[PATCH 1/1] mm: Fix struct page layout on 32-bit systems

[Jesper Dangaard Brouer]

On Wed, 14 Apr 2021 12:50:52 +0100
Matthew Wilcox <willy at infradead.org> wrote:

> > That said, I think we need to have a quicker fix for the immediate
> > issue with 64-bit bit dma_addr on 32-bit arch and the misalignment hole
> > it leaves[3] in struct page.  In[3] you mention ppc32, does it only
> > happens on certain 32-bit archs?  
> 
> AFAICT it happens on mips32, ppc32, arm32 and arc.  It doesn't happen
> on x86-32 because dma_addr_t is 32-bit aligned.

(If others want to reproduce).  First I could not reproduce on ARM32.
Then I found out that enabling CONFIG_XEN on ARCH=arm was needed to
cause the issue by enabling CONFIG_ARCH_DMA_ADDR_T_64BIT.

Details below signature.
-- 
Best regards,
  Jesper Dangaard Brouer
  MSc.CS, Principal Kernel Engineer at Red Hat
  LinkedIn: http://www.linkedin.com/in/brouer

From file: arch/arm/Kconfig

config XEN
	bool "Xen guest support on ARM"
	depends on ARM && AEABI && OF
	depends on CPU_V7 && !CPU_V6
	depends on !GENERIC_ATOMIC64
	depends on MMU
	select ARCH_DMA_ADDR_T_64BIT
	select ARM_PSCI
	select SWIOTLB
	select SWIOTLB_XEN
	select PARAVIRT
	help
	  Say Y if you want to run Linux in a Virtual Machine on Xen on ARM.

My make compile command:

 export VERSION=gcc-arm-10.2-2020.11-x86_64-arm-none-linux-gnueabihf/
 export CROSS_COMPILE="/home/${USER}/cross-compilers/${VERSION}/bin/arm-none-linux-gnueabihf-"
 make -j8 ARCH=arm CROSS_COMPILE=$CROSS_COMPILE

Pahole output:
 $ pahole -C page mm/page_alloc.o

 struct page {
        long unsigned int          flags;                /*     0     4 */

        /* XXX 4 bytes hole, try to pack */

        union {
                struct {
                        struct list_head lru;            /*     8     8 */
                        struct address_space * mapping;  /*    16     4 */
                        long unsigned int index;         /*    20     4 */
                        long unsigned int private;       /*    24     4 */
                };                                       /*     8    20 */
                struct {
                        dma_addr_t dma_addr;             /*     8     8 */
                };                                       /*     8     8 */
                struct {
                        union {
                                struct list_head slab_list; /*     8     8 */
                                struct {
                                        struct page * next; /*     8     4 */
                                        short int pages; /*    12     2 */
                                        short int pobjects; /*    14     2 */
                                };                       /*     8     8 */
                        };                               /*     8     8 */
                        struct kmem_cache * slab_cache;  /*    16     4 */
                        void *     freelist;             /*    20     4 */
                        union {
                                void * s_mem;            /*    24     4 */
                                long unsigned int counters; /*    24     4 */
                                struct {
                                        unsigned int inuse:16; /*    24: 0  4 */
                                        unsigned int objects:15; /*    24:16  4 */
                                        unsigned int frozen:1; /*    24:31  4 */
                                };                       /*    24     4 */
                        };                               /*    24     4 */
                };                                       /*     8    20 */
                struct {
                        long unsigned int compound_head; /*     8     4 */
                        unsigned char compound_dtor;     /*    12     1 */
                        unsigned char compound_order;    /*    13     1 */

                        /* XXX 2 bytes hole, try to pack */

                        atomic_t   compound_mapcount;    /*    16     4 */
                        unsigned int compound_nr;        /*    20     4 */
                };                                       /*     8    16 */
                struct {
                        long unsigned int _compound_pad_1; /*     8     4 */
                        atomic_t   hpage_pinned_refcount; /*    12     4 */
                        struct list_head deferred_list;  /*    16     8 */
                };                                       /*     8    16 */
                struct {
                        long unsigned int _pt_pad_1;     /*     8     4 */
                        pgtable_t  pmd_huge_pte;         /*    12     4 */
                        long unsigned int _pt_pad_2;     /*    16     4 */
                        union {
                                struct mm_struct * pt_mm; /*    20     4 */
                                atomic_t pt_frag_refcount; /*    20     4 */
                        };                               /*    20     4 */
                        spinlock_t ptl;                  /*    24     4 */
                };                                       /*     8    20 */
                struct {
                        struct dev_pagemap * pgmap;      /*     8     4 */
                        void *     zone_device_data;     /*    12     4 */
                };                                       /*     8     8 */
                struct callback_head callback_head __attribute__((__aligned__(4))); /*     8     8 */
        } __attribute__((__aligned__(8)));               /*     8    24 */
        union {
                atomic_t           _mapcount;            /*    32     4 */
                unsigned int       page_type;            /*    32     4 */
                unsigned int       active;               /*    32     4 */
                int                units;                /*    32     4 */
        };                                               /*    32     4 */
        atomic_t                   _refcount;            /*    36     4 */

        /* size: 40, cachelines: 1, members: 4 */
        /* sum members: 36, holes: 1, sum holes: 4 */
        /* forced alignments: 1, forced holes: 1, sum forced holes: 4 */
        /* last cacheline: 40 bytes */
} __attribute__((__aligned__(8)));