+0x88/0x2b0 el1_irq+0xb8/0x140 get_swap_pages+0x1e8/0x440 get_swap_page+0x1c8/0x2e0 add_to_swap+0x20/0x9c shrink_page_list+0x5d0/0x152c reclaim_pages+0x160/0x310 madvise_cold_or_pageout_pte_range+0x7bc/0xe3c walk_pmd_range.isra.0+0xac/0x22c walk_pud_range+0xfc/0x1c0 walk_pgd_range+0x158/0x1b0 __walk_page_range+0x64/0x100 walk_page_range+0x104/0x150
Unified · Split
| @@ -973,23 +973,23 @@ done: · 972 unmodified lines | |||
| 973 | scan: | 973 | scan: |
| 974 | spin_unlock(&si->lock); | 974 | spin_unlock(&si->lock); |
| 975 | while (++offset <= READ_ONCE(si->highest_bit)) { | 975 | while (++offset <= READ_ONCE(si->highest_bit)) { |
| 976 | if (swap_offset_available_and_locked(si, offset)) | ||
| 977 | goto checks; | ||
| 978 | if (unlikely(--latency_ration < 0)) { | 976 | if (unlikely(--latency_ration < 0)) { |
| 979 | cond_resched(); | 977 | cond_resched(); |
| 980 | latency_ration = LATENCY_LIMIT; | 978 | latency_ration = LATENCY_LIMIT; |
| 981 | scanned_many = true; | 979 | scanned_many = true; |
| 982 | } | 980 | } |
| 981 | if (swap_offset_available_and_locked(si, offset)) | ||
| 982 | goto checks; | ||
| 983 | } | 983 | } |
| 984 | offset = si->lowest_bit; | 984 | offset = si->lowest_bit; |
| 985 | while (offset < scan_base) { | 985 | while (offset < scan_base) { |
| 986 | if (swap_offset_available_and_locked(si, offset)) | ||
| 987 | goto checks; | ||
| 988 | if (unlikely(--latency_ration < 0)) { | 986 | if (unlikely(--latency_ration < 0)) { |
| 989 | cond_resched(); | 987 | cond_resched(); |
| 990 | latency_ration = LATENCY_LIMIT; | 988 | latency_ration = LATENCY_LIMIT; |
| 991 | scanned_many = true; | 989 | scanned_many = true; |
| 992 | } | 990 | } |
| 991 | if (swap_offset_available_and_locked(si, offset)) | ||
| 992 | goto checks; | ||
| 993 | offset++; | 993 | offset++; |
| 994 | } | 994 | } |
| 995 | spin_lock(&si->lock); | 995 | spin_lock(&si->lock); |