diff options
| author | Mel Gorman <mgorman@techsingularity.net> | 2022-11-08 15:27:03 +0000 |
|---|---|---|
| committer | Mel Gorman <mgorman@techsingularity.net> | 2022-11-10 12:18:45 +0000 |
| commit | c8ac8b6a6170615acaf9ffc6ceed2aa17f1a52d7 (patch) | |
| tree | 959394ff0260a96049de1205d3d9d997b03ca92b | |
| parent | 30a0b95b1335e12efef89dd78518ed3e4a71a763 (diff) | |
| download | linux-arch-fpregsclone-v2r1.tar.gz | |
x86: Drop fpregs lock before inheriting FPU permissionsarch-fpregsclone-v2r1
Mike Galbraith reported the following against an old fork of preempt-rt
but the same issue also applies to the current preempt-rt tree.
BUG: sleeping function called from invalid context at kernel/locking/spinlock_rt.c:46
in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 1, name: systemd
preempt_count: 1, expected: 0
RCU nest depth: 0, expected: 0
Preemption disabled at:
fpu_clone+0xfa/0x480
CPU: 6 PID: 1 Comm: systemd Tainted: G E (unreleased)
Call Trace:
<TASK>
dump_stack_lvl+0x45/0x5b
? fpu_clone+0xfa/0x480
__might_resched+0x165/0x200
rt_spin_lock+0x2d/0x70
fpu_clone+0x32a/0x480
? copy_thread+0xef/0x270
? copy_process+0xd2c/0x1c00
? shmem_alloc_inode+0x16/0x30
? kmem_cache_alloc+0x120/0x2a0
? kernel_clone+0x9b/0x460
? __do_sys_clone+0x72/0xa0
? do_syscall_64+0x58/0x80
? __x64_sys_rt_sigprocmask+0x93/0xd0
? syscall_exit_to_user_mode+0x18/0x40
? do_syscall_64+0x67/0x80
? syscall_exit_to_user_mode+0x18/0x40
? do_syscall_64+0x67/0x80
? syscall_exit_to_user_mode+0x18/0x40
? do_syscall_64+0x67/0x80
? exc_page_fault+0x6a/0x190
? entry_SYSCALL_64_after_hwframe+0x61/0xcb
</TASK>
The splat comes from fpu_inherit_perms() being called under fpregs_lock(),
and us reaching the spin_lock_irq() therein due to fpu_state_size_dynamic()
returning true despite static key __fpu_state_size_dynamic having never
been enabled.
Mike's assessment looks correct. fpregs_lock on PREEMPT_RT disables
preemption and the spin_lock_irq() in fpu_inherit_perms is unsafe. This
problem exists since commit 9e798e9aa14c ("x86/fpu: Prepare fpu_clone() for
dynamically enabled features"). Even though the original bug report should
not have enabled the paths, calling spin_lock_irq within a preempt_disable
section on PREEMPT_RT is problematic.
fpregs_lock is necessary when editing the FPU registers or a task's FP
state but it is not necessary for fpu_inherit_perms. The only write
of any FP state in fpu_inherit_perms is for the new child which is not
running yet and cannot context switch or be borrowed by a kernel thread
yet. Hence, fpregs_lock is not protecting anything in the new child until
clone() completes and can be dropped earlier. The siglock still needs to
be acquired by fpu_inherit_perms as the read of the parents permissions
has to be serialised.
Reported-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
| -rw-r--r-- | arch/x86/kernel/fpu/core.c | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index 3b28c5b25e12c..d00db56a88682 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -605,9 +605,9 @@ int fpu_clone(struct task_struct *dst, unsigned long clone_flags, bool minimal) if (test_thread_flag(TIF_NEED_FPU_LOAD)) fpregs_restore_userregs(); save_fpregs_to_fpstate(dst_fpu); + fpregs_unlock(); if (!(clone_flags & CLONE_THREAD)) fpu_inherit_perms(dst_fpu); - fpregs_unlock(); /* * Children never inherit PASID state. |