Commit ffe77a46 authored by Tejun Heo's avatar Tejun Heo
Browse files

x86-64, NUMA: Restructure initmem_init() 



Reorganize initmem_init() such that,

* Different NUMA init methods are iterated in a consistent way.

* Each iteration re-initializes all the parameters and different
  method can be tried after a failure.

* Dummy init is handled the same as other methods.

Apart from how retry after failure, this patch doesn't change the
behavior.  The call sequences are kept equivalent across the
conversion.

After the change, bad_srat() doesn't need to clear apic to node
mapping or worry about numa_off.  Simplified accordingly.

Signed-off-by: default avatarTejun Heo <tj@kernel.org>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Cc: Shaohui Zheng <shaohui.zheng@intel.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: H. Peter Anvin <hpa@linux.intel.com>
parent d8fc3afc

arch/x86/mm/numa_64.c

+51 −43
Original line number Diff line number Diff line
@@ -580,65 +580,73 @@ static int __init numa_emulation(unsigned long start_pfn, 
}

#endif /* CONFIG_NUMA_EMU */



static int dummy_numa_init(void)

{

	return 0;

}



static int dummy_scan_nodes(void)

{

	printk(KERN_INFO "%s\n",

	       numa_off ? "NUMA turned off" : "No NUMA configuration found");

	printk(KERN_INFO "Faking a node at %016lx-%016lx\n",

	       0LU, max_pfn << PAGE_SHIFT);



	/* setup dummy node covering all memory */

	memnode_shift = 63;

	memnodemap = memnode.embedded_map;

	memnodemap[0] = 0;

	node_set_online(0);

	node_set(0, node_possible_map);

	memblock_x86_register_active_regions(0, 0, max_pfn);

	init_memory_mapping_high();

	setup_node_bootmem(0, 0, max_pfn << PAGE_SHIFT);

	numa_init_array();



	return 0;

}



void __init initmem_init(void)

{

	int acpi = 0, amd = 0;

	int i;

	int (*numa_init[])(void) = { [2] = dummy_numa_init };

	int (*scan_nodes[])(void) = { [2] = dummy_scan_nodes };

	int i, j;



	if (!numa_off) {

#ifdef CONFIG_ACPI_NUMA

	/*

	 * Parse SRAT to discover nodes.

	 */

	acpi = !x86_acpi_numa_init();

		numa_init[0] = x86_acpi_numa_init;

		scan_nodes[0] = acpi_scan_nodes;

#endif



#ifdef CONFIG_AMD_NUMA

	if (!acpi)

		amd = !amd_numa_init();

		numa_init[1] = amd_numa_init;

		scan_nodes[1] = amd_scan_nodes;

#endif

	}



	nodes_clear(node_possible_map);

	nodes_clear(node_online_map);

	for (i = 0; i < ARRAY_SIZE(numa_init); i++) {

		if (!numa_init[i])

			continue;



#ifdef CONFIG_NUMA_EMU

	setup_physnodes(0, max_pfn << PAGE_SHIFT, acpi, amd);

	if (cmdline && !numa_emulation(0, max_pfn, acpi, amd))

		return;

	setup_physnodes(0, max_pfn << PAGE_SHIFT, acpi, amd);

	nodes_clear(node_possible_map);

	nodes_clear(node_online_map);

#endif

		for (j = 0; j < MAX_LOCAL_APIC; j++)

			set_apicid_to_node(j, NUMA_NO_NODE);



#ifdef CONFIG_ACPI_NUMA

	if (!numa_off && acpi && !acpi_scan_nodes())

		return;

		nodes_clear(node_possible_map);

		nodes_clear(node_online_map);

#endif



#ifdef CONFIG_AMD_NUMA

	if (!numa_off && amd && !amd_scan_nodes())

		if (numa_init[i]() < 0)

			continue;

#ifdef CONFIG_NUMA_EMU

		setup_physnodes(0, max_pfn << PAGE_SHIFT, i == 0, i == 1);

		if (cmdline && !numa_emulation(0, max_pfn, i == 0, i == 1))

			return;

		setup_physnodes(0, max_pfn << PAGE_SHIFT, i == 0, i == 1);

		nodes_clear(node_possible_map);

		nodes_clear(node_online_map);

#endif

	printk(KERN_INFO "%s\n",

	       numa_off ? "NUMA turned off" : "No NUMA configuration found");



	printk(KERN_INFO "Faking a node at %016lx-%016lx\n",

	       0LU, max_pfn << PAGE_SHIFT);

	/* setup dummy node covering all memory */

	memnode_shift = 63;

	memnodemap = memnode.embedded_map;

	memnodemap[0] = 0;

	node_set_online(0);

	node_set(0, node_possible_map);

	for (i = 0; i < MAX_LOCAL_APIC; i++)

		set_apicid_to_node(i, NUMA_NO_NODE);

	memblock_x86_register_active_regions(0, 0, max_pfn);

	init_memory_mapping_high();

	setup_node_bootmem(0, 0, max_pfn << PAGE_SHIFT);

	numa_init_array();

		if (!scan_nodes[i]())

			return;

	}

	BUG();

}



unsigned long __init numa_free_all_bootmem(void)

arch/x86/mm/srat_64.c

+1 −3
Original line number Diff line number Diff line
@@ -78,8 +78,6 @@ static __init void bad_srat(void) 
	int i;

	printk(KERN_ERR "SRAT: SRAT not used.\n");

	acpi_numa = -1;

	for (i = 0; i < MAX_LOCAL_APIC; i++)

		set_apicid_to_node(i, NUMA_NO_NODE);

	for (i = 0; i < MAX_NUMNODES; i++) {

		nodes[i].start = nodes[i].end = 0;

		nodes_add[i].start = nodes_add[i].end = 0;
@@ -89,7 +87,7 @@ static __init void bad_srat(void) 


static __init inline int srat_disabled(void)

{

	return numa_off || acpi_numa < 0;

	return acpi_numa < 0;

}



/* Callback for SLIT parsing */

CRA Git | Maintained and supported by SUSTech CRA and CCSE