On Tue, Mar 12, 2024 at 12:47 AM Pasha Tatashin
<pasha.tatashin@xxxxxxxxxx> wrote:
>
> In preparation for the dynamic stacks, separate out the
> __vmalloc_node_range and vfree calls from the vmap based stack
> allocations. The dynamic stacks will use their own variants of these
> functions.
>
> Signed-off-by: Pasha Tatashin <pasha.tatashin@xxxxxxxxxx>
> ---
> kernel/fork.c | 53 ++++++++++++++++++++++++++++++---------------------
> 1 file changed, 31 insertions(+), 22 deletions(-)
>
> diff --git a/kernel/fork.c b/kernel/fork.c
> index 3004e6ce6c65..bbae5f705773 100644
> --- a/kernel/fork.c
> +++ b/kernel/fork.c
> @@ -204,6 +204,29 @@ static bool try_release_thread_stack_to_cache(struct vm_struct *vm_area)
> return false;
> }
>
> +static inline struct vm_struct *alloc_vmap_stack(int node)
> +{
> + void *stack;
> +
> + /*
> + * Allocated stacks are cached and later reused by new threads,
> + * so memcg accounting is performed manually on assigning/releasing
> + * stacks to tasks. Drop __GFP_ACCOUNT.
> + */
> + stack = __vmalloc_node_range(THREAD_SIZE, THREAD_ALIGN,
> + VMALLOC_START, VMALLOC_END,
> + THREADINFO_GFP & ~__GFP_ACCOUNT,
> + PAGE_KERNEL,
> + 0, node, __builtin_return_address(0));
> +
> + return (stack) ? find_vm_area(stack) : NULL;
> +}
> +
> +static inline void free_vmap_stack(struct vm_struct *vm_area)
> +{
> + vfree(vm_area->addr);
> +}
> +
> static void thread_stack_free_rcu(struct rcu_head *rh)
> {
> struct vm_stack *vm_stack = container_of(rh, struct vm_stack, rcu);
> @@ -212,7 +235,7 @@ static void thread_stack_free_rcu(struct rcu_head *rh)
> if (try_release_thread_stack_to_cache(vm_stack->stack_vm_area))
> return;
>
> - vfree(vm_area->addr);
> + free_vmap_stack(vm_area);
> }
I've discovered that the function free_vmap_stack() can trigger a warning.
It appears that free_vmap_stack() should handle interrupt context and
task context separately as vfree().
[root@JeffXie ]# poweroff
[root@JeffXie ]# umount: devtmpfs busy - remounted read-only
[ 93.036872] EXT4-fs (vda): re-mounted
2e1f057b-471f-4c08-a7b8-611457b221f2 ro. Quota mode: none.
The system is going down NOW!
Sent SIGTERM to all processes
Sent SIGKILL to all processes
Requesting system poweroff
[ 94.043540] ------------[ cut here ]------------
[ 94.043977] WARNING: CPU: 0 PID: 0 at kernel/smp.c:786
smp_call_function_many_cond+0x4e5/0x550
[ 94.044744] Modules linked in:
[ 94.045024] CPU: 0 PID: 0 Comm: swapper/0 Not tainted
6.8.0-00014-g82270db6e1f0 #91
[ 94.045697] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009),
BIOS 1.15.0-1 04/01/2014
[ 94.046399] RIP: 0010:smp_call_function_many_cond+0x4e5/0x550
[ 94.046914] Code: 48 8b 78 08 48 c7 c1 a0 84 16 81 4c 89 f6 e8 22
11 f6 ff 65 ff 0d 23 38 ec 7e 0f 85 a1 fc ff ff 0f 1f 44 00 00 e9 97
fc ff ff <0f> 0b e9 61
[ 94.048509] RSP: 0018:ffffc90000003e48 EFLAGS: 00010206
[ 94.048965] RAX: ffffffff82cb3fd0 RBX: ffff88811862cbc0 RCX: 0000000000000003
[ 94.049598] RDX: 0000000000000100 RSI: 0000000000000000 RDI: 0000000000000000
[ 94.050226] RBP: ffff8881052c5090 R08: 0000000000000000 R09: 0000000000000001
[ 94.050861] R10: ffffffff82a060c0 R11: 0000000000008847 R12: ffff888102eb3500
[ 94.051480] R13: ffff88811862b800 R14: ffff88811862cc38 R15: 0000000000000000
[ 94.052109] FS: 0000000000000000(0000) GS:ffff888118600000(0000)
knlGS:0000000000000000
[ 94.052812] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 94.053318] CR2: 00000000004759e0 CR3: 0000000002a2e000 CR4: 0000000000750ef0
[ 94.053955] PKRU: 55555554
[ 94.054203] Call Trace:
[ 94.054433] <IRQ>
[ 94.054632] ? __warn+0x84/0x140
[ 94.054925] ? smp_call_function_many_cond+0x4e5/0x550
[ 94.055362] ? report_bug+0x199/0x1b0
[ 94.055697] ? handle_bug+0x3c/0x70
[ 94.056010] ? exc_invalid_op+0x18/0x70
[ 94.056350] ? asm_exc_invalid_op+0x1a/0x20
[ 94.056728] ? smp_call_function_many_cond+0x4e5/0x550
[ 94.057179] ? __pfx_do_kernel_range_flush+0x10/0x10
[ 94.057622] on_each_cpu_cond_mask+0x24/0x40
[ 94.057999] flush_tlb_kernel_range+0x98/0xb0
[ 94.058390] free_unmap_vmap_area+0x2d/0x40
[ 94.058768] remove_vm_area+0x3a/0x70
[ 94.059094] free_vmap_stack+0x15/0x60
[ 94.059427] rcu_core+0x2bf/0x980
[ 94.059735] ? rcu_core+0x244/0x980
[ 94.060046] ? kvm_clock_get_cycles+0x18/0x30
[ 94.060431] __do_softirq+0xc2/0x292
[ 94.060760] irq_exit_rcu+0x6a/0x90
[ 94.061074] sysvec_apic_timer_interrupt+0x6e/0x90
[ 94.061507] </IRQ>
[ 94.061704] <TASK>
[ 94.061903] asm_sysvec_apic_timer_interrupt+0x1a/0x20
[ 94.062367] RIP: 0010:default_idle+0xf/0x20
[ 94.062746] Code: 4c 01 c7 4c 29 c2 e9 72 ff ff ff 90 90 90 90 90
90 90 90 90 90 90 90 90 90 90 90 f3 0f 1e fa eb 07 0f 00 2d 33 b4 2a
00 fb f4 <fa> c3 cc c0
[ 94.064342] RSP: 0018:ffffffff82a03e70 EFLAGS: 00000212
[ 94.064805] RAX: ffff888118628608 RBX: ffffffff82a0c980 RCX: 0000000000000000
[ 94.065429] RDX: 4000000000000000 RSI: ffffffff82725be8 RDI: 000000000000a14c
[ 94.066066] RBP: 0000000000000000 R08: 000000000000a14c R09: 0000000000000001
[ 94.066705] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000
[ 94.067311] R13: 0000000000000000 R14: ffffffff82a0c030 R15: 00000000000000ac
[ 94.067936] default_idle_call+0x2c/0xd0
[ 94.068284] do_idle+0x1ce/0x210
[ 94.068584] cpu_startup_entry+0x2a/0x30
[ 94.068931] rest_init+0xc5/0xd0
[ 94.069224] arch_call_rest_init+0xe/0x30
[ 94.069597] start_kernel+0x58e/0x8d0
[ 94.069929] x86_64_start_reservations+0x18/0x30
[ 94.070353] x86_64_start_kernel+0xc6/0xe0
[ 94.070725] secondary_startup_64_no_verify+0x16d/0x17b
[ 94.071189] </TASK>
[ 94.071392] ---[ end trace 0000000000000000 ]---
[ 95.040718] e1000e: EEE TX LPI TIMER: 00000000
[ 95.055005] ACPI: PM: Preparing to enter system sleep state S5
[ 95.055619] reboot: Power down
./scripts/faddr2line ./vmlinux smp_call_function_many_cond+0x4e5/0x550
smp_call_function_many_cond+0x4e5/0x550:
smp_call_function_many_cond at kernel/smp.c:786 (discriminator 1)
756 static void smp_call_function_many_cond(const struct cpumask *mask,
757 smp_call_func_t func, void *info,
758 unsigned int scf_flags,
759 smp_cond_func_t cond_func)
[...]
781 * When @wait we can deadlock when we interrupt between
llist_add() and
782 * arch_send_call_function_ipi*(); when !@wait we can
deadlock due to
783 * csd_lock() on because the interrupt context uses the same csd
784 * storage.
785 */
786 WARN_ON_ONCE(!in_task());
// <<< warning here
[...]
--
Thanks,
JeffXie
