Grab mm lock before grabbing pt lock

planetA · gregkh · commit a879019f539c · 2025-03-13T12:47:15.000+01:00
[ Upstream commit 6d002348789bc16e9203e9818b7a3688787e3b29 ] Function xen_pin_page calls xen_pte_lock, which in turn grab page table lock (ptlock). When locking, xen_pte_lock expect mm->page_table_lock to be held before grabbing ptlock, but this does not happen when pinning is caused by xen_mm_pin_all. This commit addresses lockdep warning below, which shows up when suspending a Xen VM. [ 3680.658422] Freezing user space processes [ 3680.660156] Freezing user space processes completed (elapsed 0.001 seconds) [ 3680.660182] OOM killer disabled. [ 3680.660192] Freezing remaining freezable tasks [ 3680.661485] Freezing remaining freezable tasks completed (elapsed 0.001 seconds) [ 3680.685254] [ 3680.685265] ================================== [ 3680.685269] WARNING: Nested lock was not taken [ 3680.685274] 6.12.0+ altera-fpga#16 Tainted: G W [ 3680.685279] ---------------------------------- [ 3680.685283] migration/0/19 is trying to lock: [ 3680.685288] ffff88800bac33c0 (ptlock_ptr(ptdesc)altera-fpga#2){+.+.}-{3:3}, at: xen_pin_page+0x175/0x1d0 [ 3680.685303] [ 3680.685303] but this task is not holding: [ 3680.685308] init_mm.page_table_lock [ 3680.685311] [ 3680.685311] stack backtrace: [ 3680.685316] CPU: 0 UID: 0 PID: 19 Comm: migration/0 Tainted: G W 6.12.0+ altera-fpga#16 [ 3680.685324] Tainted: [W]=WARN [ 3680.685328] Stopper: multi_cpu_stop+0x0/0x120 <- __stop_cpus.constprop.0+0x8c/0xd0 [ 3680.685339] Call Trace: [ 3680.685344] <TASK> [ 3680.685347] dump_stack_lvl+0x77/0xb0 [ 3680.685356] __lock_acquire+0x917/0x2310 [ 3680.685364] lock_acquire+0xce/0x2c0 [ 3680.685369] ? xen_pin_page+0x175/0x1d0 [ 3680.685373] _raw_spin_lock_nest_lock+0x2f/0x70 [ 3680.685381] ? xen_pin_page+0x175/0x1d0 [ 3680.685386] xen_pin_page+0x175/0x1d0 [ 3680.685390] ? __pfx_xen_pin_page+0x10/0x10 [ 3680.685394] __xen_pgd_walk+0x233/0x2c0 [ 3680.685401] ? stop_one_cpu+0x91/0x100 [ 3680.685405] __xen_pgd_pin+0x5d/0x250 [ 3680.685410] xen_mm_pin_all+0x70/0xa0 [ 3680.685415] xen_pv_pre_suspend+0xf/0x280 [ 3680.685420] xen_suspend+0x57/0x1a0 [ 3680.685428] multi_cpu_stop+0x6b/0x120 [ 3680.685432] ? update_cpumasks_hier+0x7c/0xa60 [ 3680.685439] ? __pfx_multi_cpu_stop+0x10/0x10 [ 3680.685443] cpu_stopper_thread+0x8c/0x140 [ 3680.685448] ? smpboot_thread_fn+0x20/0x1f0 [ 3680.685454] ? __pfx_smpboot_thread_fn+0x10/0x10 [ 3680.685458] smpboot_thread_fn+0xed/0x1f0 [ 3680.685462] kthread+0xde/0x110 [ 3680.685467] ? __pfx_kthread+0x10/0x10 [ 3680.685471] ret_from_fork+0x2f/0x50 [ 3680.685478] ? __pfx_kthread+0x10/0x10 [ 3680.685482] ret_from_fork_asm+0x1a/0x30 [ 3680.685489] </TASK> [ 3680.685491] [ 3680.685491] other info that might help us debug this: [ 3680.685497] 1 lock held by migration/0/19: [ 3680.685500] #0: ffffffff8284df38 (pgd_lock){+.+.}-{3:3}, at: xen_mm_pin_all+0x14/0xa0 [ 3680.685512] [ 3680.685512] stack backtrace: [ 3680.685518] CPU: 0 UID: 0 PID: 19 Comm: migration/0 Tainted: G W 6.12.0+ altera-fpga#16 [ 3680.685528] Tainted: [W]=WARN [ 3680.685531] Stopper: multi_cpu_stop+0x0/0x120 <- __stop_cpus.constprop.0+0x8c/0xd0 [ 3680.685538] Call Trace: [ 3680.685541] <TASK> [ 3680.685544] dump_stack_lvl+0x77/0xb0 [ 3680.685549] __lock_acquire+0x93c/0x2310 [ 3680.685554] lock_acquire+0xce/0x2c0 [ 3680.685558] ? xen_pin_page+0x175/0x1d0 [ 3680.685562] _raw_spin_lock_nest_lock+0x2f/0x70 [ 3680.685568] ? xen_pin_page+0x175/0x1d0 [ 3680.685572] xen_pin_page+0x175/0x1d0 [ 3680.685578] ? __pfx_xen_pin_page+0x10/0x10 [ 3680.685582] __xen_pgd_walk+0x233/0x2c0 [ 3680.685588] ? stop_one_cpu+0x91/0x100 [ 3680.685592] __xen_pgd_pin+0x5d/0x250 [ 3680.685596] xen_mm_pin_all+0x70/0xa0 [ 3680.685600] xen_pv_pre_suspend+0xf/0x280 [ 3680.685607] xen_suspend+0x57/0x1a0 [ 3680.685611] multi_cpu_stop+0x6b/0x120 [ 3680.685615] ? update_cpumasks_hier+0x7c/0xa60 [ 3680.685620] ? __pfx_multi_cpu_stop+0x10/0x10 [ 3680.685625] cpu_stopper_thread+0x8c/0x140 [ 3680.685629] ? smpboot_thread_fn+0x20/0x1f0 [ 3680.685634] ? __pfx_smpboot_thread_fn+0x10/0x10 [ 3680.685638] smpboot_thread_fn+0xed/0x1f0 [ 3680.685642] kthread+0xde/0x110 [ 3680.685645] ? __pfx_kthread+0x10/0x10 [ 3680.685649] ret_from_fork+0x2f/0x50 [ 3680.685654] ? __pfx_kthread+0x10/0x10 [ 3680.685657] ret_from_fork_asm+0x1a/0x30 [ 3680.685662] </TASK> [ 3680.685267] xen:grant_table: Grant tables using version 1 layout [ 3680.685921] OOM killer enabled. [ 3680.685934] Restarting tasks ... done. Signed-off-by: Maksym Planeta <maksym@exostellar.io> Reviewed-by: Juergen Gross <jgross@suse.com> Message-ID: <20241204103516.3309112-1-maksym@exostellar.io> Signed-off-by: Juergen Gross <jgross@suse.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
@@ -807,6 +807,7 @@ void xen_mm_pin_all(void)
 {
 	struct page *page;
 
+	spin_lock(&init_mm.page_table_lock);
 	spin_lock(&pgd_lock);
 
 	list_for_each_entry(page, &pgd_list, lru) {
@@ -817,6 +818,7 @@ void xen_mm_pin_all(void)
 	}
 
 	spin_unlock(&pgd_lock);
+	spin_unlock(&init_mm.page_table_lock);
 }
 
 static void __init xen_mark_pinned(struct mm_struct *mm, struct page *page,
@@ -914,6 +916,7 @@ void xen_mm_unpin_all(void)
 {
 	struct page *page;
 
+	spin_lock(&init_mm.page_table_lock);
 	spin_lock(&pgd_lock);
 
 	list_for_each_entry(page, &pgd_list, lru) {
@@ -925,6 +928,7 @@ void xen_mm_unpin_all(void)
 	}
 
 	spin_unlock(&pgd_lock);
+	spin_unlock(&init_mm.page_table_lock);
 }
 
 static void xen_activate_mm(struct mm_struct *prev, struct mm_struct *next)

Original file line number	Diff line number	Diff line change
`@@ -807,6 +807,7 @@ void xen_mm_pin_all(void)`
`807`	`807`	`{`
`808`	`808`	`struct page *page;`
`809`	`809`
	`810`	`+ spin_lock(&init_mm.page_table_lock);`
`810`	`811`	`spin_lock(&pgd_lock);`
`811`	`812`
`812`	`813`	`list_for_each_entry(page, &pgd_list, lru) {`
`@@ -817,6 +818,7 @@ void xen_mm_pin_all(void)`
`817`	`818`	`}`
`818`	`819`
`819`	`820`	`spin_unlock(&pgd_lock);`
	`821`	`+ spin_unlock(&init_mm.page_table_lock);`
`820`	`822`	`}`
`821`	`823`
`822`	`824`	`static void __init xen_mark_pinned(struct mm_struct mm, struct page page,`
`@@ -914,6 +916,7 @@ void xen_mm_unpin_all(void)`
`914`	`916`	`{`
`915`	`917`	`struct page *page;`
`916`	`918`
	`919`	`+ spin_lock(&init_mm.page_table_lock);`
`917`	`920`	`spin_lock(&pgd_lock);`
`918`	`921`
`919`	`922`	`list_for_each_entry(page, &pgd_list, lru) {`
`@@ -925,6 +928,7 @@ void xen_mm_unpin_all(void)`
`925`	`928`	`}`
`926`	`929`
`927`	`930`	`spin_unlock(&pgd_lock);`
	`931`	`+ spin_unlock(&init_mm.page_table_lock);`
`928`	`932`	`}`
`929`	`933`
`930`	`934`	`static void xen_activate_mm(struct mm_struct prev, struct mm_struct next)`