Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit 0e9f93c1 authored by Tejun Heo's avatar Tejun Heo Committed by H. Peter Anvin
Browse files

x86-32, numa: Move lowmem address space reservation to init_alloc_remap() 



Remap alloc init is done in the following stages.

1. init_alloc_remap() calculates how much memory is necessary for each
   node and reserves node local memory.

2. initmem_init() collects how much each node needs and reserves a
   single contiguous lowmem area which can contain all.

3. init_remap_allocator() initializes allocator parameters from the
   determined lowmem address and per-node offsets.

4. Actual remap happens.

There is no reason for the lowmem remap area to be reserved as a
single contiguous area at one go.  They don't interact with each other
and the memblock allocator will put them side-by-side anyway.

This patch breaks up the single lowmem address reservation and put
per-node lowmem address reservation into init_alloc_remap() and
initializes allocator parameters directly in the function as all the
addresses are determined there.  This merges steps 2 and 3 into 1.

While at it, remove now largely irrelevant comments in
init_alloc_remap().

This change causes the following behavior changes.

* Remap lowmem areas are allocated in smaller per-node chunks.

* Remap lowmem area reservation failure fail future remap allocations
  instead of panicking.

* Remap allocator initialization is less verbose.

Signed-off-by: default avatarTejun Heo <tj@kernel.org>
Link: http://lkml.kernel.org/r/1301955840-7246-10-git-send-email-tj@kernel.org


Acked-by: default avatarYinghai Lu <yinghai@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: default avatarH. Peter Anvin <hpa@zytor.com>
parent 82044c32

arch/x86/mm/numa_32.c

+25 −57
Original line number Original line Diff line number Diff line
@@ -108,9 +108,6 @@ static unsigned long node_remap_size[MAX_NUMNODES]; 
static void *node_remap_start_vaddr[MAX_NUMNODES];

static void *node_remap_start_vaddr[MAX_NUMNODES];

void set_pmd_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags);

void set_pmd_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags);





static unsigned long kva_start_pfn;

static unsigned long kva_pages;



int __cpuinit numa_cpu_node(int cpu)

int __cpuinit numa_cpu_node(int cpu)

{

{

	return apic->x86_32_numa_cpu_node(cpu);

	return apic->x86_32_numa_cpu_node(cpu);
@@ -266,7 +263,8 @@ void resume_map_numa_kva(pgd_t *pgd_base) 
static __init unsigned long init_alloc_remap(int nid, unsigned long offset)

static __init unsigned long init_alloc_remap(int nid, unsigned long offset)

{

{

	unsigned long size;

	unsigned long size;

	u64 node_pa;

	u64 node_pa, remap_pa;

	void *remap_va;





	/*

	/*

	 * The acpi/srat node info can show hot-add memroy zones where

	 * The acpi/srat node info can show hot-add memroy zones where
@@ -287,6 +285,7 @@ static __init unsigned long init_alloc_remap(int nid, unsigned long offset) 
	size += ALIGN(sizeof(pg_data_t), PAGE_SIZE);

	size += ALIGN(sizeof(pg_data_t), PAGE_SIZE);

	size = ALIGN(size, LARGE_PAGE_BYTES);

	size = ALIGN(size, LARGE_PAGE_BYTES);





	/* allocate node memory and the lowmem remap area */

	node_pa = memblock_find_in_range(node_start_pfn[nid] << PAGE_SHIFT,

	node_pa = memblock_find_in_range(node_start_pfn[nid] << PAGE_SHIFT,

					 (u64)node_end_pfn[nid] << PAGE_SHIFT,

					 (u64)node_end_pfn[nid] << PAGE_SHIFT,

					 size, LARGE_PAGE_BYTES);

					 size, LARGE_PAGE_BYTES);
@@ -295,45 +294,35 @@ static __init unsigned long init_alloc_remap(int nid, unsigned long offset) 
			   size, nid);

			   size, nid);

		return 0;

		return 0;

	}

	}

	memblock_x86_reserve_range(node_pa, node_pa + size, "KVA RAM");





	remap_pa = memblock_find_in_range(min_low_pfn << PAGE_SHIFT,

					  max_low_pfn << PAGE_SHIFT,

					  size, LARGE_PAGE_BYTES);

	if (remap_pa == MEMBLOCK_ERROR) {

		pr_warning("remap_alloc: failed to allocate %lu bytes remap area for node %d\n",

			   size, nid);

		memblock_x86_free_range(node_pa, node_pa + size);

		return 0;

	}

	memblock_x86_reserve_range(remap_pa, remap_pa + size, "KVA PG");

	remap_va = phys_to_virt(remap_pa);



	/* initialize remap allocator parameters */

	node_remap_start_pfn[nid] = node_pa >> PAGE_SHIFT;

	node_remap_size[nid] = size >> PAGE_SHIFT;

	node_remap_size[nid] = size >> PAGE_SHIFT;

	node_remap_offset[nid] = offset;

	node_remap_offset[nid] = offset;

	printk(KERN_DEBUG "Reserving %ld pages of KVA for lmem_map of node %d at %llx\n",

	       size >> PAGE_SHIFT, nid, node_pa >> PAGE_SHIFT);





	/*

	node_remap_start_vaddr[nid] = remap_va;

	 *  prevent kva address below max_low_pfn want it on system

	node_remap_end_vaddr[nid] = remap_va + size;

	 *  with less memory later.

	node_remap_alloc_vaddr[nid] = remap_va + ALIGN(sizeof(pg_data_t), PAGE_SIZE);

	 *  layout will be: KVA address , KVA RAM

	 *

	 *  we are supposed to only record the one less then

	 *  max_low_pfn but we could have some hole in high memory,

	 *  and it will only check page_is_ram(pfn) &&

	 *  !page_is_reserved_early(pfn) to decide to use it as free.

	 *  So memblock_x86_reserve_range here, hope we don't run out

	 *  of that array

	 */

	memblock_x86_reserve_range(node_pa, node_pa + size, "KVA RAM");





	node_remap_start_pfn[nid] = node_pa >> PAGE_SHIFT;

	printk(KERN_DEBUG "remap_alloc: node %d [%08llx-%08llx) -> [%p-%p)\n",

	       nid, node_pa, node_pa + size, remap_va, remap_va + size);





	return size >> PAGE_SHIFT;

	return size >> PAGE_SHIFT;

}

}





static void init_remap_allocator(int nid)

{

	node_remap_start_vaddr[nid] = pfn_to_kaddr(

			kva_start_pfn + node_remap_offset[nid]);

	node_remap_end_vaddr[nid] = node_remap_start_vaddr[nid] +

		(node_remap_size[nid] * PAGE_SIZE);

	node_remap_alloc_vaddr[nid] = node_remap_start_vaddr[nid] +

		ALIGN(sizeof(pg_data_t), PAGE_SIZE);



	printk(KERN_DEBUG "node %d will remap to vaddr %08lx - %08lx\n", nid,

		(ulong) node_remap_start_vaddr[nid],

		(ulong) node_remap_end_vaddr[nid]);

}



void __init initmem_init(void)

void __init initmem_init(void)

{

{

	unsigned long reserve_pages = 0;

	unsigned long reserve_pages = 0;
@@ -352,25 +341,7 @@ void __init initmem_init(void) 




	for_each_online_node(nid)

	for_each_online_node(nid)

		reserve_pages += init_alloc_remap(nid, reserve_pages);

		reserve_pages += init_alloc_remap(nid, reserve_pages);

	kva_pages = roundup(reserve_pages, PTRS_PER_PTE);

	printk(KERN_INFO "Reserving total of %lx pages for numa KVA remap\n",

			reserve_pages);





	kva_start_pfn = memblock_find_in_range(min_low_pfn << PAGE_SHIFT,

				max_low_pfn << PAGE_SHIFT,

				kva_pages << PAGE_SHIFT,

				PTRS_PER_PTE << PAGE_SHIFT) >> PAGE_SHIFT;

	if (kva_start_pfn == MEMBLOCK_ERROR)

		panic("Can not get kva space\n");



	printk(KERN_INFO "kva_start_pfn ~ %lx max_low_pfn ~ %lx\n",

		kva_start_pfn, max_low_pfn);

	printk(KERN_INFO "max_pfn = %lx\n", max_pfn);



	/* avoid clash with initrd */

	memblock_x86_reserve_range(kva_start_pfn<<PAGE_SHIFT,

		      (kva_start_pfn + kva_pages)<<PAGE_SHIFT,

		     "KVA PG");

#ifdef CONFIG_HIGHMEM

#ifdef CONFIG_HIGHMEM

	highstart_pfn = highend_pfn = max_pfn;

	highstart_pfn = highend_pfn = max_pfn;

	if (max_pfn > max_low_pfn)

	if (max_pfn > max_low_pfn)
@@ -390,11 +361,8 @@ void __init initmem_init(void) 




	printk(KERN_DEBUG "Low memory ends at vaddr %08lx\n",

	printk(KERN_DEBUG "Low memory ends at vaddr %08lx\n",

			(ulong) pfn_to_kaddr(max_low_pfn));

			(ulong) pfn_to_kaddr(max_low_pfn));

	for_each_online_node(nid) {

	for_each_online_node(nid)

		init_remap_allocator(nid);



		allocate_pgdat(nid);

		allocate_pgdat(nid);

	}

	remap_numa_kva();

	remap_numa_kva();





	printk(KERN_DEBUG "High memory starts at vaddr %08lx\n",

	printk(KERN_DEBUG "High memory starts at vaddr %08lx\n",