On Tue, 22 Dec 2020, 02:42 Song Bao Hua (Barry Song), <song.bao.hua@xxxxxxxxxxxxx> wrote:
> -----Original Message-----
> From: Song Bao Hua (Barry Song)
> Sent: Tuesday, December 22, 2020 2:06 PM
> To: 'Vitaly Wool' <vitaly.wool@xxxxxxxxxxxx>
> Cc: Shakeel Butt <shakeelb@xxxxxxxxxx>; Minchan Kim <minchan@xxxxxxxxxx>; Mike
> Galbraith <efault@xxxxxx>; LKML <linux-kernel@xxxxxxxxxxxxxxx>; linux-mm
> <linux-mm@xxxxxxxxx>; Sebastian Andrzej Siewior <bigeasy@xxxxxxxxxxxxx>;
> NitinGupta <ngupta@xxxxxxxxxx>; Sergey Senozhatsky
> <sergey.senozhatsky.work@xxxxxxxxx>; Andrew Morton
> <akpm@xxxxxxxxxxxxxxxxxxxx>
> Subject: RE: [PATCH] zsmalloc: do not use bit_spin_lock
>
>
>
> > -----Original Message-----
> > From: Vitaly Wool [mailto:vitaly.wool@xxxxxxxxxxxx]
> > Sent: Tuesday, December 22, 2020 2:00 PM
> > To: Song Bao Hua (Barry Song) <song.bao.hua@xxxxxxxxxxxxx>
> > Cc: Shakeel Butt <shakeelb@xxxxxxxxxx>; Minchan Kim <minchan@xxxxxxxxxx>;
> Mike
> > Galbraith <efault@xxxxxx>; LKML <linux-kernel@xxxxxxxxxxxxxxx>; linux-mm
> > <linux-mm@xxxxxxxxx>; Sebastian Andrzej Siewior <bigeasy@xxxxxxxxxxxxx>;
> > NitinGupta <ngupta@xxxxxxxxxx>; Sergey Senozhatsky
> > <sergey.senozhatsky.work@xxxxxxxxx>; Andrew Morton
> > <akpm@xxxxxxxxxxxxxxxxxxxx>
> > Subject: Re: [PATCH] zsmalloc: do not use bit_spin_lock
> >
> > On Tue, Dec 22, 2020 at 12:37 AM Song Bao Hua (Barry Song)
> > <song.bao.hua@xxxxxxxxxxxxx> wrote:
> > >
> > >
> > >
> > > > -----Original Message-----
> > > > From: Song Bao Hua (Barry Song)
> > > > Sent: Tuesday, December 22, 2020 11:38 AM
> > > > To: 'Vitaly Wool' <vitaly.wool@xxxxxxxxxxxx>
> > > > Cc: Shakeel Butt <shakeelb@xxxxxxxxxx>; Minchan Kim <minchan@xxxxxxxxxx>;
> > Mike
> > > > Galbraith <efault@xxxxxx>; LKML <linux-kernel@xxxxxxxxxxxxxxx>; linux-mm
> > > > <linux-mm@xxxxxxxxx>; Sebastian Andrzej Siewior <bigeasy@xxxxxxxxxxxxx>;
> > > > NitinGupta <ngupta@xxxxxxxxxx>; Sergey Senozhatsky
> > > > <sergey.senozhatsky.work@xxxxxxxxx>; Andrew Morton
> > > > <akpm@xxxxxxxxxxxxxxxxxxxx>
> > > > Subject: RE: [PATCH] zsmalloc: do not use bit_spin_lock
> > > >
> > > >
> > > >
> > > > > -----Original Message-----
> > > > > From: Vitaly Wool [mailto:vitaly.wool@xxxxxxxxxxxx]
> > > > > Sent: Tuesday, December 22, 2020 11:12 AM
> > > > > To: Song Bao Hua (Barry Song) <song.bao.hua@xxxxxxxxxxxxx>
> > > > > Cc: Shakeel Butt <shakeelb@xxxxxxxxxx>; Minchan Kim
> <minchan@xxxxxxxxxx>;
> > > > Mike
> > > > > Galbraith <efault@xxxxxx>; LKML <linux-kernel@xxxxxxxxxxxxxxx>;
> linux-mm
> > > > > <linux-mm@xxxxxxxxx>; Sebastian Andrzej Siewior
> <bigeasy@xxxxxxxxxxxxx>;
> > > > > NitinGupta <ngupta@xxxxxxxxxx>; Sergey Senozhatsky
> > > > > <sergey.senozhatsky.work@xxxxxxxxx>; Andrew Morton
> > > > > <akpm@xxxxxxxxxxxxxxxxxxxx>
> > > > > Subject: Re: [PATCH] zsmalloc: do not use bit_spin_lock
> > > > >
> > > > > On Mon, Dec 21, 2020 at 10:30 PM Song Bao Hua (Barry Song)
> > > > > <song.bao.hua@xxxxxxxxxxxxx> wrote:
> > > > > >
> > > > > >
> > > > > >
> > > > > > > -----Original Message-----
> > > > > > > From: Shakeel Butt [mailto:shakeelb@xxxxxxxxxx]
> > > > > > > Sent: Tuesday, December 22, 2020 10:03 AM
> > > > > > > To: Song Bao Hua (Barry Song) <song.bao.hua@xxxxxxxxxxxxx>
> > > > > > > Cc: Vitaly Wool <vitaly.wool@xxxxxxxxxxxx>; Minchan Kim
> > > > > <minchan@xxxxxxxxxx>;
> > > > > > > Mike Galbraith <efault@xxxxxx>; LKML <linux-kernel@xxxxxxxxxxxxxxx>;
> > > > > linux-mm
> > > > > > > <linux-mm@xxxxxxxxx>; Sebastian Andrzej Siewior
> > <bigeasy@xxxxxxxxxxxxx>;
> > > > > > > NitinGupta <ngupta@xxxxxxxxxx>; Sergey Senozhatsky
> > > > > > > <sergey.senozhatsky.work@xxxxxxxxx>; Andrew Morton
> > > > > > > <akpm@xxxxxxxxxxxxxxxxxxxx>
> > > > > > > Subject: Re: [PATCH] zsmalloc: do not use bit_spin_lock
> > > > > > >
> > > > > > > On Mon, Dec 21, 2020 at 12:06 PM Song Bao Hua (Barry Song)
> > > > > > > <song.bao.hua@xxxxxxxxxxxxx> wrote:
> > > > > > > >
> > > > > > > >
> > > > > > > >
> > > > > > > > > -----Original Message-----
> > > > > > > > > From: Shakeel Butt [mailto:shakeelb@xxxxxxxxxx]
> > > > > > > > > Sent: Tuesday, December 22, 2020 8:50 AM
> > > > > > > > > To: Vitaly Wool <vitaly.wool@xxxxxxxxxxxx>
> > > > > > > > > Cc: Minchan Kim <minchan@xxxxxxxxxx>; Mike Galbraith
> > <efault@xxxxxx>;
> > > > > LKML
> > > > > > > > > <linux-kernel@xxxxxxxxxxxxxxx>; linux-mm <linux-mm@xxxxxxxxx>;
> > Song
> > > > > Bao
> > > > > > > Hua
> > > > > > > > > (Barry Song) <song.bao.hua@xxxxxxxxxxxxx>; Sebastian Andrzej
> > Siewior
> > > > > > > > > <bigeasy@xxxxxxxxxxxxx>; NitinGupta <ngupta@xxxxxxxxxx>; Sergey
> > > > > > > Senozhatsky
> > > > > > > > > <sergey.senozhatsky.work@xxxxxxxxx>; Andrew Morton
> > > > > > > > > <akpm@xxxxxxxxxxxxxxxxxxxx>
> > > > > > > > > Subject: Re: [PATCH] zsmalloc: do not use bit_spin_lock
> > > > > > > > >
> > > > > > > > > On Mon, Dec 21, 2020 at 11:20 AM Vitaly Wool
> > <vitaly.wool@xxxxxxxxxxxx>
> > > > > > > wrote:
> > > > > > > > > >
> > > > > > > > > > On Mon, Dec 21, 2020 at 6:24 PM Minchan Kim <minchan@xxxxxxxxxx>
> > > > wrote:
> > > > > > > > > > >
> > > > > > > > > > > On Sun, Dec 20, 2020 at 02:22:28AM +0200, Vitaly Wool wrote:
> > > > > > > > > > > > zsmalloc takes bit spinlock in its _map() callback and
> releases
> > > > > it
> > > > > > > > > > > > only in unmap() which is unsafe and leads to zswap complaining
> > > > > > > > > > > > about scheduling in atomic context.
> > > > > > > > > > > >
> > > > > > > > > > > > To fix that and to improve RT properties of zsmalloc,
> remove
> > > > that
> > > > > > > > > > > > bit spinlock completely and use a bit flag instead.
> > > > > > > > > > >
> > > > > > > > > > > I don't want to use such open code for the lock.
> > > > > > > > > > >
> > > > > > > > > > > I see from Mike's patch, recent zswap change introduced
> the
> > lockdep
> > > > > > > > > > > splat bug and you want to improve zsmalloc to fix the zswap
> > bug
> > > > > and
> > > > > > > > > > > introduce this patch with allowing preemption enabling.
> > > > > > > > > >
> > > > > > > > > > This understanding is upside down. The code in zswap you are
> > referring
> > > > > > > > > > to is not buggy. You may claim that it is suboptimal but there
> > is
> > > > > > > > > > nothing wrong in taking a mutex.
> > > > > > > > > >
> > > > > > > > >
> > > > > > > > > Is this suboptimal for all or just the hardware accelerators?
> > Sorry,
> > > > > I
> > > > > > > > > am not very familiar with the crypto API. If I select lzo or
> lz4
> > as
> > > > > a
> > > > > > > > > zswap compressor will the [de]compression be async or sync?
> > > > > > > >
> > > > > > > > Right now, in crypto subsystem, new drivers are required to write
> > based
> > > > > on
> > > > > > > > async APIs. The old sync API can't work in new accelerator drivers
> > as
> > > > > they
> > > > > > > > are not supported at all.
> > > > > > > >
> > > > > > > > Old drivers are used to sync, but they've got async wrappers to
> > support
> > > > > async
> > > > > > > > APIs. Eg.
> > > > > > > > crypto: acomp - add support for lz4 via scomp
> > > > > > > >
> > > > > > >
> > > > >
> > > >
> >
> https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/
> > > > > > > crypto/lz4.c?id=8cd9330e0a615c931037d4def98b5ce0d540f08d
> > > > > > > >
> > > > > > > > crypto: acomp - add support for lzo via scomp
> > > > > > > >
> > > > > > >
> > > > >
> > > >
> >
> https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/
> > > > > > > crypto/lzo.c?id=ac9d2c4b39e022d2c61486bfc33b730cfd02898e
> > > > > > > >
> > > > > > > > so they are supporting async APIs but they are still working in
> > sync
> > > > mode
> > > > > > > as
> > > > > > > > those old drivers don't sleep.
> > > > > > > >
> > > > > > >
> > > > > > > Good to know that those are sync because I want them to be sync.
> > > > > > > Please note that zswap is a cache in front of a real swap and the
> > load
> > > > > > > operation is latency sensitive as it comes in the page fault path
> > and
> > > > > > > directly impacts the applications. I doubt decompressing synchronously
> > > > > > > a 4k page on a cpu will be costlier than asynchronously decompressing
> > > > > > > the same page from hardware accelerators.
> > > > > >
> > > > > > If you read the old paper:
> > > > > >
> > > > >
> > > >
> >
> https://www.ibm.com/support/pages/new-linux-zswap-compression-functionalit
> > > > > y
> > > > > > Because the hardware accelerator speeds up compression, looking at
> the
> > zswap
> > > > > > metrics we observed that there were more store and load requests in
> > a given
> > > > > > amount of time, which filled up the zswap pool faster than a software
> > > > > > compression run. Because of this behavior, we set the max_pool_percent
> > > > > > parameter to 30 for the hardware compression runs - this means that
> > zswap
> > > > > > can use up to 30% of the 10GB of total memory.
> > > > > >
> > > > > > So using hardware accelerators, we get a chance to speed up compression
> > > > > > while decreasing cpu utilization.
> > > > > >
> > > > > > BTW, If it is not easy to change zsmalloc, one quick workaround we
> might
> > > > do
> > > > > > in zswap is adding the below after applying Mike's original patch:
> > > > > >
> > > > > > if(in_atomic()) /* for zsmalloc */
> > > > > > while(!try_wait_for_completion(&req->done);
> > > > > > else /* for zbud, z3fold */
> > > > > > crypto_wait_req(....);
> > > > >
> > > > > I don't think I'm going to ack this, sorry.
> > > > >
> > > >
> > > > Fair enough. And I am also thinking if we can move zpool_unmap_handle()
> > > > quite after zpool_map_handle() as below:
> > > >
> > > > dlen = PAGE_SIZE;
> > > > src = "" entry->handle,
> > ZPOOL_MM_RO);
> > > > if (zpool_evictable(entry->pool->zpool))
> > > > src += sizeof(struct zswap_header);
> > > > + zpool_unmap_handle(entry->pool->zpool, entry->handle);
> > > >
> > > > acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx);
> > > > mutex_lock(acomp_ctx->mutex);
> > > > sg_init_one(&input, src, entry->length);
> > > > sg_init_table(&output, 1);
> > > > sg_set_page(&output, page, PAGE_SIZE, 0);
> > > > acomp_request_set_params(acomp_ctx->req, &input, &output,
> > entry->length,
> > > > dlen);
> > > > ret = crypto_wait_req(crypto_acomp_decompress(acomp_ctx->req),
> > > > &acomp_ctx->wait);
> > > > mutex_unlock(acomp_ctx->mutex);
> > > >
> > > > - zpool_unmap_handle(entry->pool->zpool, entry->handle);
> > > >
> > > > Since src is always low memory and we only need its virtual address
> > > > to get the page of src in sg_init_one(). We don't actually read it
> > > > by CPU anywhere.
> > >
> > > The below code might be better:
> > >
> > > dlen = PAGE_SIZE;
> > > src = "" entry->handle,
> > ZPOOL_MM_RO);
> > > if (zpool_evictable(entry->pool->zpool))
> > > src += sizeof(struct zswap_header);
> > >
> > > acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx);
> > >
> > > + zpool_unmap_handle(entry->pool->zpool, entry->handle);
> > >
> > > mutex_lock(acomp_ctx->mutex);
> > > sg_init_one(&input, src, entry->length);
> > > sg_init_table(&output, 1);
> > > sg_set_page(&output, page, PAGE_SIZE, 0);
> > > acomp_request_set_params(acomp_ctx->req, &input, &output,
> > entry->length, dlen);
> > > ret = crypto_wait_req(crypto_acomp_decompress(acomp_ctx->req),
> > &acomp_ctx->wait);
> > > mutex_unlock(acomp_ctx->mutex);
> > >
> > > - zpool_unmap_handle(entry->pool->zpool, entry->handle);
> >
> > I don't see how this is going to work since we can't guarantee src
> > will be a valid pointer after the zpool_unmap_handle() call, can we?
> > Could you please elaborate?
>
> A valid pointer is for cpu to read and write. Here, cpu doesn't read
> and write it, we only need to get page struct from the address.
>
> void sg_init_one(struct scatterlist *sg, const void *buf, unsigned int buflen)
> {
> sg_init_table(sg, 1);
> sg_set_buf(sg, buf, buflen);
> }
>
> static inline void sg_set_buf(struct scatterlist *sg, const void *buf,
> unsigned int buflen)
> {
> #ifdef CONFIG_DEBUG_SG
> BUG_ON(!virt_addr_valid(buf));
> #endif
> sg_set_page(sg, virt_to_page(buf), buflen, offset_in_page(buf));
> }
>
> sg_init_one() is always using an address which has a linear mapping
> with physical address.
> So once we get the value of src, we can get the page struct.
>
> src has a linear mapping with physical address. It doesn't require
> page table walk which vmalloc_to_page() wants.
>
> The req only requires page to initialize sg table, I think if
> we are going to use a cpu-based (de)compression, the crypto
> driver will kmap it again.
Probably I made another bug here. for zsmalloc, it is possible to
get highmem for zpool since its malloc_support_movable = true.
if (zpool_malloc_support_movable(entry->pool->zpool))
gfp |= __GFP_HIGHMEM | __GFP_MOVABLE;
ret = zpool_malloc(entry->pool->zpool, hlen + dlen, gfp, &handle);
For 64bit system, there is never a highmem. For 32bit system, we may
trigger this bug.
So actually zswap should have used kmap_to_page() which can support
both linear mapping and non-linear mapping. sg_init_one() only supports
linear mapping.
But it does't change the fact: Once req is initialized with page
struct, we can unmap src. If we are going to use a HW accelerator,
it would be a DMA; if we are going to use CPU decompression, crypto
driver will kmap() again.
I'm still not convinced. Will kmap what, src? At this point src might become just a bogus pointer. Why couldn't the object have been moved somewhere else (due to the compaction mechanism for instance) at the time DMA kicks in?
>
> >
> > ~Vitaly
>
Thanks
Barry
