Skip to content

Commit

Permalink
mm/vmalloc: combine all TLB flush operations of KASAN shadow virtual …
Browse files Browse the repository at this point in the history 
…address into one operation

When compiling kernel source 'make -j $(nproc)' with the up-and-running
KASAN-enabled kernel on a 256-core machine, the following soft lockup is
shown:

watchdog: BUG: soft lockup - CPU#28 stuck for 22s! [kworker/28:1:1760]
CPU: 28 PID: 1760 Comm: kworker/28:1 Kdump: loaded Not tainted 6.10.0-rc5 torvalds#95
Workqueue: events drain_vmap_area_work
RIP: 0010:smp_call_function_many_cond+0x1d8/0xbb0
Code: 38 c8 7c 08 84 c9 0f 85 49 08 00 00 8b 45 08 a8 01 74 2e 48 89 f1 49 89 f7 48 c1 e9 03 41 83 e7 07 4c 01 e9 41 83 c7 03 f3 90 <0f> b6 01 41 38 c7 7c 08 84 c0 0f 85 d4 06 00 00 8b 45 08 a8 01 75
RSP: 0018:ffffc9000cb3fb60 EFLAGS: 00000202
RAX: 0000000000000011 RBX: ffff8883bc4469c0 RCX: ffffed10776e9949
RDX: 0000000000000002 RSI: ffff8883bb74ca48 RDI: ffffffff8434dc50
RBP: ffff8883bb74ca40 R08: ffff888103585dc0 R09: ffff8884533a1800
R10: 0000000000000004 R11: ffffffffffffffff R12: ffffed1077888d39
R13: dffffc0000000000 R14: ffffed1077888d38 R15: 0000000000000003
FS:  0000000000000000(0000) GS:ffff8883bc400000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00005577b5c8d158 CR3: 0000000004850000 CR4: 0000000000350ef0
Call Trace:
 <IRQ>
 ? watchdog_timer_fn+0x2cd/0x390
 ? __pfx_watchdog_timer_fn+0x10/0x10
 ? __hrtimer_run_queues+0x300/0x6d0
 ? sched_clock_cpu+0x69/0x4e0
 ? __pfx___hrtimer_run_queues+0x10/0x10
 ? srso_return_thunk+0x5/0x5f
 ? ktime_get_update_offsets_now+0x7f/0x2a0
 ? srso_return_thunk+0x5/0x5f
 ? srso_return_thunk+0x5/0x5f
 ? hrtimer_interrupt+0x2ca/0x760
 ? __sysvec_apic_timer_interrupt+0x8c/0x2b0
 ? sysvec_apic_timer_interrupt+0x6a/0x90
 </IRQ>
 <TASK>
 ? asm_sysvec_apic_timer_interrupt+0x16/0x20
 ? smp_call_function_many_cond+0x1d8/0xbb0
 ? __pfx_do_kernel_range_flush+0x10/0x10
 on_each_cpu_cond_mask+0x20/0x40
 flush_tlb_kernel_range+0x19b/0x250
 ? srso_return_thunk+0x5/0x5f
 ? kasan_release_vmalloc+0xa7/0xc0
 purge_vmap_node+0x357/0x820
 ? __pfx_purge_vmap_node+0x10/0x10
 __purge_vmap_area_lazy+0x5b8/0xa10
 drain_vmap_area_work+0x21/0x30
 process_one_work+0x661/0x10b0
 worker_thread+0x844/0x10e0
 ? srso_return_thunk+0x5/0x5f
 ? __kthread_parkme+0x82/0x140
 ? __pfx_worker_thread+0x10/0x10
 kthread+0x2a5/0x370
 ? __pfx_kthread+0x10/0x10
 ret_from_fork+0x30/0x70
 ? __pfx_kthread+0x10/0x10
 ret_from_fork_asm+0x1a/0x30
 </TASK>

Debugging Analysis:

  1. The following ftrace log shows that the lockup CPU spends too much
     time iterating vmap_nodes and flushing TLB when purging vm_area
     structures. (Some info is trimmed).

     kworker: funcgraph_entry:              |  drain_vmap_area_work() {
     kworker: funcgraph_entry:              |   mutex_lock() {
     kworker: funcgraph_entry:  1.092 us    |     __cond_resched();
     kworker: funcgraph_exit:   3.306 us    |   }
     ...                                        ...
     kworker: funcgraph_entry:              |    flush_tlb_kernel_range() {
     ...                                          ...
     kworker: funcgraph_exit: # 7533.649 us |    }
     ...                                         ...
     kworker: funcgraph_entry:  2.344 us    |   mutex_unlock();
     kworker: funcgraph_exit: $ 23871554 us | }

     The drain_vmap_area_work() spends over 23 seconds.

     There are 2805 flush_tlb_kernel_range() calls in the ftrace log.
       * One is called in __purge_vmap_area_lazy().
       * Others are called by purge_vmap_node->kasan_release_vmalloc.
         purge_vmap_node() iteratively releases kasan vmalloc
         allocations and flushes TLB for each vmap_area.
           - [Rough calculation] Each flush_tlb_kernel_range() runs
             about 7.5ms.
               -- 2804 * 7.5ms = 21.03 seconds.
               -- That's why a soft lock is triggered.

  2. Extending the soft lockup time can work around the issue (For example,
     # echo 60 > /proc/sys/kernel/watchdog_thresh). This confirms the
     above-mentioned speculation: drain_vmap_area_work() spends too much
     time.

If we combine all TLB flush operations of the KASAN shadow virtual
address into one operation in the call path
'purge_vmap_node()->kasan_release_vmalloc()', the running time of
drain_vmap_area_work() can be saved greatly. The idea is from the
flush_tlb_kernel_range() call in __purge_vmap_area_lazy(). And, the
soft lockup won't be triggered.

Here is the test result based on 6.10:

[6.10 wo/ the patch]
  1. ftrace latency profiling (record a trace if the latency > 20s).
     echo 20000000 > /sys/kernel/debug/tracing/tracing_thresh
     echo drain_vmap_area_work > /sys/kernel/debug/tracing/set_graph_function
     echo function_graph > /sys/kernel/debug/tracing/current_tracer
     echo 1 > /sys/kernel/debug/tracing/tracing_on

  2. Run `make -j $(nproc)` to compile the kernel source

  3. Once the soft lockup is reproduced, check the ftrace log:
     cat /sys/kernel/debug/tracing/trace
        # tracer: function_graph
        #
        # CPU  DURATION                  FUNCTION CALLS
        # |     |   |                     |   |   |   |
          76) $ 50412985 us |    } /* __purge_vmap_area_lazy */
          76) $ 50412997 us |  } /* drain_vmap_area_work */
          76) $ 29165911 us |    } /* __purge_vmap_area_lazy */
          76) $ 29165926 us |  } /* drain_vmap_area_work */
          91) $ 53629423 us |    } /* __purge_vmap_area_lazy */
          91) $ 53629434 us |  } /* drain_vmap_area_work */
          91) $ 28121014 us |    } /* __purge_vmap_area_lazy */
          91) $ 28121026 us |  } /* drain_vmap_area_work */

[6.10 w/ the patch]
  1. Repeat step 1-2 in "[6.10 wo/ the patch]"

  2. The soft lockup is not triggered and ftrace log is empty.
     cat /sys/kernel/debug/tracing/trace
     # tracer: function_graph
     #
     # CPU  DURATION                  FUNCTION CALLS
     # |     |   |                     |   |   |   |

  3. Setting 'tracing_thresh' to 10/5 seconds does not get any ftrace
     log.

  4. Setting 'tracing_thresh' to 1 second gets ftrace log.
     cat /sys/kernel/debug/tracing/trace
     # tracer: function_graph
     #
     # CPU  DURATION                  FUNCTION CALLS
     # |     |   |                     |   |   |   |
       23) $ 1074942 us  |    } /* __purge_vmap_area_lazy */
       23) $ 1074950 us  |  } /* drain_vmap_area_work */

  The worst execution time of drain_vmap_area_work() is about 1 second.

Link: https://lore.kernel.org/lkml/ZqFlawuVnOMY2k3E@pc638.lan/
Link: https://lkml.kernel.org/r/20240726165246.31326-1-ahuang12@lenovo.com
Fixes: 282631c ("mm: vmalloc: remove global purge_vmap_area_root rb-tree")
Signed-off-by: Adrian Huang <ahuang12@lenovo.com>
Co-developed-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Tested-by: Jiwei Sun <sunjw10@lenovo.com>
Reviewed-by: Baoquan He <bhe@redhat.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Andrey Konovalov <andreyknvl@gmail.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
  • Loading branch information
@akpm00
Adrian Huang authored and akpm00 committed Sep 8, 2024
1 parent fe67ee5 commit e067280
Show file tree
Hide file tree
Showing 3 changed files with 45 additions and 15 deletions.
12 changes: 9 additions & 3 deletions include/linux/kasan.h
View file
Original file line number Diff line number Diff line change
Expand Up @@ -29,6 +29,9 @@ typedef unsigned int __bitwise kasan_vmalloc_flags_t;
#define KASAN_VMALLOC_VM_ALLOC ((__force kasan_vmalloc_flags_t)0x02u)
#define KASAN_VMALLOC_PROT_NORMAL ((__force kasan_vmalloc_flags_t)0x04u)

#define KASAN_VMALLOC_PAGE_RANGE 0x1 /* Apply exsiting page range */
#define KASAN_VMALLOC_TLB_FLUSH 0x2 /* TLB flush */

#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)

#include <linux/pgtable.h>
Expand Down Expand Up @@ -511,7 +514,8 @@ void kasan_populate_early_vm_area_shadow(void *start, unsigned long size);
int kasan_populate_vmalloc(unsigned long addr, unsigned long size);
void kasan_release_vmalloc(unsigned long start, unsigned long end,
unsigned long free_region_start,
unsigned long free_region_end);
unsigned long free_region_end,
unsigned long flags);

#else /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */

Expand All @@ -526,7 +530,8 @@ static inline int kasan_populate_vmalloc(unsigned long start,
static inline void kasan_release_vmalloc(unsigned long start,
unsigned long end,
unsigned long free_region_start,
unsigned long free_region_end) { }
unsigned long free_region_end,
unsigned long flags) { }

#endif /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */

Expand Down Expand Up @@ -561,7 +566,8 @@ static inline int kasan_populate_vmalloc(unsigned long start,
static inline void kasan_release_vmalloc(unsigned long start,
unsigned long end,
unsigned long free_region_start,
unsigned long free_region_end) { }
unsigned long free_region_end,
unsigned long flags) { }

static inline void *kasan_unpoison_vmalloc(const void *start,
unsigned long size,
Expand Down
14 changes: 10 additions & 4 deletions mm/kasan/shadow.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -489,7 +489,8 @@ static int kasan_depopulate_vmalloc_pte(pte_t *ptep, unsigned long addr,
*/
void kasan_release_vmalloc(unsigned long start, unsigned long end,
unsigned long free_region_start,
unsigned long free_region_end)
unsigned long free_region_end,
unsigned long flags)
{
void *shadow_start, *shadow_end;
unsigned long region_start, region_end;
Expand Down Expand Up @@ -522,12 +523,17 @@ void kasan_release_vmalloc(unsigned long start, unsigned long end,
__memset(shadow_start, KASAN_SHADOW_INIT, shadow_end - shadow_start);
return;
}
apply_to_existing_page_range(&init_mm,


if (flags & KASAN_VMALLOC_PAGE_RANGE)
apply_to_existing_page_range(&init_mm,
(unsigned long)shadow_start,
size, kasan_depopulate_vmalloc_pte,
NULL);
flush_tlb_kernel_range((unsigned long)shadow_start,
(unsigned long)shadow_end);

if (flags & KASAN_VMALLOC_TLB_FLUSH)
flush_tlb_kernel_range((unsigned long)shadow_start,
(unsigned long)shadow_end);
}
}

Expand Down
34 changes: 26 additions & 8 deletions mm/vmalloc.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -2187,6 +2187,25 @@ decay_va_pool_node(struct vmap_node *vn, bool full_decay)
reclaim_list_global(&decay_list);
}

static void
kasan_release_vmalloc_node(struct vmap_node *vn)
{
struct vmap_area *va;
unsigned long start, end;

start = list_first_entry(&vn->purge_list, struct vmap_area, list)->va_start;
end = list_last_entry(&vn->purge_list, struct vmap_area, list)->va_end;

list_for_each_entry(va, &vn->purge_list, list) {
if (is_vmalloc_or_module_addr((void *) va->va_start))
kasan_release_vmalloc(va->va_start, va->va_end,
va->va_start, va->va_end,
KASAN_VMALLOC_PAGE_RANGE);
}

kasan_release_vmalloc(start, end, start, end, KASAN_VMALLOC_TLB_FLUSH);
}

static void purge_vmap_node(struct work_struct *work)
{
struct vmap_node *vn = container_of(work,
Expand All @@ -2195,20 +2214,17 @@ static void purge_vmap_node(struct work_struct *work)
struct vmap_area *va, *n_va;
LIST_HEAD(local_list);

if (IS_ENABLED(CONFIG_KASAN_VMALLOC))
kasan_release_vmalloc_node(vn);

vn->nr_purged = 0;

list_for_each_entry_safe(va, n_va, &vn->purge_list, list) {
unsigned long nr = (va->va_end - va->va_start) >> PAGE_SHIFT;
unsigned long orig_start = va->va_start;
unsigned long orig_end = va->va_end;
unsigned int vn_id = decode_vn_id(va->flags);

list_del_init(&va->list);

if (is_vmalloc_or_module_addr((void *)orig_start))
kasan_release_vmalloc(orig_start, orig_end,
va->va_start, va->va_end);

nr_purged_pages += nr;
vn->nr_purged++;

Expand Down Expand Up @@ -4790,7 +4806,8 @@ struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets,
&free_vmap_area_list);
if (va)
kasan_release_vmalloc(orig_start, orig_end,
va->va_start, va->va_end);
va->va_start, va->va_end,
KASAN_VMALLOC_PAGE_RANGE | KASAN_VMALLOC_TLB_FLUSH);
vas[area] = NULL;
}

Expand Down Expand Up @@ -4840,7 +4857,8 @@ struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets,
&free_vmap_area_list);
if (va)
kasan_release_vmalloc(orig_start, orig_end,
va->va_start, va->va_end);
va->va_start, va->va_end,
KASAN_VMALLOC_PAGE_RANGE | KASAN_VMALLOC_TLB_FLUSH);
vas[area] = NULL;
kfree(vms[area]);
}
Expand Down

0 comments on commit e067280

Please sign in to comment.