From 5cb248abf5ab65ab543b2d5fc16c738b28031fc0 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 27 Sep 2006 01:49:52 -0700 Subject: [PATCH] Have x86_64 use add_active_range() and free_area_init_nodes Size zones and holes in an architecture independent manner for x86_64. Signed-off-by: Mel Gorman Cc: Dave Hansen Cc: Andy Whitcroft Cc: Andi Kleen Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: "Keith Mannthey" Cc: "Luck, Tony" Cc: KAMEZAWA Hiroyuki Cc: Yasunori Goto Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86_64/mm/init.c | 65 +++++---------------------------------------- arch/x86_64/mm/k8topology.c | 3 +++ arch/x86_64/mm/numa.c | 21 ++++++++------- arch/x86_64/mm/srat.c | 11 +++++--- 4 files changed, 28 insertions(+), 72 deletions(-) (limited to 'arch/x86_64/mm') diff --git a/arch/x86_64/mm/init.c b/arch/x86_64/mm/init.c index 1e4669fa5734..47928399e38a 100644 --- a/arch/x86_64/mm/init.c +++ b/arch/x86_64/mm/init.c @@ -403,69 +403,15 @@ void __cpuinit zap_low_mappings(int cpu) __flush_tlb_all(); } -/* Compute zone sizes for the DMA and DMA32 zones in a node. */ -__init void -size_zones(unsigned long *z, unsigned long *h, - unsigned long start_pfn, unsigned long end_pfn) -{ - int i; - unsigned long w; - - for (i = 0; i < MAX_NR_ZONES; i++) - z[i] = 0; - - if (start_pfn < MAX_DMA_PFN) - z[ZONE_DMA] = MAX_DMA_PFN - start_pfn; - if (start_pfn < MAX_DMA32_PFN) { - unsigned long dma32_pfn = MAX_DMA32_PFN; - if (dma32_pfn > end_pfn) - dma32_pfn = end_pfn; - z[ZONE_DMA32] = dma32_pfn - start_pfn; - } - z[ZONE_NORMAL] = end_pfn - start_pfn; - - /* Remove lower zones from higher ones. */ - w = 0; - for (i = 0; i < MAX_NR_ZONES; i++) { - if (z[i]) - z[i] -= w; - w += z[i]; - } - - /* Compute holes */ - w = start_pfn; - for (i = 0; i < MAX_NR_ZONES; i++) { - unsigned long s = w; - w += z[i]; - h[i] = e820_hole_size(s, w); - } - - /* Add the space pace needed for mem_map to the holes too. */ - for (i = 0; i < MAX_NR_ZONES; i++) - h[i] += (z[i] * sizeof(struct page)) / PAGE_SIZE; - - /* The 16MB DMA zone has the kernel and other misc mappings. - Account them too */ - if (h[ZONE_DMA]) { - h[ZONE_DMA] += dma_reserve; - if (h[ZONE_DMA] >= z[ZONE_DMA]) { - printk(KERN_WARNING - "Kernel too large and filling up ZONE_DMA?\n"); - h[ZONE_DMA] = z[ZONE_DMA]; - } - } -} - #ifndef CONFIG_NUMA void __init paging_init(void) { - unsigned long zones[MAX_NR_ZONES], holes[MAX_NR_ZONES]; - + unsigned long max_zone_pfns[MAX_NR_ZONES] = {MAX_DMA_PFN, + MAX_DMA32_PFN, + end_pfn}; memory_present(0, 0, end_pfn); sparse_init(); - size_zones(zones, holes, 0, end_pfn); - free_area_init_node(0, NODE_DATA(0), zones, - __pa(PAGE_OFFSET) >> PAGE_SHIFT, holes); + free_area_init_nodes(max_zone_pfns); } #endif @@ -608,7 +554,8 @@ void __init mem_init(void) #else totalram_pages = free_all_bootmem(); #endif - reservedpages = end_pfn - totalram_pages - e820_hole_size(0, end_pfn); + reservedpages = end_pfn - totalram_pages - + absent_pages_in_range(0, end_pfn); after_bootmem = 1; diff --git a/arch/x86_64/mm/k8topology.c b/arch/x86_64/mm/k8topology.c index 5cf594f9230d..b5b8dba28b4e 100644 --- a/arch/x86_64/mm/k8topology.c +++ b/arch/x86_64/mm/k8topology.c @@ -149,6 +149,9 @@ int __init k8_scan_nodes(unsigned long start, unsigned long end) nodes[nodeid].start = base; nodes[nodeid].end = limit; + e820_register_active_regions(nodeid, + nodes[nodeid].start >> PAGE_SHIFT, + nodes[nodeid].end >> PAGE_SHIFT); prevbase = base; diff --git a/arch/x86_64/mm/numa.c b/arch/x86_64/mm/numa.c index 322bf45fc36a..829a008bd39b 100644 --- a/arch/x86_64/mm/numa.c +++ b/arch/x86_64/mm/numa.c @@ -161,7 +161,7 @@ void __init setup_node_bootmem(int nodeid, unsigned long start, unsigned long en bootmap_start >> PAGE_SHIFT, start_pfn, end_pfn); - e820_bootmem_free(NODE_DATA(nodeid), start, end); + free_bootmem_with_active_regions(nodeid, end); reserve_bootmem_node(NODE_DATA(nodeid), nodedata_phys, pgdat_size); reserve_bootmem_node(NODE_DATA(nodeid), bootmap_start, bootmap_pages<> PAGE_SHIFT, + nodes[i].end >> PAGE_SHIFT); setup_node_bootmem(i, nodes[i].start, nodes[i].end); + } numa_init_array(); return 0; } @@ -299,6 +296,7 @@ void __init numa_initmem_init(unsigned long start_pfn, unsigned long end_pfn) for (i = 0; i < NR_CPUS; i++) numa_set_node(i, 0); node_to_cpumask[0] = cpumask_of_cpu(0); + e820_register_active_regions(0, start_pfn, end_pfn); setup_node_bootmem(0, start_pfn << PAGE_SHIFT, end_pfn << PAGE_SHIFT); } @@ -340,12 +338,17 @@ static void __init arch_sparse_init(void) void __init paging_init(void) { int i; + unsigned long max_zone_pfns[MAX_NR_ZONES] = { MAX_DMA_PFN, + MAX_DMA32_PFN, + end_pfn}; arch_sparse_init(); for_each_online_node(i) { setup_node_zones(i); } + + free_area_init_nodes(max_zone_pfns); } static __init int numa_setup(char *opt) diff --git a/arch/x86_64/mm/srat.c b/arch/x86_64/mm/srat.c index ca10701e7a90..7b50bb1caabe 100644 --- a/arch/x86_64/mm/srat.c +++ b/arch/x86_64/mm/srat.c @@ -93,6 +93,7 @@ static __init void bad_srat(void) apicid_to_node[i] = NUMA_NO_NODE; for (i = 0; i < MAX_NUMNODES; i++) nodes_add[i].start = nodes[i].end = 0; + remove_all_active_ranges(); } static __init inline int srat_disabled(void) @@ -175,7 +176,7 @@ static int hotadd_enough_memory(struct bootnode *nd) if (mem < 0) return 0; - allowed = (end_pfn - e820_hole_size(0, end_pfn)) * PAGE_SIZE; + allowed = (end_pfn - absent_pages_in_range(0, end_pfn)) * PAGE_SIZE; allowed = (allowed / 100) * hotadd_percent; if (allocated + mem > allowed) { unsigned long range; @@ -225,7 +226,7 @@ static int reserve_hotadd(int node, unsigned long start, unsigned long end) } /* This check might be a bit too strict, but I'm keeping it for now. */ - if (e820_hole_size(s_pfn, e_pfn) != e_pfn - s_pfn) { + if (absent_pages_in_range(s_pfn, e_pfn) != e_pfn - s_pfn) { printk(KERN_ERR "SRAT: Hotplug area has existing memory\n"); return -1; } @@ -319,6 +320,8 @@ acpi_numa_memory_affinity_init(struct acpi_table_memory_affinity *ma) printk(KERN_INFO "SRAT: Node %u PXM %u %Lx-%Lx\n", node, pxm, nd->start, nd->end); + e820_register_active_regions(node, nd->start >> PAGE_SHIFT, + nd->end >> PAGE_SHIFT); #ifdef RESERVE_HOTADD if (ma->flags.hot_pluggable && reserve_hotadd(node, start, end) < 0) { @@ -343,13 +346,13 @@ static int nodes_cover_memory(void) unsigned long s = nodes[i].start >> PAGE_SHIFT; unsigned long e = nodes[i].end >> PAGE_SHIFT; pxmram += e - s; - pxmram -= e820_hole_size(s, e); + pxmram -= absent_pages_in_range(s, e); pxmram -= nodes_add[i].end - nodes_add[i].start; if ((long)pxmram < 0) pxmram = 0; } - e820ram = end_pfn - e820_hole_size(0, end_pfn); + e820ram = end_pfn - absent_pages_in_range(0, end_pfn); /* We seem to lose 3 pages somewhere. Allow a bit of slack. */ if ((long)(e820ram - pxmram) >= 1*1024*1024) { printk(KERN_ERR -- cgit v1.2.3-55-g7522