[PATCH 17/21] mm: free_area_init: allow defining max_zone_pfn in descending order

[Baoquan He]

On 04/23/20 at 10:53am, Baoquan He wrote:
> On 04/12/20 at 10:48pm, Mike Rapoport wrote:
> > From: Mike Rapoport <rppt at linux.ibm.com>
> > 
> > Some architectures (e.g. ARC) have the ZONE_HIGHMEM zone below the
> > ZONE_NORMAL. Allowing free_area_init() parse max_zone_pfn array even it is
> > sorted in descending order allows using free_area_init() on such
> > architectures.
> > 
> > Add top -> down traversal of max_zone_pfn array in free_area_init() and use
> > the latter in ARC node/zone initialization.
> 
> Or maybe leave ARC as is. The change in this patchset doesn't impact
> ARC's handling about zone initialization, leaving it as is can reduce
> the complication in implementation of free_area_init(), which is a
> common function. So I personally don't see a strong motivation to have
> this patch.

OK, seems this patch is prepared to simplify free_area_init_node(), so
take back what I said at above.

Then this looks necessary, even though it introduces special case into
common function free_area_init().

Reviewed-by: Baoquan He <bhe at redhat.com>

> 
> > 
> > Signed-off-by: Mike Rapoport <rppt at linux.ibm.com>
> > ---
> >  arch/arc/mm/init.c | 36 +++++++-----------------------------
> >  mm/page_alloc.c    | 24 +++++++++++++++++++-----
> >  2 files changed, 26 insertions(+), 34 deletions(-)
> > 
> > diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c
> > index 0920c969c466..41eb9be1653c 100644
> > --- a/arch/arc/mm/init.c
> > +++ b/arch/arc/mm/init.c
> > @@ -63,11 +63,13 @@ void __init early_init_dt_add_memory_arch(u64 base, u64 size)
> >  
> >  		low_mem_sz = size;
> >  		in_use = 1;
> > +		memblock_add_node(base, size, 0);
> >  	} else {
> >  #ifdef CONFIG_HIGHMEM
> >  		high_mem_start = base;
> >  		high_mem_sz = size;
> >  		in_use = 1;
> > +		memblock_add_node(base, size, 1);
> >  #endif
> >  	}
> >  
> > @@ -83,8 +85,7 @@ void __init early_init_dt_add_memory_arch(u64 base, u64 size)
> >   */
> >  void __init setup_arch_memory(void)
> >  {
> > -	unsigned long zones_size[MAX_NR_ZONES];
> > -	unsigned long zones_holes[MAX_NR_ZONES];
> > +	unsigned long max_zone_pfn[MAX_NR_ZONES] = { 0 };
> >  
> >  	init_mm.start_code = (unsigned long)_text;
> >  	init_mm.end_code = (unsigned long)_etext;
> > @@ -115,7 +116,6 @@ void __init setup_arch_memory(void)
> >  	 * the crash
> >  	 */
> >  
> > -	memblock_add_node(low_mem_start, low_mem_sz, 0);
> >  	memblock_reserve(CONFIG_LINUX_LINK_BASE,
> >  			 __pa(_end) - CONFIG_LINUX_LINK_BASE);
> >  
> > @@ -133,22 +133,7 @@ void __init setup_arch_memory(void)
> >  	memblock_dump_all();
> >  
> >  	/*----------------- node/zones setup --------------------------*/
> > -	memset(zones_size, 0, sizeof(zones_size));
> > -	memset(zones_holes, 0, sizeof(zones_holes));
> > -
> > -	zones_size[ZONE_NORMAL] = max_low_pfn - min_low_pfn;
> > -	zones_holes[ZONE_NORMAL] = 0;
> > -
> > -	/*
> > -	 * We can't use the helper free_area_init(zones[]) because it uses
> > -	 * PAGE_OFFSET to compute the @min_low_pfn which would be wrong
> > -	 * when our kernel doesn't start at PAGE_OFFSET, i.e.
> > -	 * PAGE_OFFSET != CONFIG_LINUX_RAM_BASE
> > -	 */
> > -	free_area_init_node(0,			/* node-id */
> > -			    zones_size,		/* num pages per zone */
> > -			    min_low_pfn,	/* first pfn of node */
> > -			    zones_holes);	/* holes */
> > +	max_zone_pfn[ZONE_NORMAL] = max_low_pfn;
> >  
> >  #ifdef CONFIG_HIGHMEM
> >  	/*
> > @@ -168,20 +153,13 @@ void __init setup_arch_memory(void)
> >  	min_high_pfn = PFN_DOWN(high_mem_start);
> >  	max_high_pfn = PFN_DOWN(high_mem_start + high_mem_sz);
> >  
> > -	zones_size[ZONE_NORMAL] = 0;
> > -	zones_holes[ZONE_NORMAL] = 0;
> > -
> > -	zones_size[ZONE_HIGHMEM] = max_high_pfn - min_high_pfn;
> > -	zones_holes[ZONE_HIGHMEM] = 0;
> > -
> > -	free_area_init_node(1,			/* node-id */
> > -			    zones_size,		/* num pages per zone */
> > -			    min_high_pfn,	/* first pfn of node */
> > -			    zones_holes);	/* holes */
> > +	max_zone_pfn[ZONE_HIGHMEM] = max_high_pfn;
> >  
> >  	high_memory = (void *)(min_high_pfn << PAGE_SHIFT);
> >  	kmap_init();
> >  #endif
> > +
> > +	free_area_init(max_zone_pfn);
> >  }
> >  
> >  /*
> > diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> > index 343d87b8697d..376434c7a78b 100644
> > --- a/mm/page_alloc.c
> > +++ b/mm/page_alloc.c
> > @@ -7429,7 +7429,8 @@ static void check_for_memory(pg_data_t *pgdat, int nid)
> >  void __init free_area_init(unsigned long *max_zone_pfn)
> >  {
> >  	unsigned long start_pfn, end_pfn;
> > -	int i, nid;
> > +	int i, nid, zone;
> > +	bool descending = false;
> >  
> >  	/* Record where the zone boundaries are */
> >  	memset(arch_zone_lowest_possible_pfn, 0,
> > @@ -7439,13 +7440,26 @@ void __init free_area_init(unsigned long *max_zone_pfn)
> >  
> >  	start_pfn = find_min_pfn_with_active_regions();
> >  
> > +	/*
> > +	 * Some architecturs, e.g. ARC may have ZONE_HIGHMEM below
> > +	 * ZONE_NORMAL. For such cases we allow max_zone_pfn sorted in the
> > +	 * descending order
> > +	 */
> > +	if (MAX_NR_ZONES > 1 && max_zone_pfn[0] > max_zone_pfn[1])
> > +		descending = true;
> > +
> >  	for (i = 0; i < MAX_NR_ZONES; i++) {
> > -		if (i == ZONE_MOVABLE)
> > +		if (descending)
> > +			zone = MAX_NR_ZONES - i - 1;
> > +		else
> > +			zone = i;
> > +
> > +		if (zone == ZONE_MOVABLE)
> >  			continue;
> >  
> > -		end_pfn = max(max_zone_pfn[i], start_pfn);
> > -		arch_zone_lowest_possible_pfn[i] = start_pfn;
> > -		arch_zone_highest_possible_pfn[i] = end_pfn;
> > +		end_pfn = max(max_zone_pfn[zone], start_pfn);
> > +		arch_zone_lowest_possible_pfn[zone] = start_pfn;
> > +		arch_zone_highest_possible_pfn[zone] = end_pfn;
> >  
> >  		start_pfn = end_pfn;
> >  	}
> > -- 
> > 2.25.1
> >