Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Feedback-ID: if0294502:Fastmail
User-Agent: Cyrus-JMAP/3.7.0-alpha0-1087-g968661d8e1-fm-20221021.001-g968661d8
Mime-Version: 1.0
Message-Id: <00ce752c-17e0-4813-afa3-fe1510545b23@app.fastmail.com>
In-Reply-To: <9b71ae3e-7f53-4c9e-90c4-79d3d649f94c@app.fastmail.com>
References: <20220913065423.520159-1-feng.tang@intel.com>
 <20220913065423.520159-2-feng.tang@intel.com>
 <becf2ac3-2a90-4f3a-96d9-a70f67c66e4a@app.fastmail.com>
 <af2ba83d-c3f4-c6fb-794e-c2c7c0892c44@suse.cz> <Y180l6zUnNjdCoaE@feng-clx>
 <c4285caf-277c-45fd-8fc7-8a1d61685ce8@app.fastmail.com>
 <Y1+0sbQ3R4DB46NX@feng-clx>
 <9b71ae3e-7f53-4c9e-90c4-79d3d649f94c@app.fastmail.com>
Date:   Tue, 01 Nov 2022 02:41:45 +0000
From:   "John Thomson" <lists@johnthomson.fastmail.com.au>
To:     "John Thomson" <lists@johnthomson.fastmail.com.au>,
        "Feng Tang" <feng.tang@intel.com>
Cc:     "Vlastimil Babka" <vbabka@suse.cz>,
        "Andrew Morton" <akpm@linux-foundation.org>,
        "Christoph Lameter" <cl@linux.com>,
        "Pekka Enberg" <penberg@kernel.org>,
        "David Rientjes" <rientjes@google.com>,
        "Joonsoo Kim" <iamjoonsoo.kim@lge.com>,
        "Roman Gushchin" <roman.gushchin@linux.dev>,
        "Hyeonggon Yoo" <42.hyeyoo@gmail.com>,
        "Dmitry Vyukov" <dvyukov@google.com>,
        "Jonathan Corbet" <corbet@lwn.net>,
        "Andrey Konovalov" <andreyknvl@gmail.com>,
        "Hansen, Dave" <dave.hansen@intel.com>,
        "linux-mm@kvack.org" <linux-mm@kvack.org>,
        "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
        "kasan-dev@googlegroups.com" <kasan-dev@googlegroups.com>,
        "Robin Murphy" <robin.murphy@arm.com>,
        "John Garry" <john.garry@huawei.com>,
        "Kefeng Wang" <wangkefeng.wang@huawei.com>
Subject: Re: [PATCH v6 1/4] mm/slub: enable debugging memory wasting of kmalloc
Content-Type: text/plain
Precedence: bulk


On Tue, 1 Nov 2022, at 00:18, John Thomson wrote:
> I may have got lucky. it appears as though this is all I need to boot:
> (against 6.1-rc3), and with the Bootlin toolchain. Will test my other 
> build system as well.
>
> --- a/mm/slub.c
> +++ b/mm/slub.c
> @@ -3276,7 +3276,7 @@ static void *__slab_alloc(struct kmem_cache *s, 
> gfp_t gfpflags, int node,
>         c = slub_get_cpu_ptr(s->cpu_slab);
>  #endif
> 
> -       p = ___slab_alloc(s, gfpflags, node, addr, c, orig_size);
> +       p = ___slab_alloc(s, gfpflags, node, addr, c, 0);
>  #ifdef CONFIG_PREEMPT_COUNT
>         slub_put_cpu_ptr(s->cpu_slab);
>  #endif

Tested that with and without SLUB_DEBUG


Testing without SLUB_DEBUG below:
With this change on 6.1-rc3:
diff --git a/mm/slub.c b/mm/slub.c
index 157527d7101b..5fdb7609bb9e 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -3410,6 +3410,8 @@ static __always_inline
 void *__kmem_cache_alloc_lru(struct kmem_cache *s, struct list_lru *lru,
                             gfp_t gfpflags)
 {
+
+       pr_warn("SLUB: __slab_alloc from slab_alloc s->object_size=%d\n", s->object_size);
        void *ret = slab_alloc(s, lru, gfpflags, _RET_IP_, s->object_size);
 
        trace_kmem_cache_alloc(_RET_IP_, ret, s, gfpflags, NUMA_NO_NODE);


UART & boot stops here:
transfer started ......................................... transfer ok, time=2.00s
setting up elf image... OK
jumping to kernel code
zimage at:     80B842A0 810B4BE4

Uncompressing Linux at load address 80001000

Copy device tree to address  80B80EE0

Now, booting the kernel...

[    0.000000] Linux version 6.1.0-rc3+ (john@john) (mipsel-buildroot-linux-gnu-gcc.br_real (Buildroot 2021.11-4428-g6b6741b) 12.2.0, GNU ld (GNU Binutils) 2.39) #34 SMP Tue Nov  1 12:33:10 AEST 2022
[    0.000000] Overriding previously set SMP ops
[    0.000000] SoC Type: MediaTek MT7621 ver:1 eco:3
[    0.000000] printk: bootconsole [early0] enabled
[    0.000000] CPU0 revision is: 0001992f (MIPS 1004Kc)
[    0.000000] MIPS: machine is MikroTik RouterBOARD 760iGS
[    0.000000] Initrd not found or empty - disabling initrd
[    0.000000] VPE topology {2,2} total 4
[    0.000000] Primary instruction cache 32kB, VIPT, 4-way, linesize 32 bytes.
[    0.000000] Primary data cache 32kB, 4-way, PIPT, no aliases, linesize 32 bytes
[    0.000000] MIPS secondary cache 256kB, 8-way, linesize 32 bytes.
[    0.000000] Zone ranges:
[    0.000000]   Normal   [mem 0x0000000000000000-0x000000000fffffff]
[    0.000000]   HighMem  empty
[    0.000000] Movable zone start for each node
[    0.000000] Early memory node ranges
[    0.000000]   node   0: [mem 0x0000000000000000-0x000000000fffffff]
[    0.000000] Initmem setup node 0 [mem 0x0000000000000000-0x000000000fffffff]
[    0.000000] percpu: Embedded 11 pages/cpu s16064 r8192 d20800 u45056
[    0.000000] Built 1 zonelists, mobility grouping on.  Total pages: 64960
[    0.000000] Kernel command line: earlyprintk=ttyS0,115200 console=ttyS0,115200 rootfstype=squashfs,jffs2
[    0.000000] Unknown kernel command line parameters "earlyprintk=ttyS0,115200", will be passed to user space.
[    0.000000] Dentry cache hash table entries: 32768 (order: 5, 131072 bytes, linear)
[    0.000000] Inode-cache hash table entries: 16384 (order: 4, 65536 bytes, linear)
[    0.000000] Writing ErrCtl register=00011146
[    0.000000] Readback ErrCtl register=00011146
[    0.000000] mem auto-init: stack:off, heap alloc:off, heap free:off
[    0.000000] Memory: 246284K/262144K available (7417K kernel code, 630K rwdata, 1304K rodata, 3500K init, 245K bss, 15860K reserved, 0K cma-reserved, 0K highmem)
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=132
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=132
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=132
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=132
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=132
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=132
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=132
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=132
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=132
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=132
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=132
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=132
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=132
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=132
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=132
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=132
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=132
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=132
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=132
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=132
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=132
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=132
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=132
[    0.000000] SLUB: HWalign=32, Order=0-3, MinObjects=0, CPUs=4, Nodes=1
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=132
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=32
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=132
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=128
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=132
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=132
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=128
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=128
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=300
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=128
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=128
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=128
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=128
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=128
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=128
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=128
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=128
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=128
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=128
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=128
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=128
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=128
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=128
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=128
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=128
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=128
[    0.000000] rcu: Hierarchical RCU implementation.
[    0.000000] 	Tracing variant of Tasks RCU enabled.
[    0.000000] rcu: RCU calculated value of scheduler-enlistment delay is 10 jiffies.
[    0.000000] NR_IRQS: 256
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=128
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=128
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=128
[    0.000000] rcu: srcu_init: Setting srcu_struct sizes based on contention.
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=128
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=128
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=128
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=128
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=128
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=128
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=512
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=128
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=128
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=128
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=512
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=128
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=128
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=256
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=128
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=256
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=128
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=256
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=128
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=128
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=128
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=128
[    0.000000] clocksource: GIC: mask: 0xffffffffffffffff max_cycles: 0xcaf478abb4, max_idle_ns: 440795247997 ns
[    0.000000] SLUB: __slab_alloc from slab_alloc s->object_size=256
[    0.000004] sched_clock: 64 bits at 880MHz, resolution 1ns, wraps every 4398046511103ns


This change, and kernel boots fine:

diff --git a/mm/slub.c b/mm/slub.c
index 157527d7101b..e9677c04d19c 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -3410,7 +3410,11 @@ static __always_inline
 void *__kmem_cache_alloc_lru(struct kmem_cache *s, struct list_lru *lru,
                             gfp_t gfpflags)
 {
-       void *ret = slab_alloc(s, lru, gfpflags, _RET_IP_, s->object_size);
+
+       /*
+       pr_warn("SLUB: __slab_alloc from slab_alloc s->object_size=%d\n", s->object_size);
+       void *ret = slab_alloc(s, lru, gfpflags, _RET_IP_, s->object_size);*/
+       void *ret = slab_alloc(s, lru, gfpflags, _RET_IP_, 0);
 
        trace_kmem_cache_alloc(_RET_IP_, ret, s, gfpflags, NUMA_NO_NODE);
 

Cheers,

-- 
  John Thomson