Re: [PATCH v2 3/4] powerpc/mm: fix a warning when a cache is common to PGD and hugepages

[Christophe LEROY]

Le 17/08/2018 Ã 05:32, Aneesh Kumar K.V a ÃcritÂ:
> On 08/14/2018 08:24 PM, Christophe Leroy wrote:
> > While implementing TLB miss HW assistance on the 8xx, the following
> > warning was encountered:
> >
> > [Â 423.732965] WARNING: CPU: 0 PID: 345 at mm/slub.c:2412 
> > ___slab_alloc.constprop.30+0x26c/0x46c
> > [Â 423.733033] CPU: 0 PID: 345 Comm: mmap Not tainted 
> > 4.18.0-rc8-00664-g2dfff9121c55 #671
> > [Â 423.733075] NIP:Â c0108f90 LR: c0109ad0 CTR: 00000004
> > [Â 423.733121] REGS: c455bba0 TRAP: 0700ÂÂ Not tainted  
> > (4.18.0-rc8-00664-g2dfff9121c55)
> > [Â 423.733147] MSR:Â 00021032 <ME,IR,DR,RI>Â CR: 24224848Â XER: 20000000
> > [Â 423.733319]
> > [Â 423.733319] GPR00: c0109ad0 c455bc50 c4521910 c60053c0 007080c0 
> > c0011b34 c7fa41e0 c455be30
> > [Â 423.733319] GPR08: 00000001 c00103a0 c7fa41e0 c49afcc4 24282842 
> > 10018840 c079b37c 00000040
> > [Â 423.733319] GPR16: 73f00000 00210d00 00000000 00000001 c455a000 
> > 00000100 00000200 c455a000
> > [Â 423.733319] GPR24: c60053c0 c0011b34 007080c0 c455a000 c455a000 
> > c7fa41e0 00000000 00009032
> > [Â 423.734190] NIP [c0108f90] ___slab_alloc.constprop.30+0x26c/0x46c
> > [Â 423.734257] LR [c0109ad0] kmem_cache_alloc+0x210/0x23c
> > [Â 423.734283] Call Trace:
> > [Â 423.734326] [c455bc50] [00000100] 0x100 (unreliable)
> > [Â 423.734430] [c455bcc0] [c0109ad0] kmem_cache_alloc+0x210/0x23c
> > [Â 423.734543] [c455bcf0] [c0011b34] huge_pte_alloc+0xc0/0x1dc
> > [Â 423.734633] [c455bd20] [c01044dc] hugetlb_fault+0x408/0x48c
> > [Â 423.734720] [c455bdb0] [c0104b20] follow_hugetlb_page+0x14c/0x44c
> > [Â 423.734826] [c455be10] [c00e8e54] __get_user_pages+0x1c4/0x3dc
> > [Â 423.734919] [c455be80] [c00e9924] __mm_populate+0xac/0x140
> > [Â 423.735020] [c455bec0] [c00db14c] vm_mmap_pgoff+0xb4/0xb8
> > [Â 423.735127] [c455bf00] [c00f27c0] ksys_mmap_pgoff+0xcc/0x1fc
> > [Â 423.735222] [c455bf40] [c000e0f8] ret_from_syscall+0x0/0x38
> > [Â 423.735271] Instruction dump:
> > [Â 423.735321] 7cbf482e 38fd0008 7fa6eb78 7fc4f378 4bfff5dd 7fe3fb78 
> > 4bfffe24 81370010
> > [Â 423.735536] 71280004 41a2ff88 4840c571 4bffff80 <0fe00000> 4bfffeb8 
> > 81340010 712a0004
> > [Â 423.735757] ---[ end trace e9b222919a470790 ]---
> >
> > This warning occurs when calling kmem_cache_zalloc() on a
> > cache having a constructor.
> >
> > In this case it happens because PGD cache and 512k hugepte cache are
> > the same size (4k). While a cache with constructor is created for
> > the PGD, hugepages create cache without constructor and uses
> > kmem_cache_zalloc(). As both expect a cache with the same size,
> > the hugepages reuse the cache created for PGD, hence the conflict.
> >
> > In order to avoid this conflict, this patch:
> > - modifies pgtable_cache_add() so that a zeroising constructor is
> > added for any cache size.
> > - replaces calls to kmem_cache_zalloc() by kmem_cache_alloc()
>
> Can't we just do kmem_cache_alloc with gfp flags __GFP_ZERO? and remove 
> the constructor completely?

I don't understand what you mean. That's exactly what I did in v1 (by 
using kmem_cache_zalloc()), and you commented that doing this we would 
zeroise at allocation whereas the constructors are called when adding 
memory to the slab and when freeing the allocated block. Or did I 
misunderstood your comment ?

static inline void *kmem_cache_zalloc(struct kmem_cache *k, gfp_t flags)
{
	return kmem_cache_alloc(k, flags | __GFP_ZERO);
}

Christophe


> -aneesh