The patch titled Subject: mm: fix null-ptr-deref in kswapd_is_running() has been added to the -mm mm-unstable branch. Its filename is mm-fix-null-ptr-deref-in-kswapd_is_running.patch This patch will shortly appear at https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-fix-null-ptr-deref-in-kswapd_is_running.patch This patch will later appear in the mm-unstable branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next via the mm-everything branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there every 2-3 working days ------------------------------------------------------ From: Kefeng Wang <wangkefeng.wang@xxxxxxxxxx> Subject: mm: fix null-ptr-deref in kswapd_is_running() Date: Sat, 27 Aug 2022 19:19:59 +0800 kswapd_run/stop() will set pgdat->kswapd to NULL, which could race with kswapd_is_running() in kcompactd(), kswapd_run/stop() kcompactd() kswapd_is_running() pgdat->kswapd // error or nomal ptr verify pgdat->kswapd // load non-NULL pgdat->kswapd pgdat->kswapd = NULL task_is_running(pgdat->kswapd) // Null pointer derefence KASAN reports the null-ptr-deref shown below, vmscan: Failed to start kswapd on node 0 ... BUG: KASAN: null-ptr-deref in kcompactd+0x440/0x504 Read of size 8 at addr 0000000000000024 by task kcompactd0/37 CPU: 0 PID: 37 Comm: kcompactd0 Kdump: loaded Tainted: G OE 5.10.60 #1 Hardware name: QEMU KVM Virtual Machine, BIOS 0.0.0 02/06/2015 Call trace: dump_backtrace+0x0/0x394 show_stack+0x34/0x4c dump_stack+0x158/0x1e4 __kasan_report+0x138/0x140 kasan_report+0x44/0xdc __asan_load8+0x94/0xd0 kcompactd+0x440/0x504 kthread+0x1a4/0x1f0 ret_from_fork+0x10/0x18 At present kswapd/kcompactd_run() and kswapd/kcompactd_stop() are protected by mem_hotplug_begin/done(), but without kcompactd(). There is no need to involve memory hotplug lock in kcompactd(), so let's add a new mutex to protect pgdat->kswapd accesses. Also, because the kcompactd task will check the state of kswapd task, it's better to call kcompactd_stop() before kswapd_stop() to reduce lock conflicts. Link: https://lkml.kernel.org/r/20220827111959.186838-1-wangkefeng.wang@xxxxxxxxxx Signed-off-by: Kefeng Wang <wangkefeng.wang@xxxxxxxxxx> Cc: David Hildenbrand <david@xxxxxxxxxx> Cc: Muchun Song <muchun.song@xxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- include/linux/memory_hotplug.h | 19 +++++++++++++++++++ include/linux/mmzone.h | 6 ++++-- mm/compaction.c | 8 +++++++- mm/memory_hotplug.c | 2 +- mm/page_alloc.c | 1 + mm/vmscan.c | 27 ++++++++++++++++----------- 6 files changed, 48 insertions(+), 15 deletions(-) --- a/include/linux/memory_hotplug.h~mm-fix-null-ptr-deref-in-kswapd_is_running +++ a/include/linux/memory_hotplug.h @@ -215,6 +215,21 @@ void put_online_mems(void); void mem_hotplug_begin(void); void mem_hotplug_done(void); +static inline void pgdat_kswapd_lock(pg_data_t *pgdat) +{ + mutex_lock(&pgdat->kswapd_lock); +} + +static inline void pgdat_kswapd_unlock(pg_data_t *pgdat) +{ + mutex_unlock(&pgdat->kswapd_lock); +} + +static inline void pgdat_kswapd_lock_init(pg_data_t *pgdat) +{ + mutex_init(&pgdat->kswapd_lock); +} + #else /* ! CONFIG_MEMORY_HOTPLUG */ #define pfn_to_online_page(pfn) \ ({ \ @@ -251,6 +266,10 @@ static inline bool movable_node_is_enabl { return false; } + +static inline void pgdat_kswapd_lock(pg_data_t *pgdat) {} +static inline void pgdat_kswapd_unlock(pg_data_t *pgdat) {} +static inline void pgdat_kswapd_lock_init(pg_data_t *pgdat) {} #endif /* ! CONFIG_MEMORY_HOTPLUG */ /* --- a/include/linux/mmzone.h~mm-fix-null-ptr-deref-in-kswapd_is_running +++ a/include/linux/mmzone.h @@ -1151,8 +1151,10 @@ typedef struct pglist_data { atomic_t nr_writeback_throttled;/* nr of writeback-throttled tasks */ unsigned long nr_reclaim_start; /* nr pages written while throttled * when throttling started. */ - struct task_struct *kswapd; /* Protected by - mem_hotplug_begin/done() */ +#ifdef CONFIG_MEMORY_HOTPLUG + struct mutex kswapd_lock; +#endif + struct task_struct *kswapd; /* Protected by kswapd_lock */ int kswapd_order; enum zone_type kswapd_highest_zoneidx; --- a/mm/compaction.c~mm-fix-null-ptr-deref-in-kswapd_is_running +++ a/mm/compaction.c @@ -1982,7 +1982,13 @@ static inline bool is_via_compact_memory static bool kswapd_is_running(pg_data_t *pgdat) { - return pgdat->kswapd && task_is_running(pgdat->kswapd); + bool running; + + pgdat_kswapd_lock(pgdat); + running = pgdat->kswapd && task_is_running(pgdat->kswapd); + pgdat_kswapd_unlock(pgdat); + + return running; } /* --- a/mm/memory_hotplug.c~mm-fix-null-ptr-deref-in-kswapd_is_running +++ a/mm/memory_hotplug.c @@ -1940,8 +1940,8 @@ int __ref offline_pages(unsigned long st node_states_clear_node(node, &arg); if (arg.status_change_nid >= 0) { - kswapd_stop(node); kcompactd_stop(node); + kswapd_stop(node); } writeback_set_ratelimit(); --- a/mm/page_alloc.c~mm-fix-null-ptr-deref-in-kswapd_is_running +++ a/mm/page_alloc.c @@ -7676,6 +7676,7 @@ static void __meminit pgdat_init_interna int i; pgdat_resize_init(pgdat); + pgdat_kswapd_lock_init(pgdat); pgdat_init_split_queue(pgdat); pgdat_init_kcompactd(pgdat); --- a/mm/vmscan.c~mm-fix-null-ptr-deref-in-kswapd_is_running +++ a/mm/vmscan.c @@ -7425,16 +7425,17 @@ void kswapd_run(int nid) { pg_data_t *pgdat = NODE_DATA(nid); - if (pgdat->kswapd) - return; - - pgdat->kswapd = kthread_run(kswapd, pgdat, "kswapd%d", nid); - if (IS_ERR(pgdat->kswapd)) { - /* failure at boot is fatal */ - BUG_ON(system_state < SYSTEM_RUNNING); - pr_err("Failed to start kswapd on node %d\n", nid); - pgdat->kswapd = NULL; + pgdat_kswapd_lock(pgdat); + if (!pgdat->kswapd) { + pgdat->kswapd = kthread_run(kswapd, pgdat, "kswapd%d", nid); + if (IS_ERR(pgdat->kswapd)) { + /* failure at boot is fatal */ + BUG_ON(system_state < SYSTEM_RUNNING); + pr_err("Failed to start kswapd on node %d\n", nid); + pgdat->kswapd = NULL; + } } + pgdat_kswapd_unlock(pgdat); } /* @@ -7443,12 +7444,16 @@ void kswapd_run(int nid) */ void kswapd_stop(int nid) { - struct task_struct *kswapd = NODE_DATA(nid)->kswapd; + pg_data_t *pgdat = NODE_DATA(nid); + struct task_struct *kswapd; + pgdat_kswapd_lock(pgdat); + kswapd = pgdat->kswapd; if (kswapd) { kthread_stop(kswapd); - NODE_DATA(nid)->kswapd = NULL; + pgdat->kswapd = NULL; } + pgdat_kswapd_unlock(pgdat); } static int __init kswapd_init(void) _ Patches currently in -mm which might be from wangkefeng.wang@xxxxxxxxxx are mm-memory-failure-cleanup-try_to_split_thp_page.patch mm-add-warning-if-__vm_enough_memory-fails.patch mm-kill-find_min_pfn_with_active_regions.patch mm-memory-failure-kill-soft_offline_free_page.patch mm-memory-failure-kill-__soft_offline_page.patch mm-kill-is_memblock_offlined.patch mm-fix-null-ptr-deref-in-kswapd_is_running.patch kernel-exit-cleanup-release_thread.patch