RE: [RFC] percpu: decrease pcpu_nr_slots by 1
From: Peng Fan
Date: Wed Feb 27 2019 - 08:33:23 EST
Hi Dennis,
> -----Original Message-----
> From: Dennis Zhou [mailto:dennis@xxxxxxxxxx]
> Sent: 2019å2æ27æ 1:33
> To: Peng Fan <peng.fan@xxxxxxx>
> Cc: dennis@xxxxxxxxxx; tj@xxxxxxxxxx; cl@xxxxxxxxx; linux-mm@xxxxxxxxx;
> linux-kernel@xxxxxxxxxxxxxxx; van.freenix@xxxxxxxxx
> Subject: Re: [RFC] percpu: decrease pcpu_nr_slots by 1
>
> On Tue, Feb 26, 2019 at 12:09:28AM +0000, Peng Fan wrote:
> > Hi Dennis,
> >
> > > -----Original Message-----
> > > From: dennis@xxxxxxxxxx [mailto:dennis@xxxxxxxxxx]
> > > Sent: 2019å2æ25æ 23:24
> > > To: Peng Fan <peng.fan@xxxxxxx>
> > > Cc: tj@xxxxxxxxxx; cl@xxxxxxxxx; linux-mm@xxxxxxxxx;
> > > linux-kernel@xxxxxxxxxxxxxxx; van.freenix@xxxxxxxxx
> > > Subject: Re: [RFC] percpu: decrease pcpu_nr_slots by 1
> > >
> > > On Sun, Feb 24, 2019 at 09:17:08AM +0000, Peng Fan wrote:
> > > > Entry pcpu_slot[pcpu_nr_slots - 2] is wasted with current code logic.
> > > > pcpu_nr_slots is calculated with `__pcpu_size_to_slot(size) + 2`.
> > > > Take pcpu_unit_size as 1024 for example, __pcpu_size_to_slot will
> > > > return max(11 - PCPU_SLOT_BASE_SHIFT + 2, 1), it is 8, so the
> > > > pcpu_nr_slots will be 10.
> > > >
> > > > The chunk with free_bytes 1024 will be linked into pcpu_slot[9].
> > > > However free_bytes in range [512,1024) will be linked into
> > > > pcpu_slot[7], because `fls(512) - PCPU_SLOT_BASE_SHIFT + 2` is 7.
> > > > So pcpu_slot[8] is has no chance to be used.
> > > >
> > > > According comments of PCPU_SLOT_BASE_SHIFT, 1~31 bytes share the
> > > same
> > > > slot and PCPU_SLOT_BASE_SHIFT is defined as 5. But actually 1~15
> > > > share the same slot 1 if we not take PCPU_MIN_ALLOC_SIZE into
> > > > consideration,
> > > > 16~31 share slot 2. Calculation as below:
> > > > highbit = fls(16) -> highbit = 5
> > > > max(5 - PCPU_SLOT_BASE_SHIFT + 2, 1) equals 2, not 1.
> > > >
> > > > This patch by decreasing pcpu_nr_slots to avoid waste one slot and
> > > > let [PCPU_MIN_ALLOC_SIZE, 31) really share the same slot.
> > > >
> > > > Signed-off-by: Peng Fan <peng.fan@xxxxxxx>
> > > > ---
> > > >
> > > > V1:
> > > > Not very sure about whether it is intended to leave the slot there.
> > > >
> > > > mm/percpu.c | 4 ++--
> > > > 1 file changed, 2 insertions(+), 2 deletions(-)
> > > >
> > > > diff --git a/mm/percpu.c b/mm/percpu.c index
> > > > 8d9933db6162..12a9ba38f0b5 100644
> > > > --- a/mm/percpu.c
> > > > +++ b/mm/percpu.c
> > > > @@ -219,7 +219,7 @@ static bool pcpu_addr_in_chunk(struct
> > > > pcpu_chunk *chunk, void *addr) static int __pcpu_size_to_slot(int size)
> {
> > > > int highbit = fls(size); /* size is in bytes */
> > > > - return max(highbit - PCPU_SLOT_BASE_SHIFT + 2, 1);
> > > > + return max(highbit - PCPU_SLOT_BASE_SHIFT + 1, 1);
> > > > }
> > >
> > > Honestly, it may be better to just have [1-16) [16-31) be separate.
Missed to reply this in previous thread, the following comments let
me think the chunk slot calculation might be wrong, so this comment
needs to be updated, saying "[PCPU_MIN_ALLOC_SIZE - 15) bytes share
the same slot", if [1-16)[16-31) is expected.
"
/* the slots are sorted by free bytes left, 1-31 bytes share the same slot */
#define PCPU_SLOT_BASE_SHIFT 5
"
> > > I'm working on a change to this area, so I may change what's going on
> here.
> > >
> > > >
> > > > static int pcpu_size_to_slot(int size) @@ -2145,7 +2145,7 @@ int
> > > > __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
> > > > * Allocate chunk slots. The additional last slot is for
> > > > * empty chunks.
> > > > */
> > > > - pcpu_nr_slots = __pcpu_size_to_slot(pcpu_unit_size) + 2;
> > > > + pcpu_nr_slots = __pcpu_size_to_slot(pcpu_unit_size) + 1;
> > > > pcpu_slot = memblock_alloc(pcpu_nr_slots * sizeof(pcpu_slot[0]),
> > > > SMP_CACHE_BYTES);
> > > > for (i = 0; i < pcpu_nr_slots; i++)
> > > > --
> > > > 2.16.4
> > > >
> > >
> > > This is a tricky change. The nice thing about keeping the additional
> > > slot around is that it ensures a distinction between a completely
> > > empty chunk and a nearly empty chunk.
> >
> > Are there any issues met before if not keeping the unused slot?
> > From reading the code and git history I could not find information.
> > I tried this code on aarch64 qemu and did not meet issues.
> >
>
> This change would require verification that all paths lead to power of 2 chunk
> sizes and most likely a BUG_ON if that's not the case.
I try to understand, "power of 2 chunk sizes", you mean the runtime free_bytes
of a chunk?
>
> So while this would work, we're holding onto an additional slot also to be used
> for chunk reclamation via pcpu_balance_workfn(). If a chunk was not a power
> of 2 resulting in the last slot being entirely empty chunks we could free stuff a
> chunk with addresses still in use.
You mean the following code might free stuff when a percpu variable is still being used
if the chunk runtime free_bytes is not a power of 2?
"
1623 list_for_each_entry_safe(chunk, next, &to_free, list) {
1624 int rs, re;
1625
1626 pcpu_for_each_pop_region(chunk->populated, rs, re, 0,
1627 chunk->nr_pages) {
1628 pcpu_depopulate_chunk(chunk, rs, re);
1629 spin_lock_irq(&pcpu_lock);
1630 pcpu_chunk_depopulated(chunk, rs, re);
1631 spin_unlock_irq(&pcpu_lock);
1632 }
1633 pcpu_destroy_chunk(chunk);
1634 cond_resched();
1635 }
"
>
> > > It happens to be that the logic creates power of 2 chunks which ends
> > > up being an additional slot anyway.
> >
> >
> > So,
> > > given that this logic is tricky and architecture dependent,
> >
> > Could you share more information about architecture dependent?
> >
>
> The crux of the logic is in pcpu_build_alloc_info(). It's been some time since
> I've thought deeply about it, but I don't believe there is a guarantee that it will
> be a power of 2 chunk.
I am a bit lost about a power of 2, need to read more about the code.
Thanks,
Peng.
>
> Thanks,
> Dennis