From: <hu.shengming@zte.com.cn>
To: <harry@kernel.org>
Cc: <tglx@kernel.org>, <linux-kernel@vger.kernel.org>,
<vbabka@kernel.org>, <linux-mm@kvack.org>, <arnd@arndb.de>,
<x86@kernel.org>, <baolu.lu@linux.intel.com>,
<iommu@lists.linux.dev>, <m.grzeschik@pengutronix.de>,
<netdev@vger.kernel.org>, <linux-wireless@vger.kernel.org>,
<herbert@gondor.apana.org.au>, <linux-crypto@vger.kernel.org>,
<dwmw2@infradead.org>, <bernie@plugable.com>,
<linux-fbdev@vger.kernel.org>, <tytso@mit.edu>,
<linux-ext4@vger.kernel.org>, <akpm@linux-foundation.org>,
<urezki@gmail.com>, <elver@google.com>, <dvyukov@google.com>,
<kasan-dev@googlegroups.com>, <ryabinin.a.a@gmail.com>,
<t.sailer@alumni.ethz.ch>, <linux-hams@vger.kernel.org>,
<Jason@zx2c4.com>, <richard.henderson@linaro.org>,
<linux-alpha@vger.kernel.org>, <linux@armlinux.org.uk>,
<linux-arm-kernel@lists.infradead.org>, <catalin.marinas@arm.com>,
<chenhuacai@kernel.org>, <loongarch@lists.linux.dev>,
<geert@linux-m68k.org>, <linux-m68k@lists.linux-m68k.org>,
<dinguyen@kernel.org>, <jonas@southpole.se>,
<linux-openrisc@vger.kernel.org>, <deller@gmx.de>,
<linux-parisc@vger.kernel.org>, <mpe@ellerman.id.au>,
<linuxppc-dev@lists.ozlabs.org>, <pjw@kernel.org>,
<linux-riscv@lists.infradead.org>, <hca@linux.ibm.com>,
<linux-s390@vger.kernel.org>, <davem@davemloft.net>,
<sparclinux@vger.kernel.org>, <hao.li@linux.dev>, <cl@gentwo.org>,
<rientjes@google.com>, <roman.gushchin@linux.dev>
Subject: Re: [patch 14/38] slub: Use prandom instead of get_cycles()
Date: Mon, 13 Apr 2026 21:02:52 +0800 (CST) [thread overview]
Message-ID: <20260413210252672ZfdcegJLJtyvlYdFAUBlr@zte.com.cn> (raw)
In-Reply-To: <adyyNeVTkXQlnh_2@hyeyoo>
Harry wrote:
> [Resending after fixing broken email headers]
>
> On Fri, Apr 10, 2026 at 02:19:37PM +0200, Thomas Gleixner wrote:
> > The decision whether to scan remote nodes is based on a 'random' number
> > retrieved via get_cycles(). get_cycles() is about to be removed.
> >
> > There is already prandom state in the code, so use that instead.
> >
> > Signed-off-by: Thomas Gleixner <tglx@kernel.org>
> > Cc: Vlastimil Babka <vbabka@kernel.org>
> > Cc: linux-mm@kvack.org
> > ---
>
> Acked-by: Harry Yoo (Oracle) <harry@kernel.org>
>
> Is this for this merge window?
>
> This may conflict with upcoming changes on freelist shuffling [1]
> (not queued for slab/for-next yet though), but it should be easy to
> resolve.
>
Hi Harry,
Would you like me to wait for this patch to land linux-next and then
rebase and send v6 on top?
Thanks,
--
With Best Regards,
Shengming
> [Cc'ing Shengming and SLAB ALLOCATOR folks]
> [1] https://lore.kernel.org/linux-mm/20260409204352095kKWVYKtZImN59ybO6iRNj@zte.com.cn
>
> --
> Cheers,
> Harry / Hyeonggon
>
> > mm/slub.c | 37 +++++++++++++++++++++++--------------
> > 1 file changed, 23 insertions(+), 14 deletions(-)
> >
> > --- a/mm/slub.c
> > +++ b/mm/slub.c
> > @@ -3302,6 +3302,25 @@ static inline struct slab *alloc_slab_pa
> > return slab;
> > }
> >
> > +#if defined(CONFIG_SLAB_FREELIST_RANDOM) || defined(CONFIG_NUMA)
> > +static DEFINE_PER_CPU(struct rnd_state, slab_rnd_state);
> > +
> > +static unsigned int slab_get_prandom_state(unsigned int limit)
> > +{
> > + struct rnd_state *state;
> > + unsigned int res;
> > +
> > + /*
> > + * An interrupt or NMI handler might interrupt and change
> > + * the state in the middle, but that's safe.
> > + */
> > + state = &get_cpu_var(slab_rnd_state);
> > + res = prandom_u32_state(state) % limit;
> > + put_cpu_var(slab_rnd_state);
> > + return res;
> > +}
> > +#endif
> > +
> > #ifdef CONFIG_SLAB_FREELIST_RANDOM
> > /* Pre-initialize the random sequence cache */
> > static int init_cache_random_seq(struct kmem_cache *s)
> > @@ -3365,8 +3384,6 @@ static void *next_freelist_entry(struct
> > return (char *)start + idx;
> > }
> >
> > -static DEFINE_PER_CPU(struct rnd_state, slab_rnd_state);
> > -
> > /* Shuffle the single linked freelist based on a random pre-computed sequence */
> > static bool shuffle_freelist(struct kmem_cache *s, struct slab *slab,
> > bool allow_spin)
> > @@ -3383,15 +3400,7 @@ static bool shuffle_freelist(struct kmem
> > if (allow_spin) {
> > pos = get_random_u32_below(freelist_count);
> > } else {
> > - struct rnd_state *state;
> > -
> > - /*
> > - * An interrupt or NMI handler might interrupt and change
> > - * the state in the middle, but that's safe.
> > - */
> > - state = &get_cpu_var(slab_rnd_state);
> > - pos = prandom_u32_state(state) % freelist_count;
> > - put_cpu_var(slab_rnd_state);
> > + pos = slab_get_prandom_state(freelist_count);
> > }
> >
> > page_limit = slab->objects * s->size;
> > @@ -3882,7 +3891,7 @@ static void *get_from_any_partial(struct
> > * with available objects.
> > */
> > if (!s->remote_node_defrag_ratio ||
> > - get_cycles() % 1024 > s->remote_node_defrag_ratio)
> > + slab_get_prandom_state(1024) > s->remote_node_defrag_ratio)
> > return NULL;
> >
> > do {
> > @@ -7102,7 +7111,7 @@ static unsigned int
> >
> > /* see get_from_any_partial() for the defrag ratio description */
> > if (!s->remote_node_defrag_ratio ||
> > - get_cycles() % 1024 > s->remote_node_defrag_ratio)
> > + slab_get_prandom_state(1024) > s->remote_node_defrag_ratio)
> > return 0;
> >
> > do {
> > @@ -8421,7 +8430,7 @@ void __init kmem_cache_init_late(void)
> > flushwq = alloc_workqueue("slub_flushwq", WQ_MEM_RECLAIM | WQ_PERCPU,
> > 0);
> > WARN_ON(!flushwq);
> > -#ifdef CONFIG_SLAB_FREELIST_RANDOM
> > +#if defined(CONFIG_SLAB_FREELIST_RANDOM) || defined(CONFIG_NUMA)
> > prandom_init_once(&slab_rnd_state);
> > #endif
> > }
> >
> >
next prev parent reply other threads:[~2026-04-13 13:03 UTC|newest]
Thread overview: 58+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-04-10 12:18 [patch 00/38] treewide: Cleanup LATCH, CLOCK_TICK_RATE and get_cycles() [ab]use Thomas Gleixner
2026-04-10 12:18 ` [patch 01/38] percpu: Sanitize __percpu_qual include hell Thomas Gleixner
2026-04-10 12:18 ` [patch 02/38] x86: Cleanup include recursion hell Thomas Gleixner
2026-04-10 20:55 ` [patch V1.1 " Thomas Gleixner
2026-04-10 12:18 ` [patch 03/38] x86/apm: Remove last LATCH usage Thomas Gleixner
2026-04-10 12:18 ` [patch 04/38] x86: Use PIT_TICK_RATE instead of CLOCK_TICK_RATE Thomas Gleixner
2026-04-10 12:18 ` [patch 05/38] treewide: Remove CLOCK_TICK_RATE Thomas Gleixner
2026-04-10 12:18 ` [patch 06/38] calibrate: Rework delay timer calibration Thomas Gleixner
2026-04-10 12:19 ` [patch 07/38] treewide: Consolidate cycles_t Thomas Gleixner
2026-04-13 9:15 ` Ojaswin Mujoo
2026-04-10 12:19 ` [patch 08/38] x86/tsc: Use rdtsc() instead of get_cycles() Thomas Gleixner
2026-04-10 12:19 ` [patch 09/38] iommu/vt-d: Use sched_clock() " Thomas Gleixner
2026-04-10 13:45 ` Baolu Lu
2026-04-10 15:14 ` Thomas Gleixner
2026-04-10 12:19 ` [patch 10/38] arcnet: Remove function timing code Thomas Gleixner
2026-04-13 15:29 ` David Woodhouse
2026-04-10 12:19 ` [patch 11/38] misc: sgi-gru: Remove get_cycles() [ab]use Thomas Gleixner
2026-04-10 20:56 ` [patch V1.1 " Thomas Gleixner
2026-04-10 12:19 ` [patch 12/38] wifi: wil6210: Replace get_cyles() usage Thomas Gleixner
2026-04-10 12:19 ` [patch 13/38] crypto: tcrypt: Replace get_cycles() with ktime_get() Thomas Gleixner
2026-04-10 12:19 ` [patch 14/38] slub: Use prandom instead of get_cycles() Thomas Gleixner
2026-04-13 9:00 ` Vlastimil Babka (SUSE)
2026-04-13 9:07 ` Harry Yoo (Oracle)
2026-04-13 13:02 ` hu.shengming [this message]
2026-04-13 13:45 ` Vlastimil Babka (SUSE)
2026-04-10 12:19 ` [patch 15/38] ptp: ptp_vmclock: Replace get_cycles() usage Thomas Gleixner
2026-04-13 15:33 ` David Woodhouse
2026-04-10 12:19 ` [patch 16/38] fbdev: udlfb: Replace get_cycles() with ktime_get() Thomas Gleixner
2026-04-10 12:19 ` [patch 17/38] ext4: Replace get_cycles() usage " Thomas Gleixner
2026-04-13 14:46 ` Arnd Bergmann
2026-04-10 12:19 ` [patch 18/38] lib/tests: Replace get_cycles() " Thomas Gleixner
2026-04-10 12:20 ` [patch 19/38] kcsan: Replace get_cycles() usage Thomas Gleixner
2026-04-10 13:39 ` Marco Elver
2026-04-10 12:20 ` [patch 20/38] kasan: sw_tags: Replace get_cycles() by random_get_entropy() Thomas Gleixner
2026-04-10 12:20 ` [patch 21/38] hamradio: baycom_epp: Remove BAYCOM_DEBUG Thomas Gleixner
2026-04-10 12:20 ` [patch 22/38] random: Provide CONFIG_ARCH_HAS_RANDOM_ENTROPY Thomas Gleixner
2026-04-10 12:20 ` [patch 23/38] alpha: Select ARCH_HAS_RANDOM_ENTROPY Thomas Gleixner
2026-04-12 13:22 ` Magnus Lindholm
2026-04-10 12:20 ` [patch 24/38] ARM: " Thomas Gleixner
2026-04-10 12:20 ` [patch 25/38] arm64: " Thomas Gleixner
2026-04-10 12:20 ` [patch 26/38] loongarch: " Thomas Gleixner
2026-04-10 12:20 ` [patch 27/38] m68k: " Thomas Gleixner
2026-04-10 15:31 ` Daniel Palmer
2026-04-10 12:20 ` [patch 28/38] mips: " Thomas Gleixner
2026-04-13 5:47 ` Maciej W. Rozycki
2026-04-10 12:20 ` [patch 29/38] nios2: " Thomas Gleixner
2026-04-10 12:20 ` [patch 30/38] openrisc: " Thomas Gleixner
2026-04-12 8:56 ` Stafford Horne
2026-04-10 12:21 ` [patch 31/38] parisc: " Thomas Gleixner
2026-04-10 12:21 ` [patch 32/38] powerpc/spufs: Use mftb() directly Thomas Gleixner
2026-04-13 14:43 ` Arnd Bergmann
2026-04-10 12:21 ` [patch 33/38] powerpc: Select ARCH_HAS_RANDOM_ENTROPY Thomas Gleixner
2026-04-10 12:21 ` [patch 34/38] riscv: " Thomas Gleixner
2026-04-10 12:21 ` [patch 35/38] s390: " Thomas Gleixner
2026-04-10 12:21 ` [patch 36/38] sparc: Select ARCH_HAS_RANDOM_ENTROPY for SPARC64 Thomas Gleixner
2026-04-10 12:21 ` [patch 37/38] x86: Select ARCH_HAS_RANDOM_ENTROPY Thomas Gleixner
2026-04-10 12:21 ` [patch 38/38] treewide: Remove asm/timex.h includes from generic code Thomas Gleixner
2026-04-13 14:45 ` Arnd Bergmann
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20260413210252672ZfdcegJLJtyvlYdFAUBlr@zte.com.cn \
--to=hu.shengming@zte.com.cn \
--cc=Jason@zx2c4.com \
--cc=akpm@linux-foundation.org \
--cc=arnd@arndb.de \
--cc=baolu.lu@linux.intel.com \
--cc=bernie@plugable.com \
--cc=catalin.marinas@arm.com \
--cc=chenhuacai@kernel.org \
--cc=cl@gentwo.org \
--cc=davem@davemloft.net \
--cc=deller@gmx.de \
--cc=dinguyen@kernel.org \
--cc=dvyukov@google.com \
--cc=dwmw2@infradead.org \
--cc=elver@google.com \
--cc=geert@linux-m68k.org \
--cc=hao.li@linux.dev \
--cc=harry@kernel.org \
--cc=hca@linux.ibm.com \
--cc=herbert@gondor.apana.org.au \
--cc=iommu@lists.linux.dev \
--cc=jonas@southpole.se \
--cc=kasan-dev@googlegroups.com \
--cc=linux-alpha@vger.kernel.org \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-crypto@vger.kernel.org \
--cc=linux-ext4@vger.kernel.org \
--cc=linux-fbdev@vger.kernel.org \
--cc=linux-hams@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-m68k@lists.linux-m68k.org \
--cc=linux-mm@kvack.org \
--cc=linux-openrisc@vger.kernel.org \
--cc=linux-parisc@vger.kernel.org \
--cc=linux-riscv@lists.infradead.org \
--cc=linux-s390@vger.kernel.org \
--cc=linux-wireless@vger.kernel.org \
--cc=linux@armlinux.org.uk \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=loongarch@lists.linux.dev \
--cc=m.grzeschik@pengutronix.de \
--cc=mpe@ellerman.id.au \
--cc=netdev@vger.kernel.org \
--cc=pjw@kernel.org \
--cc=richard.henderson@linaro.org \
--cc=rientjes@google.com \
--cc=roman.gushchin@linux.dev \
--cc=ryabinin.a.a@gmail.com \
--cc=sparclinux@vger.kernel.org \
--cc=t.sailer@alumni.ethz.ch \
--cc=tglx@kernel.org \
--cc=tytso@mit.edu \
--cc=urezki@gmail.com \
--cc=vbabka@kernel.org \
--cc=x86@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox