From 1007843a91909a4995ee78a538f62d8665705b66 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Tue, 4 Apr 2023 23:31:58 +0900 Subject: [PATCH] mm/page_alloc: fix potential deadlock on zonelist_update_seq seqlock MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit syzbot is reporting circular locking dependency which involves zonelist_update_seq seqlock [1], for this lock is checked by memory allocation requests which do not need to be retried. One deadlock scenario is kmalloc(GFP_ATOMIC) from an interrupt handler. CPU0 ---- __build_all_zonelists() { write_seqlock(&zonelist_update_seq); // makes zonelist_update_seq.seqcount odd // e.g. timer interrupt handler runs at this moment some_timer_func() { kmalloc(GFP_ATOMIC) { __alloc_pages_slowpath() { read_seqbegin(&zonelist_update_seq) { // spins forever because zonelist_update_seq.seqcount is odd } } } } // e.g. timer interrupt handler finishes write_sequnlock(&zonelist_update_seq); // makes zonelist_update_seq.seqcount even } This deadlock scenario can be easily eliminated by not calling read_seqbegin(&zonelist_update_seq) from !__GFP_DIRECT_RECLAIM allocation requests, for retry is applicable to only __GFP_DIRECT_RECLAIM allocation requests. But Michal Hocko does not know whether we should go with this approach. Another deadlock scenario which syzbot is reporting is a race between kmalloc(GFP_ATOMIC) from tty_insert_flip_string_and_push_buffer() with port->lock held and printk() from __build_all_zonelists() with zonelist_update_seq held. CPU0 CPU1 ---- ---- pty_write() { tty_insert_flip_string_and_push_buffer() { __build_all_zonelists() { write_seqlock(&zonelist_update_seq); build_zonelists() { printk() { vprintk() { vprintk_default() { vprintk_emit() { console_unlock() { console_flush_all() { console_emit_next_record() { con->write() = serial8250_console_write() { spin_lock_irqsave(&port->lock, flags); tty_insert_flip_string() { tty_insert_flip_string_fixed_flag() { __tty_buffer_request_room() { tty_buffer_alloc() { kmalloc(GFP_ATOMIC | __GFP_NOWARN) { __alloc_pages_slowpath() { zonelist_iter_begin() { read_seqbegin(&zonelist_update_seq); // spins forever because zonelist_update_seq.seqcount is odd spin_lock_irqsave(&port->lock, flags); // spins forever because port->lock is held } } } } } } } } spin_unlock_irqrestore(&port->lock, flags); // message is printed to console spin_unlock_irqrestore(&port->lock, flags); } } } } } } } } } write_sequnlock(&zonelist_update_seq); } } } This deadlock scenario can be eliminated by preventing interrupt context from calling kmalloc(GFP_ATOMIC) and preventing printk() from calling console_flush_all() while zonelist_update_seq.seqcount is odd. Since Petr Mladek thinks that __build_all_zonelists() can become a candidate for deferring printk() [2], let's address this problem by disabling local interrupts in order to avoid kmalloc(GFP_ATOMIC) and disabling synchronous printk() in order to avoid console_flush_all() . As a side effect of minimizing duration of zonelist_update_seq.seqcount being odd by disabling synchronous printk(), latency at read_seqbegin(&zonelist_update_seq) for both !__GFP_DIRECT_RECLAIM and __GFP_DIRECT_RECLAIM allocation requests will be reduced. Although, from lockdep perspective, not calling read_seqbegin(&zonelist_update_seq) (i.e. do not record unnecessary locking dependency) from interrupt context is still preferable, even if we don't allow calling kmalloc(GFP_ATOMIC) inside write_seqlock(&zonelist_update_seq)/write_sequnlock(&zonelist_update_seq) section... Link: https://lkml.kernel.org/r/8796b95c-3da3-5885-fddd-6ef55f30e4d3@I-love.SAKURA.ne.jp Fixes: 3d36424b3b58 ("mm/page_alloc: fix race condition between build_all_zonelists and page allocation") Link: https://lkml.kernel.org/r/ZCrs+1cDqPWTDFNM@alley [2] Reported-by: syzbot Link: https://syzkaller.appspot.com/bug?extid=223c7461c58c58a4cb10 [1] Signed-off-by: Tetsuo Handa Acked-by: Michal Hocko Acked-by: Mel Gorman Cc: Petr Mladek Cc: David Hildenbrand Cc: Ilpo Järvinen Cc: John Ogness Cc: Patrick Daly Cc: Sergey Senozhatsky Cc: Steven Rostedt Cc: Signed-off-by: Andrew Morton --- mm/page_alloc.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 7136c36..e8b4f29 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6632,7 +6632,21 @@ static void __build_all_zonelists(void *data) int nid; int __maybe_unused cpu; pg_data_t *self = data; + unsigned long flags; + /* + * Explicitly disable this CPU's interrupts before taking seqlock + * to prevent any IRQ handler from calling into the page allocator + * (e.g. GFP_ATOMIC) that could hit zonelist_iter_begin and livelock. + */ + local_irq_save(flags); + /* + * Explicitly disable this CPU's synchronous printk() before taking + * seqlock to prevent any printk() from trying to hold port->lock, for + * tty_insert_flip_string_and_push_buffer() on other CPU might be + * calling kmalloc(GFP_ATOMIC | __GFP_NOWARN) with port->lock held. + */ + printk_deferred_enter(); write_seqlock(&zonelist_update_seq); #ifdef CONFIG_NUMA @@ -6671,6 +6685,8 @@ static void __build_all_zonelists(void *data) } write_sequnlock(&zonelist_update_seq); + printk_deferred_exit(); + local_irq_restore(flags); } static noinline void __init -- 2.7.4