From: Zhaoyang Huang <[email protected]>
Broken vbq->free reported on a v6.6 based system which is caused
by invalid vbq->lock protect over vbq->free in purge_fragmented_block.
This should be introduced by the Fixes below which ignored vbq->lock
matter.
Fixes: fc1e0d980037 ("mm/vmalloc: prevent stale TLBs in fully utilized blocks")
Signed-off-by: Zhaoyang Huang <[email protected]>
---
mm/vmalloc.c | 11 +++++++----
1 file changed, 7 insertions(+), 4 deletions(-)
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 22aa63f4ef63..112b50431725 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -2614,9 +2614,10 @@ static void free_vmap_block(struct vmap_block *vb)
}
static bool purge_fragmented_block(struct vmap_block *vb,
- struct vmap_block_queue *vbq, struct list_head *purge_list,
- bool force_purge)
+ struct list_head *purge_list, bool force_purge)
{
+ struct vmap_block_queue *vbq;
+
if (vb->free + vb->dirty != VMAP_BBMAP_BITS ||
vb->dirty == VMAP_BBMAP_BITS)
return false;
@@ -2625,6 +2626,8 @@ static bool purge_fragmented_block(struct vmap_block *vb,
if (!(force_purge || vb->free < VMAP_PURGE_THRESHOLD))
return false;
+ vbq = container_of(addr_to_vb_xa(vb->va->va_start),
+ struct vmap_block_queue, vmap_blocks);
/* prevent further allocs after releasing lock */
WRITE_ONCE(vb->free, 0);
/* prevent purging it again */
@@ -2664,7 +2667,7 @@ static void purge_fragmented_blocks(int cpu)
continue;
spin_lock(&vb->lock);
- purge_fragmented_block(vb, vbq, &purge, true);
+ purge_fragmented_block(vb, &purge, true);
spin_unlock(&vb->lock);
}
rcu_read_unlock();
@@ -2801,7 +2804,7 @@ static void _vm_unmap_aliases(unsigned long start, unsigned long end, int flush)
* not purgeable, check whether there is dirty
* space to be flushed.
*/
- if (!purge_fragmented_block(vb, vbq, &purge_list, false) &&
+ if (!purge_fragmented_block(vb, &purge_list, false) &&
vb->dirty_max && vb->dirty != VMAP_BBMAP_BITS) {
unsigned long va_start = vb->va->va_start;
unsigned long s, e;
--
2.25.1
loop Thomas
On Thu, May 30, 2024 at 10:52 AM zhaoyang.huang
<[email protected]> wrote:
>
> From: Zhaoyang Huang <[email protected]>
>
> Broken vbq->free reported on a v6.6 based system which is caused
> by invalid vbq->lock protect over vbq->free in purge_fragmented_block.
> This should be introduced by the Fixes below which ignored vbq->lock
> matter.
>
> Fixes: fc1e0d980037 ("mm/vmalloc: prevent stale TLBs in fully utilized blocks")
>
> Signed-off-by: Zhaoyang Huang <[email protected]>
> ---
> mm/vmalloc.c | 11 +++++++----
> 1 file changed, 7 insertions(+), 4 deletions(-)
>
> diff --git a/mm/vmalloc.c b/mm/vmalloc.c
> index 22aa63f4ef63..112b50431725 100644
> --- a/mm/vmalloc.c
> +++ b/mm/vmalloc.c
> @@ -2614,9 +2614,10 @@ static void free_vmap_block(struct vmap_block *vb)
> }
>
> static bool purge_fragmented_block(struct vmap_block *vb,
> - struct vmap_block_queue *vbq, struct list_head *purge_list,
> - bool force_purge)
> + struct list_head *purge_list, bool force_purge)
> {
> + struct vmap_block_queue *vbq;
> +
> if (vb->free + vb->dirty != VMAP_BBMAP_BITS ||
> vb->dirty == VMAP_BBMAP_BITS)
> return false;
> @@ -2625,6 +2626,8 @@ static bool purge_fragmented_block(struct vmap_block *vb,
> if (!(force_purge || vb->free < VMAP_PURGE_THRESHOLD))
> return false;
>
> + vbq = container_of(addr_to_vb_xa(vb->va->va_start),
> + struct vmap_block_queue, vmap_blocks);
> /* prevent further allocs after releasing lock */
> WRITE_ONCE(vb->free, 0);
> /* prevent purging it again */
> @@ -2664,7 +2667,7 @@ static void purge_fragmented_blocks(int cpu)
> continue;
>
> spin_lock(&vb->lock);
> - purge_fragmented_block(vb, vbq, &purge, true);
> + purge_fragmented_block(vb, &purge, true);
> spin_unlock(&vb->lock);
> }
> rcu_read_unlock();
> @@ -2801,7 +2804,7 @@ static void _vm_unmap_aliases(unsigned long start, unsigned long end, int flush)
> * not purgeable, check whether there is dirty
> * space to be flushed.
> */
> - if (!purge_fragmented_block(vb, vbq, &purge_list, false) &&
> + if (!purge_fragmented_block(vb, &purge_list, false) &&
> vb->dirty_max && vb->dirty != VMAP_BBMAP_BITS) {
> unsigned long va_start = vb->va->va_start;
> unsigned long s, e;
> --
> 2.25.1
>
On 05/30/24 at 10:51am, zhaoyang.huang wrote:
> From: Zhaoyang Huang <[email protected]>
>
> Broken vbq->free reported on a v6.6 based system which is caused
> by invalid vbq->lock protect over vbq->free in purge_fragmented_block.
> This should be introduced by the Fixes below which ignored vbq->lock
> matter.
It will be helpful to provide more details, what's the symptom of the
brekage, and in which case vbq->free is broken.
>
> Fixes: fc1e0d980037 ("mm/vmalloc: prevent stale TLBs in fully utilized blocks")
>
> Signed-off-by: Zhaoyang Huang <[email protected]>
> ---
> mm/vmalloc.c | 11 +++++++----
> 1 file changed, 7 insertions(+), 4 deletions(-)
>
> diff --git a/mm/vmalloc.c b/mm/vmalloc.c
> index 22aa63f4ef63..112b50431725 100644
> --- a/mm/vmalloc.c
> +++ b/mm/vmalloc.c
> @@ -2614,9 +2614,10 @@ static void free_vmap_block(struct vmap_block *vb)
> }
>
> static bool purge_fragmented_block(struct vmap_block *vb,
> - struct vmap_block_queue *vbq, struct list_head *purge_list,
> - bool force_purge)
> + struct list_head *purge_list, bool force_purge)
> {
> + struct vmap_block_queue *vbq;
> +
> if (vb->free + vb->dirty != VMAP_BBMAP_BITS ||
> vb->dirty == VMAP_BBMAP_BITS)
> return false;
> @@ -2625,6 +2626,8 @@ static bool purge_fragmented_block(struct vmap_block *vb,
> if (!(force_purge || vb->free < VMAP_PURGE_THRESHOLD))
> return false;
>
> + vbq = container_of(addr_to_vb_xa(vb->va->va_start),
> + struct vmap_block_queue, vmap_blocks);
> /* prevent further allocs after releasing lock */
> WRITE_ONCE(vb->free, 0);
> /* prevent purging it again */
> @@ -2664,7 +2667,7 @@ static void purge_fragmented_blocks(int cpu)
> continue;
>
> spin_lock(&vb->lock);
> - purge_fragmented_block(vb, vbq, &purge, true);
> + purge_fragmented_block(vb, &purge, true);
> spin_unlock(&vb->lock);
> }
> rcu_read_unlock();
> @@ -2801,7 +2804,7 @@ static void _vm_unmap_aliases(unsigned long start, unsigned long end, int flush)
> * not purgeable, check whether there is dirty
> * space to be flushed.
> */
> - if (!purge_fragmented_block(vb, vbq, &purge_list, false) &&
> + if (!purge_fragmented_block(vb, &purge_list, false) &&
> vb->dirty_max && vb->dirty != VMAP_BBMAP_BITS) {
> unsigned long va_start = vb->va->va_start;
> unsigned long s, e;
> --
> 2.25.1
>
>
On Thu, May 30, 2024 at 3:19 PM Baoquan He <[email protected]> wrote:
>
> On 05/30/24 at 10:51am, zhaoyang.huang wrote:
> > From: Zhaoyang Huang <[email protected]>
> >
> > Broken vbq->free reported on a v6.6 based system which is caused
> > by invalid vbq->lock protect over vbq->free in purge_fragmented_block.
> > This should be introduced by the Fixes below which ignored vbq->lock
> > matter.
>
> It will be helpful to provide more details, what's the symptom of the
> brekage, and in which case vbq->free is broken.
Vmalloc area runs out in our ARM64 system during an erofs test as
vm_map_ram failed[1]. We find that one vbq->free->next point to
vbq->free which makes list_for_each_entry_rcu can not iterate the list
and find the BUG.
[1]
PID: 1 TASK: ffffff80802b4e00 CPU: 6 COMMAND: "init"
#0 [ffffffc08006afe0] __switch_to at ffffffc08111d5cc
#1 [ffffffc08006b040] __schedule at ffffffc08111dde0
#2 [ffffffc08006b0a0] schedule at ffffffc08111e294
#3 [ffffffc08006b0d0] schedule_preempt_disabled at ffffffc08111e3f0
#4 [ffffffc08006b140] __mutex_lock at ffffffc08112068c
#5 [ffffffc08006b180] __mutex_lock_slowpath at ffffffc08111f8f8
#6 [ffffffc08006b1a0] mutex_lock at ffffffc08111f834
#7 [ffffffc08006b1d0] reclaim_and_purge_vmap_areas at ffffffc0803ebc3c
#8 [ffffffc08006b290] alloc_vmap_area at ffffffc0803e83fc
#9 [ffffffc08006b300] vm_map_ram at ffffffc0803e78c0
#10 [ffffffc08006b420] z_erofs_lz4_decompress at ffffffc0806a49b0
#11 [ffffffc08006b670] z_erofs_decompress_queue at ffffffc0806a8fd0
#12 [ffffffc08006b860] z_erofs_runqueue at ffffffc0806a8744
#13 [ffffffc08006b970] z_erofs_readahead at ffffffc0806a6cfc
#14 [ffffffc08006ba00] read_pages at ffffffc08037ed78
#15 [ffffffc08006ba70] page_cache_ra_unbounded at ffffffc08037eb58
#16 [ffffffc08006bb00] page_cache_ra_order at ffffffc08037f42c
#17 [ffffffc08006bbb0] do_sync_mmap_readahead at ffffffc080371d3c
#18 [ffffffc08006bc40] filemap_fault at ffffffc080371774
#19 [ffffffc08006bd60] handle_mm_fault at ffffffc0803cc118
#20 [ffffffc08006bdc0] do_page_fault at ffffffc08112a618
#21 [ffffffc08006be20] do_translation_fault at ffffffc08112a36c
#22 [ffffffc08006be30] do_mem_abort at ffffffc0800bfbf0
#23 [ffffffc08006be70] el0_ia at ffffffc08111583c
#24 [ffffffc08006bea0] el0t_64_sync_handler at ffffffc0811156a4
#25 [ffffffc08006bfe0] el0t_64_sync at ffffffc080091584
>
> >
> > Fixes: fc1e0d980037 ("mm/vmalloc: prevent stale TLBs in fully utilized blocks")
> >
> > Signed-off-by: Zhaoyang Huang <[email protected]>
> > ---
> > mm/vmalloc.c | 11 +++++++----
> > 1 file changed, 7 insertions(+), 4 deletions(-)
> >
> > diff --git a/mm/vmalloc.c b/mm/vmalloc.c
> > index 22aa63f4ef63..112b50431725 100644
> > --- a/mm/vmalloc.c
> > +++ b/mm/vmalloc.c
> > @@ -2614,9 +2614,10 @@ static void free_vmap_block(struct vmap_block *vb)
> > }
> >
> > static bool purge_fragmented_block(struct vmap_block *vb,
> > - struct vmap_block_queue *vbq, struct list_head *purge_list,
> > - bool force_purge)
> > + struct list_head *purge_list, bool force_purge)
> > {
> > + struct vmap_block_queue *vbq;
> > +
> > if (vb->free + vb->dirty != VMAP_BBMAP_BITS ||
> > vb->dirty == VMAP_BBMAP_BITS)
> > return false;
> > @@ -2625,6 +2626,8 @@ static bool purge_fragmented_block(struct vmap_block *vb,
> > if (!(force_purge || vb->free < VMAP_PURGE_THRESHOLD))
> > return false;
> >
> > + vbq = container_of(addr_to_vb_xa(vb->va->va_start),
> > + struct vmap_block_queue, vmap_blocks);
> > /* prevent further allocs after releasing lock */
> > WRITE_ONCE(vb->free, 0);
> > /* prevent purging it again */
> > @@ -2664,7 +2667,7 @@ static void purge_fragmented_blocks(int cpu)
> > continue;
> >
> > spin_lock(&vb->lock);
> > - purge_fragmented_block(vb, vbq, &purge, true);
> > + purge_fragmented_block(vb, &purge, true);
> > spin_unlock(&vb->lock);
> > }
> > rcu_read_unlock();
> > @@ -2801,7 +2804,7 @@ static void _vm_unmap_aliases(unsigned long start, unsigned long end, int flush)
> > * not purgeable, check whether there is dirty
> > * space to be flushed.
> > */
> > - if (!purge_fragmented_block(vb, vbq, &purge_list, false) &&
> > + if (!purge_fragmented_block(vb, &purge_list, false) &&
> > vb->dirty_max && vb->dirty != VMAP_BBMAP_BITS) {
> > unsigned long va_start = vb->va->va_start;
> > unsigned long s, e;
> > --
> > 2.25.1
> >
> >
>
On 05/30/24 at 03:35pm, Zhaoyang Huang wrote:
> On Thu, May 30, 2024 at 3:19 PM Baoquan He <[email protected]> wrote:
> >
> > On 05/30/24 at 10:51am, zhaoyang.huang wrote:
> > > From: Zhaoyang Huang <[email protected]>
> > >
> > > Broken vbq->free reported on a v6.6 based system which is caused
> > > by invalid vbq->lock protect over vbq->free in purge_fragmented_block.
> > > This should be introduced by the Fixes below which ignored vbq->lock
> > > matter.
> >
> > It will be helpful to provide more details, what's the symptom of the
> > brekage, and in which case vbq->free is broken.
> Vmalloc area runs out in our ARM64 system during an erofs test as
> vm_map_ram failed[1]. We find that one vbq->free->next point to
> vbq->free which makes list_for_each_entry_rcu can not iterate the list
> and find the BUG.
Thanks for these information which are very helpful and important.
They need be put in log for easier understanding. I am wondering
about the vbq->free list breakage by the run out vmalloc area, could
you say more about how it's caused? And do you think we need fix that
vbq->free list breakage either?
>
> [1]
> PID: 1 TASK: ffffff80802b4e00 CPU: 6 COMMAND: "init"
> #0 [ffffffc08006afe0] __switch_to at ffffffc08111d5cc
> #1 [ffffffc08006b040] __schedule at ffffffc08111dde0
> #2 [ffffffc08006b0a0] schedule at ffffffc08111e294
> #3 [ffffffc08006b0d0] schedule_preempt_disabled at ffffffc08111e3f0
> #4 [ffffffc08006b140] __mutex_lock at ffffffc08112068c
> #5 [ffffffc08006b180] __mutex_lock_slowpath at ffffffc08111f8f8
> #6 [ffffffc08006b1a0] mutex_lock at ffffffc08111f834
> #7 [ffffffc08006b1d0] reclaim_and_purge_vmap_areas at ffffffc0803ebc3c
> #8 [ffffffc08006b290] alloc_vmap_area at ffffffc0803e83fc
> #9 [ffffffc08006b300] vm_map_ram at ffffffc0803e78c0
> #10 [ffffffc08006b420] z_erofs_lz4_decompress at ffffffc0806a49b0
> #11 [ffffffc08006b670] z_erofs_decompress_queue at ffffffc0806a8fd0
> #12 [ffffffc08006b860] z_erofs_runqueue at ffffffc0806a8744
> #13 [ffffffc08006b970] z_erofs_readahead at ffffffc0806a6cfc
> #14 [ffffffc08006ba00] read_pages at ffffffc08037ed78
> #15 [ffffffc08006ba70] page_cache_ra_unbounded at ffffffc08037eb58
> #16 [ffffffc08006bb00] page_cache_ra_order at ffffffc08037f42c
> #17 [ffffffc08006bbb0] do_sync_mmap_readahead at ffffffc080371d3c
> #18 [ffffffc08006bc40] filemap_fault at ffffffc080371774
> #19 [ffffffc08006bd60] handle_mm_fault at ffffffc0803cc118
> #20 [ffffffc08006bdc0] do_page_fault at ffffffc08112a618
> #21 [ffffffc08006be20] do_translation_fault at ffffffc08112a36c
> #22 [ffffffc08006be30] do_mem_abort at ffffffc0800bfbf0
> #23 [ffffffc08006be70] el0_ia at ffffffc08111583c
> #24 [ffffffc08006bea0] el0t_64_sync_handler at ffffffc0811156a4
> #25 [ffffffc08006bfe0] el0t_64_sync at ffffffc080091584
>
>
> >
> > >
> > > Fixes: fc1e0d980037 ("mm/vmalloc: prevent stale TLBs in fully utilized blocks")
> > >
> > > Signed-off-by: Zhaoyang Huang <[email protected]>
> > > ---
> > > mm/vmalloc.c | 11 +++++++----
> > > 1 file changed, 7 insertions(+), 4 deletions(-)
> > >
> > > diff --git a/mm/vmalloc.c b/mm/vmalloc.c
> > > index 22aa63f4ef63..112b50431725 100644
> > > --- a/mm/vmalloc.c
> > > +++ b/mm/vmalloc.c
> > > @@ -2614,9 +2614,10 @@ static void free_vmap_block(struct vmap_block *vb)
> > > }
> > >
> > > static bool purge_fragmented_block(struct vmap_block *vb,
> > > - struct vmap_block_queue *vbq, struct list_head *purge_list,
> > > - bool force_purge)
> > > + struct list_head *purge_list, bool force_purge)
> > > {
> > > + struct vmap_block_queue *vbq;
> > > +
> > > if (vb->free + vb->dirty != VMAP_BBMAP_BITS ||
> > > vb->dirty == VMAP_BBMAP_BITS)
> > > return false;
> > > @@ -2625,6 +2626,8 @@ static bool purge_fragmented_block(struct vmap_block *vb,
> > > if (!(force_purge || vb->free < VMAP_PURGE_THRESHOLD))
> > > return false;
> > >
> > > + vbq = container_of(addr_to_vb_xa(vb->va->va_start),
> > > + struct vmap_block_queue, vmap_blocks);
> > > /* prevent further allocs after releasing lock */
> > > WRITE_ONCE(vb->free, 0);
> > > /* prevent purging it again */
> > > @@ -2664,7 +2667,7 @@ static void purge_fragmented_blocks(int cpu)
> > > continue;
> > >
> > > spin_lock(&vb->lock);
> > > - purge_fragmented_block(vb, vbq, &purge, true);
> > > + purge_fragmented_block(vb, &purge, true);
> > > spin_unlock(&vb->lock);
> > > }
> > > rcu_read_unlock();
> > > @@ -2801,7 +2804,7 @@ static void _vm_unmap_aliases(unsigned long start, unsigned long end, int flush)
> > > * not purgeable, check whether there is dirty
> > > * space to be flushed.
> > > */
> > > - if (!purge_fragmented_block(vb, vbq, &purge_list, false) &&
> > > + if (!purge_fragmented_block(vb, &purge_list, false) &&
> > > vb->dirty_max && vb->dirty != VMAP_BBMAP_BITS) {
> > > unsigned long va_start = vb->va->va_start;
> > > unsigned long s, e;
> > > --
> > > 2.25.1
> > >
> > >
> >
>
On Thu, May 30, 2024 at 3:54 PM Baoquan He <[email protected]> wrote:
>
> On 05/30/24 at 03:35pm, Zhaoyang Huang wrote:
> > On Thu, May 30, 2024 at 3:19 PM Baoquan He <[email protected]> wrote:
> > >
> > > On 05/30/24 at 10:51am, zhaoyang.huang wrote:
> > > > From: Zhaoyang Huang <[email protected]>
> > > >
> > > > Broken vbq->free reported on a v6.6 based system which is caused
> > > > by invalid vbq->lock protect over vbq->free in purge_fragmented_block.
> > > > This should be introduced by the Fixes below which ignored vbq->lock
> > > > matter.
> > >
> > > It will be helpful to provide more details, what's the symptom of the
> > > brekage, and in which case vbq->free is broken.
> > Vmalloc area runs out in our ARM64 system during an erofs test as
> > vm_map_ram failed[1]. We find that one vbq->free->next point to
> > vbq->free which makes list_for_each_entry_rcu can not iterate the list
> > and find the BUG.
>
> Thanks for these information which are very helpful and important.
> They need be put in log for easier understanding.
ok, I will update the commit message in the next version.
> about the vbq->free list breakage by the run out vmalloc area, could
vm_map_ram()->vb_alloc() will allocate new vb->va which corresponding
to 4MB vmalloc area as list_for_each_entry_rcu returns immediately
when vbq->free->next points to vbq->free. That is to say, 65536 times
of page fault after the list's broken will run out of the whole
vmalloc area.
> you say more about how it's caused? And do you think we need fix that
> vbq->free list breakage either?
IMO, the purge_fragmented_block->list_del_rcu could race with
new_vmap_block->list_add_tail_rcu when vbq is wrongly referenced.
>
> >
> > [1]
> > PID: 1 TASK: ffffff80802b4e00 CPU: 6 COMMAND: "init"
> > #0 [ffffffc08006afe0] __switch_to at ffffffc08111d5cc
> > #1 [ffffffc08006b040] __schedule at ffffffc08111dde0
> > #2 [ffffffc08006b0a0] schedule at ffffffc08111e294
> > #3 [ffffffc08006b0d0] schedule_preempt_disabled at ffffffc08111e3f0
> > #4 [ffffffc08006b140] __mutex_lock at ffffffc08112068c
> > #5 [ffffffc08006b180] __mutex_lock_slowpath at ffffffc08111f8f8
> > #6 [ffffffc08006b1a0] mutex_lock at ffffffc08111f834
> > #7 [ffffffc08006b1d0] reclaim_and_purge_vmap_areas at ffffffc0803ebc3c
> > #8 [ffffffc08006b290] alloc_vmap_area at ffffffc0803e83fc
> > #9 [ffffffc08006b300] vm_map_ram at ffffffc0803e78c0
> > #10 [ffffffc08006b420] z_erofs_lz4_decompress at ffffffc0806a49b0
> > #11 [ffffffc08006b670] z_erofs_decompress_queue at ffffffc0806a8fd0
> > #12 [ffffffc08006b860] z_erofs_runqueue at ffffffc0806a8744
> > #13 [ffffffc08006b970] z_erofs_readahead at ffffffc0806a6cfc
> > #14 [ffffffc08006ba00] read_pages at ffffffc08037ed78
> > #15 [ffffffc08006ba70] page_cache_ra_unbounded at ffffffc08037eb58
> > #16 [ffffffc08006bb00] page_cache_ra_order at ffffffc08037f42c
> > #17 [ffffffc08006bbb0] do_sync_mmap_readahead at ffffffc080371d3c
> > #18 [ffffffc08006bc40] filemap_fault at ffffffc080371774
> > #19 [ffffffc08006bd60] handle_mm_fault at ffffffc0803cc118
> > #20 [ffffffc08006bdc0] do_page_fault at ffffffc08112a618
> > #21 [ffffffc08006be20] do_translation_fault at ffffffc08112a36c
> > #22 [ffffffc08006be30] do_mem_abort at ffffffc0800bfbf0
> > #23 [ffffffc08006be70] el0_ia at ffffffc08111583c
> > #24 [ffffffc08006bea0] el0t_64_sync_handler at ffffffc0811156a4
> > #25 [ffffffc08006bfe0] el0t_64_sync at ffffffc080091584
> >
> >
> > >
> > > >
> > > > Fixes: fc1e0d980037 ("mm/vmalloc: prevent stale TLBs in fully utilized blocks")
> > > >
> > > > Signed-off-by: Zhaoyang Huang <[email protected]>
> > > > ---
> > > > mm/vmalloc.c | 11 +++++++----
> > > > 1 file changed, 7 insertions(+), 4 deletions(-)
> > > >
> > > > diff --git a/mm/vmalloc.c b/mm/vmalloc.c
> > > > index 22aa63f4ef63..112b50431725 100644
> > > > --- a/mm/vmalloc.c
> > > > +++ b/mm/vmalloc.c
> > > > @@ -2614,9 +2614,10 @@ static void free_vmap_block(struct vmap_block *vb)
> > > > }
> > > >
> > > > static bool purge_fragmented_block(struct vmap_block *vb,
> > > > - struct vmap_block_queue *vbq, struct list_head *purge_list,
> > > > - bool force_purge)
> > > > + struct list_head *purge_list, bool force_purge)
> > > > {
> > > > + struct vmap_block_queue *vbq;
> > > > +
> > > > if (vb->free + vb->dirty != VMAP_BBMAP_BITS ||
> > > > vb->dirty == VMAP_BBMAP_BITS)
> > > > return false;
> > > > @@ -2625,6 +2626,8 @@ static bool purge_fragmented_block(struct vmap_block *vb,
> > > > if (!(force_purge || vb->free < VMAP_PURGE_THRESHOLD))
> > > > return false;
> > > >
> > > > + vbq = container_of(addr_to_vb_xa(vb->va->va_start),
> > > > + struct vmap_block_queue, vmap_blocks);
> > > > /* prevent further allocs after releasing lock */
> > > > WRITE_ONCE(vb->free, 0);
> > > > /* prevent purging it again */
> > > > @@ -2664,7 +2667,7 @@ static void purge_fragmented_blocks(int cpu)
> > > > continue;
> > > >
> > > > spin_lock(&vb->lock);
> > > > - purge_fragmented_block(vb, vbq, &purge, true);
> > > > + purge_fragmented_block(vb, &purge, true);
> > > > spin_unlock(&vb->lock);
> > > > }
> > > > rcu_read_unlock();
> > > > @@ -2801,7 +2804,7 @@ static void _vm_unmap_aliases(unsigned long start, unsigned long end, int flush)
> > > > * not purgeable, check whether there is dirty
> > > > * space to be flushed.
> > > > */
> > > > - if (!purge_fragmented_block(vb, vbq, &purge_list, false) &&
> > > > + if (!purge_fragmented_block(vb, &purge_list, false) &&
> > > > vb->dirty_max && vb->dirty != VMAP_BBMAP_BITS) {
> > > > unsigned long va_start = vb->va->va_start;
> > > > unsigned long s, e;
> > > > --
> > > > 2.25.1
> > > >
> > > >
> > >
> >
>
zhaoyang.huang <[email protected]> 于2024年5月30日周四 10:52写道：
>
> From: Zhaoyang Huang <[email protected]>
>
> Broken vbq->free reported on a v6.6 based system which is caused
> by invalid vbq->lock protect over vbq->free in purge_fragmented_block.
> This should be introduced by the Fixes below which ignored vbq->lock
> matter.
>
> Fixes: fc1e0d980037 ("mm/vmalloc: prevent stale TLBs in fully utilized blocks")
>
> Signed-off-by: Zhaoyang Huang <[email protected]>
> ---
> mm/vmalloc.c | 11 +++++++----
> 1 file changed, 7 insertions(+), 4 deletions(-)
>
> diff --git a/mm/vmalloc.c b/mm/vmalloc.c
> index 22aa63f4ef63..112b50431725 100644
> --- a/mm/vmalloc.c
> +++ b/mm/vmalloc.c
> @@ -2614,9 +2614,10 @@ static void free_vmap_block(struct vmap_block *vb)
> }
>
> static bool purge_fragmented_block(struct vmap_block *vb,
> - struct vmap_block_queue *vbq, struct list_head *purge_list,
> - bool force_purge)
> + struct list_head *purge_list, bool force_purge)
> {
> + struct vmap_block_queue *vbq;
> +
> if (vb->free + vb->dirty != VMAP_BBMAP_BITS ||
> vb->dirty == VMAP_BBMAP_BITS)
> return false;
> @@ -2625,6 +2626,8 @@ static bool purge_fragmented_block(struct vmap_block *vb,
> if (!(force_purge || vb->free < VMAP_PURGE_THRESHOLD))
> return false;
>
> + vbq = container_of(addr_to_vb_xa(vb->va->va_start),
> + struct vmap_block_queue, vmap_blocks);
This seems to be the same as before fix :), the vbq found by
addr_to_vb_xa is still added to the xarray vbq, not necessarily to the
free_list vbq,
These two vbqs may not be the same, we need to find the vbq when added
to free_list.
For example:
We add vb to vbq1's xarray and vbq2's free_list, and we need to find
vbq2 instead of vbq1.
So I feel like this place isn't really fixed？
> /* prevent further allocs after releasing lock */
> WRITE_ONCE(vb->free, 0);
> /* prevent purging it again */
> @@ -2664,7 +2667,7 @@ static void purge_fragmented_blocks(int cpu)
> continue;
>
> spin_lock(&vb->lock);
> - purge_fragmented_block(vb, vbq, &purge, true);
> + purge_fragmented_block(vb, &purge, true);
> spin_unlock(&vb->lock);
> }
> rcu_read_unlock();
> @@ -2801,7 +2804,7 @@ static void _vm_unmap_aliases(unsigned long start, unsigned long end, int flush)
> * not purgeable, check whether there is dirty
> * space to be flushed.
> */
> - if (!purge_fragmented_block(vb, vbq, &purge_list, false) &&
> + if (!purge_fragmented_block(vb, &purge_list, false) &&
> vb->dirty_max && vb->dirty != VMAP_BBMAP_BITS) {
> unsigned long va_start = vb->va->va_start;
> unsigned long s, e;
> --
> 2.25.1
>
>
--
Thanks,
Chuanhua
On Thu, May 30, 2024 at 5:16 PM Chuanhua Han <[email protected]> wrote:
>
> zhaoyang.huang <[email protected]> 于2024年5月30日周四 10:52写道：
> >
> > From: Zhaoyang Huang <[email protected]>
> >
> > Broken vbq->free reported on a v6.6 based system which is caused
> > by invalid vbq->lock protect over vbq->free in purge_fragmented_block.
> > This should be introduced by the Fixes below which ignored vbq->lock
> > matter.
> >
> > Fixes: fc1e0d980037 ("mm/vmalloc: prevent stale TLBs in fully utilized blocks")
> >
> > Signed-off-by: Zhaoyang Huang <[email protected]>
> > ---
> > mm/vmalloc.c | 11 +++++++----
> > 1 file changed, 7 insertions(+), 4 deletions(-)
> >
> > diff --git a/mm/vmalloc.c b/mm/vmalloc.c
> > index 22aa63f4ef63..112b50431725 100644
> > --- a/mm/vmalloc.c
> > +++ b/mm/vmalloc.c
> > @@ -2614,9 +2614,10 @@ static void free_vmap_block(struct vmap_block *vb)
> > }
> >
> > static bool purge_fragmented_block(struct vmap_block *vb,
> > - struct vmap_block_queue *vbq, struct list_head *purge_list,
> > - bool force_purge)
> > + struct list_head *purge_list, bool force_purge)
> > {
> > + struct vmap_block_queue *vbq;
> > +
> > if (vb->free + vb->dirty != VMAP_BBMAP_BITS ||
> > vb->dirty == VMAP_BBMAP_BITS)
> > return false;
> > @@ -2625,6 +2626,8 @@ static bool purge_fragmented_block(struct vmap_block *vb,
> > if (!(force_purge || vb->free < VMAP_PURGE_THRESHOLD))
> > return false;
> >
> > + vbq = container_of(addr_to_vb_xa(vb->va->va_start),
> > + struct vmap_block_queue, vmap_blocks);
> This seems to be the same as before fix :), the vbq found by
> addr_to_vb_xa is still added to the xarray vbq, not necessarily to the
> free_list vbq,
Yes, my fault. Should we expand the vmap_block_queue by introducing a
cpu_id which I actually do in my local regression.
> These two vbqs may not be the same, we need to find the vbq when added
> to free_list.
>
> For example:
> We add vb to vbq1's xarray and vbq2's free_list, and we need to find
> vbq2 instead of vbq1.
> So I feel like this place isn't really fixed？
> > /* prevent further allocs after releasing lock */
> > WRITE_ONCE(vb->free, 0);
> > /* prevent purging it again */
> > @@ -2664,7 +2667,7 @@ static void purge_fragmented_blocks(int cpu)
> > continue;
> >
> > spin_lock(&vb->lock);
> > - purge_fragmented_block(vb, vbq, &purge, true);
> > + purge_fragmented_block(vb, &purge, true);
> > spin_unlock(&vb->lock);
> > }
> > rcu_read_unlock();
> > @@ -2801,7 +2804,7 @@ static void _vm_unmap_aliases(unsigned long start, unsigned long end, int flush)
> > * not purgeable, check whether there is dirty
> > * space to be flushed.
> > */
> > - if (!purge_fragmented_block(vb, vbq, &purge_list, false) &&
> > + if (!purge_fragmented_block(vb, &purge_list, false) &&
> > vb->dirty_max && vb->dirty != VMAP_BBMAP_BITS) {
> > unsigned long va_start = vb->va->va_start;
> > unsigned long s, e;
> > --
> > 2.25.1
> >
> >
>
>
> --
> Thanks,
> Chuanhua
Zhaoyang Huang <[email protected]> 于2024年5月30日周四 17:25写道：
>
> On Thu, May 30, 2024 at 5:16 PM Chuanhua Han <[email protected]> wrote:
> >
> > zhaoyang.huang <[email protected]> 于2024年5月30日周四 10:52写道：
> > >
> > > From: Zhaoyang Huang <[email protected]>
> > >
> > > Broken vbq->free reported on a v6.6 based system which is caused
> > > by invalid vbq->lock protect over vbq->free in purge_fragmented_block.
> > > This should be introduced by the Fixes below which ignored vbq->lock
> > > matter.
> > >
> > > Fixes: fc1e0d980037 ("mm/vmalloc: prevent stale TLBs in fully utilized blocks")
> > >
> > > Signed-off-by: Zhaoyang Huang <[email protected]>
> > > ---
> > > mm/vmalloc.c | 11 +++++++----
> > > 1 file changed, 7 insertions(+), 4 deletions(-)
> > >
> > > diff --git a/mm/vmalloc.c b/mm/vmalloc.c
> > > index 22aa63f4ef63..112b50431725 100644
> > > --- a/mm/vmalloc.c
> > > +++ b/mm/vmalloc.c
> > > @@ -2614,9 +2614,10 @@ static void free_vmap_block(struct vmap_block *vb)
> > > }
> > >
> > > static bool purge_fragmented_block(struct vmap_block *vb,
> > > - struct vmap_block_queue *vbq, struct list_head *purge_list,
> > > - bool force_purge)
> > > + struct list_head *purge_list, bool force_purge)
> > > {
> > > + struct vmap_block_queue *vbq;
> > > +
> > > if (vb->free + vb->dirty != VMAP_BBMAP_BITS ||
> > > vb->dirty == VMAP_BBMAP_BITS)
> > > return false;
> > > @@ -2625,6 +2626,8 @@ static bool purge_fragmented_block(struct vmap_block *vb,
> > > if (!(force_purge || vb->free < VMAP_PURGE_THRESHOLD))
> > > return false;
> > >
> > > + vbq = container_of(addr_to_vb_xa(vb->va->va_start),
> > > + struct vmap_block_queue, vmap_blocks);
> > This seems to be the same as before fix :), the vbq found by
> > addr_to_vb_xa is still added to the xarray vbq, not necessarily to the
> > free_list vbq,
> Yes, my fault. Should we expand the vmap_block_queue by introducing a
> cpu_id which I actually do in my local regression.
You may need to embed a cpu_id in vb, and then use cpu_id to get the
vbq where the free_list is located
>
> > These two vbqs may not be the same, we need to find the vbq when added
> > to free_list.
> >
> > For example:
> > We add vb to vbq1's xarray and vbq2's free_list, and we need to find
> > vbq2 instead of vbq1.
> > So I feel like this place isn't really fixed？
> > > /* prevent further allocs after releasing lock */
> > > WRITE_ONCE(vb->free, 0);
> > > /* prevent purging it again */
> > > @@ -2664,7 +2667,7 @@ static void purge_fragmented_blocks(int cpu)
> > > continue;
> > >
> > > spin_lock(&vb->lock);
> > > - purge_fragmented_block(vb, vbq, &purge, true);
> > > + purge_fragmented_block(vb, &purge, true);
> > > spin_unlock(&vb->lock);
> > > }
> > > rcu_read_unlock();
> > > @@ -2801,7 +2804,7 @@ static void _vm_unmap_aliases(unsigned long start, unsigned long end, int flush)
> > > * not purgeable, check whether there is dirty
> > > * space to be flushed.
> > > */
> > > - if (!purge_fragmented_block(vb, vbq, &purge_list, false) &&
> > > + if (!purge_fragmented_block(vb, &purge_list, false) &&
> > > vb->dirty_max && vb->dirty != VMAP_BBMAP_BITS) {
> > > unsigned long va_start = vb->va->va_start;
> > > unsigned long s, e;
> > > --
> > > 2.25.1
> > >
> > >
> >
> >
> > --
> > Thanks,
> > Chuanhua
--
Thanks,
Chuanhua