Size zones and holes in an architecture independent manner for x86_64.
This has only been boot tested on an x86_64 with NUMA and SRAT.
arch/x86_64/Kconfig | 3 +
arch/x86_64/kernel/e820.c | 109 ++++++++++-----------------------------
arch/x86_64/kernel/setup.c | 3 -
arch/x86_64/mm/init.c | 62 +---------------------
arch/x86_64/mm/k8topology.c | 3 +
arch/x86_64/mm/numa.c | 18 +++---
arch/x86_64/mm/srat.c | 7 +-
include/asm-x86_64/e820.h | 5 -
include/asm-x86_64/proto.h | 2
9 files changed, 57 insertions(+), 155 deletions(-)
Signed-off-by: Mel Gorman <[email protected]>
diff -rup -X /usr/src/patchset-0.5/bin//dontdiff linux-2.6.17-rc1-103-x86_use_init_nodes/arch/x86_64/Kconfig linux-2.6.17-rc1-104-x86_64_use_init_nodes/arch/x86_64/Kconfig
--- linux-2.6.17-rc1-103-x86_use_init_nodes/arch/x86_64/Kconfig 2006-04-03 04:22:10.000000000 +0100
+++ linux-2.6.17-rc1-104-x86_64_use_init_nodes/arch/x86_64/Kconfig 2006-04-18 10:20:25.000000000 +0100
@@ -73,6 +73,9 @@ config ARCH_MAY_HAVE_PC_FDC
bool
default y
+config ARCH_POPULATES_NODE_MAP
+ def_bool y
+
config DMI
bool
default y
diff -rup -X /usr/src/patchset-0.5/bin//dontdiff linux-2.6.17-rc1-103-x86_use_init_nodes/arch/x86_64/kernel/e820.c linux-2.6.17-rc1-104-x86_64_use_init_nodes/arch/x86_64/kernel/e820.c
--- linux-2.6.17-rc1-103-x86_use_init_nodes/arch/x86_64/kernel/e820.c 2006-04-03 04:22:10.000000000 +0100
+++ linux-2.6.17-rc1-104-x86_64_use_init_nodes/arch/x86_64/kernel/e820.c 2006-04-18 10:20:25.000000000 +0100
@@ -18,6 +18,7 @@
#include <linux/string.h>
#include <linux/kexec.h>
#include <linux/module.h>
+#include <linux/mm.h>
#include <asm/page.h>
#include <asm/e820.h>
@@ -121,58 +122,14 @@ unsigned long __init find_e820_area(unsi
return -1UL;
}
-/*
- * Free bootmem based on the e820 table for a node.
- */
-void __init e820_bootmem_free(pg_data_t *pgdat, unsigned long start,unsigned long end)
-{
- int i;
- for (i = 0; i < e820.nr_map; i++) {
- struct e820entry *ei = &e820.map[i];
- unsigned long last, addr;
-
- if (ei->type != E820_RAM ||
- ei->addr+ei->size <= start ||
- ei->addr >= end)
- continue;
-
- addr = round_up(ei->addr, PAGE_SIZE);
- if (addr < start)
- addr = start;
-
- last = round_down(ei->addr + ei->size, PAGE_SIZE);
- if (last >= end)
- last = end;
-
- if (last > addr && last-addr >= PAGE_SIZE)
- free_bootmem_node(pgdat, addr, last-addr);
- }
-}
-
/*
* Find the highest page frame number we have available
*/
unsigned long __init e820_end_of_ram(void)
{
- int i;
unsigned long end_pfn = 0;
- for (i = 0; i < e820.nr_map; i++) {
- struct e820entry *ei = &e820.map[i];
- unsigned long start, end;
-
- start = round_up(ei->addr, PAGE_SIZE);
- end = round_down(ei->addr + ei->size, PAGE_SIZE);
- if (start >= end)
- continue;
- if (ei->type == E820_RAM) {
- if (end > end_pfn<<PAGE_SHIFT)
- end_pfn = end>>PAGE_SHIFT;
- } else {
- if (end > end_pfn_map<<PAGE_SHIFT)
- end_pfn_map = end>>PAGE_SHIFT;
- }
- }
+ end_pfn = find_max_pfn_with_active_regions();
if (end_pfn > end_pfn_map)
end_pfn_map = end_pfn;
@@ -186,40 +143,6 @@ unsigned long __init e820_end_of_ram(voi
return end_pfn;
}
-/*
- * Compute how much memory is missing in a range.
- * Unlike the other functions in this file the arguments are in page numbers.
- */
-unsigned long __init
-e820_hole_size(unsigned long start_pfn, unsigned long end_pfn)
-{
- unsigned long ram = 0;
- unsigned long start = start_pfn << PAGE_SHIFT;
- unsigned long end = end_pfn << PAGE_SHIFT;
- int i;
- for (i = 0; i < e820.nr_map; i++) {
- struct e820entry *ei = &e820.map[i];
- unsigned long last, addr;
-
- if (ei->type != E820_RAM ||
- ei->addr+ei->size <= start ||
- ei->addr >= end)
- continue;
-
- addr = round_up(ei->addr, PAGE_SIZE);
- if (addr < start)
- addr = start;
-
- last = round_down(ei->addr + ei->size, PAGE_SIZE);
- if (last >= end)
- last = end;
-
- if (last > addr)
- ram += last - addr;
- }
- return ((end - start) - ram) >> PAGE_SHIFT;
-}
-
/*
* Mark e820 reserved areas as busy for the resource manager.
*/
@@ -254,6 +177,34 @@ void __init e820_reserve_resources(void)
}
}
+/* Walk the e820 map and register active regions within a node */
+void __init
+e820_register_active_regions(int nid, unsigned long start_pfn,
+ unsigned long end_pfn)
+{
+ int i;
+ unsigned long ei_startpfn, ei_endpfn;
+ for (i = 0; i < e820.nr_map; i++) {
+ struct e820entry *ei = &e820.map[i];
+ ei_startpfn = round_up(ei->addr, PAGE_SIZE) >> PAGE_SHIFT;
+ ei_endpfn = round_down(ei->addr + ei->size, PAGE_SIZE)
+ >> PAGE_SHIFT;
+ /* Skip if map is outside the node */
+ if (ei->type != E820_RAM ||
+ ei_endpfn <= start_pfn ||
+ ei_startpfn >= end_pfn)
+ continue;
+
+ /* Check for overlaps */
+ if (ei_startpfn < start_pfn)
+ ei_startpfn = start_pfn;
+ if (ei_endpfn > end_pfn)
+ ei_endpfn = end_pfn;
+
+ add_active_range(nid, ei_startpfn, ei_endpfn);
+ }
+}
+
/*
* Add a memory region to the kernel e820 map.
*/
diff -rup -X /usr/src/patchset-0.5/bin//dontdiff linux-2.6.17-rc1-103-x86_use_init_nodes/arch/x86_64/kernel/setup.c linux-2.6.17-rc1-104-x86_64_use_init_nodes/arch/x86_64/kernel/setup.c
--- linux-2.6.17-rc1-103-x86_use_init_nodes/arch/x86_64/kernel/setup.c 2006-04-03 04:22:10.000000000 +0100
+++ linux-2.6.17-rc1-104-x86_64_use_init_nodes/arch/x86_64/kernel/setup.c 2006-04-18 10:20:25.000000000 +0100
@@ -466,7 +466,8 @@ contig_initmem_init(unsigned long start_
if (bootmap == -1L)
panic("Cannot find bootmem map of size %ld\n",bootmap_size);
bootmap_size = init_bootmem(bootmap >> PAGE_SHIFT, end_pfn);
- e820_bootmem_free(NODE_DATA(0), 0, end_pfn << PAGE_SHIFT);
+ e820_register_active_regions(0, 0, end_pfn);
+ free_bootmem_with_active_regions(0, end_pfn);
reserve_bootmem(bootmap, bootmap_size);
}
#endif
diff -rup -X /usr/src/patchset-0.5/bin//dontdiff linux-2.6.17-rc1-103-x86_use_init_nodes/arch/x86_64/mm/init.c linux-2.6.17-rc1-104-x86_64_use_init_nodes/arch/x86_64/mm/init.c
--- linux-2.6.17-rc1-103-x86_use_init_nodes/arch/x86_64/mm/init.c 2006-04-03 04:22:10.000000000 +0100
+++ linux-2.6.17-rc1-104-x86_64_use_init_nodes/arch/x86_64/mm/init.c 2006-04-18 10:20:25.000000000 +0100
@@ -405,69 +405,12 @@ 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];
-
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_DMA_PFN, MAX_DMA32_PFN, end_pfn, end_pfn);
}
#endif
@@ -578,7 +521,8 @@ 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 -rup -X /usr/src/patchset-0.5/bin//dontdiff linux-2.6.17-rc1-103-x86_use_init_nodes/arch/x86_64/mm/k8topology.c linux-2.6.17-rc1-104-x86_64_use_init_nodes/arch/x86_64/mm/k8topology.c
--- linux-2.6.17-rc1-103-x86_use_init_nodes/arch/x86_64/mm/k8topology.c 2006-04-03 04:22:10.000000000 +0100
+++ linux-2.6.17-rc1-104-x86_64_use_init_nodes/arch/x86_64/mm/k8topology.c 2006-04-18 10:20:25.000000000 +0100
@@ -149,6 +149,9 @@ int __init k8_scan_nodes(unsigned long s
prevbase = base;
+ e820_register_active_regions(nodeid,
+ nodes[nodeid].start >> PAGE_SHIFT,
+ nodes[nodeid].end >> PAGE_SHIFT);
node_set(nodeid, nodes_parsed);
}
diff -rup -X /usr/src/patchset-0.5/bin//dontdiff linux-2.6.17-rc1-103-x86_use_init_nodes/arch/x86_64/mm/numa.c linux-2.6.17-rc1-104-x86_64_use_init_nodes/arch/x86_64/mm/numa.c
--- linux-2.6.17-rc1-103-x86_use_init_nodes/arch/x86_64/mm/numa.c 2006-04-03 04:22:10.000000000 +0100
+++ linux-2.6.17-rc1-104-x86_64_use_init_nodes/arch/x86_64/mm/numa.c 2006-04-18 10:20:25.000000000 +0100
@@ -138,7 +138,7 @@ void __init setup_node_bootmem(int nodei
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);
@@ -149,13 +149,11 @@ void __init setup_node_bootmem(int nodei
void __init setup_node_zones(int nodeid)
{
unsigned long start_pfn, end_pfn, memmapsize, limit;
- unsigned long zones[MAX_NR_ZONES];
- unsigned long holes[MAX_NR_ZONES];
start_pfn = node_start_pfn(nodeid);
end_pfn = node_end_pfn(nodeid);
- Dprintk(KERN_INFO "Setting up node %d %lx-%lx\n",
+ Dprintk(KERN_INFO "Setting up memmap for node %d %lx-%lx\n",
nodeid, start_pfn, end_pfn);
/* Try to allocate mem_map at end to not fill up precious <4GB
@@ -167,10 +165,6 @@ void __init setup_node_zones(int nodeid)
memmapsize, SMP_CACHE_BYTES,
round_down(limit - memmapsize, PAGE_SIZE),
limit);
-
- size_zones(zones, holes, start_pfn, end_pfn);
- free_area_init_node(nodeid, NODE_DATA(nodeid), zones,
- start_pfn, holes);
}
void __init numa_init_array(void)
@@ -231,8 +225,11 @@ static int numa_emulation(unsigned long
printk(KERN_ERR "No NUMA hash function found. Emulation disabled.\n");
return -1;
}
- for_each_online_node(i)
+ for_each_online_node(i) {
+ e820_register_active_regions(i, nodes[i].start >> PAGE_SHIFT,
+ nodes[i].end >> PAGE_SHIFT);
setup_node_bootmem(i, nodes[i].start, nodes[i].end);
+ }
numa_init_array();
return 0;
}
@@ -271,6 +268,7 @@ void __init numa_initmem_init(unsigned l
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);
}
@@ -318,6 +316,8 @@ void __init paging_init(void)
for_each_online_node(i) {
setup_node_zones(i);
}
+
+ free_area_init_nodes(MAX_DMA_PFN, MAX_DMA32_PFN, end_pfn, end_pfn);
}
/* [numa=off] */
diff -rup -X /usr/src/patchset-0.5/bin//dontdiff linux-2.6.17-rc1-103-x86_use_init_nodes/arch/x86_64/mm/srat.c linux-2.6.17-rc1-104-x86_64_use_init_nodes/arch/x86_64/mm/srat.c
--- linux-2.6.17-rc1-103-x86_use_init_nodes/arch/x86_64/mm/srat.c 2006-04-03 04:22:10.000000000 +0100
+++ linux-2.6.17-rc1-104-x86_64_use_init_nodes/arch/x86_64/mm/srat.c 2006-04-18 10:20:25.000000000 +0100
@@ -15,6 +15,7 @@
#include <linux/bitmap.h>
#include <linux/module.h>
#include <linux/topology.h>
+#include <linux/mm.h>
#include <asm/proto.h>
#include <asm/numa.h>
#include <asm/e820.h>
@@ -208,6 +209,8 @@ acpi_numa_memory_affinity_init(struct ac
if (nd->end < end)
nd->end = end;
}
+ e820_register_active_regions(node,
+ nd->start >> PAGE_SHIFT, nd->end >> PAGE_SHIFT);
printk(KERN_INFO "SRAT: Node %u PXM %u %Lx-%Lx\n", node, pxm,
nd->start, nd->end);
}
@@ -224,10 +227,10 @@ 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);
}
- 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
diff -rup -X /usr/src/patchset-0.5/bin//dontdiff linux-2.6.17-rc1-103-x86_use_init_nodes/include/asm-x86_64/e820.h linux-2.6.17-rc1-104-x86_64_use_init_nodes/include/asm-x86_64/e820.h
--- linux-2.6.17-rc1-103-x86_use_init_nodes/include/asm-x86_64/e820.h 2006-04-03 04:22:10.000000000 +0100
+++ linux-2.6.17-rc1-104-x86_64_use_init_nodes/include/asm-x86_64/e820.h 2006-04-18 10:20:25.000000000 +0100
@@ -49,10 +49,9 @@ extern void e820_reserve_resources(void)
extern void e820_print_map(char *who);
extern int e820_mapped(unsigned long start, unsigned long end, unsigned type);
-extern void e820_bootmem_free(pg_data_t *pgdat, unsigned long start,unsigned long end);
extern void e820_setup_gap(void);
-extern unsigned long e820_hole_size(unsigned long start_pfn,
- unsigned long end_pfn);
+extern void e820_register_active_regions(int nid,
+ unsigned long start_pfn, unsigned long end_pfn);
extern void __init parse_memopt(char *p, char **end);
extern void __init parse_memmapopt(char *p, char **end);
diff -rup -X /usr/src/patchset-0.5/bin//dontdiff linux-2.6.17-rc1-103-x86_use_init_nodes/include/asm-x86_64/proto.h linux-2.6.17-rc1-104-x86_64_use_init_nodes/include/asm-x86_64/proto.h
--- linux-2.6.17-rc1-103-x86_use_init_nodes/include/asm-x86_64/proto.h 2006-04-03 04:22:10.000000000 +0100
+++ linux-2.6.17-rc1-104-x86_64_use_init_nodes/include/asm-x86_64/proto.h 2006-04-18 10:20:25.000000000 +0100
@@ -24,8 +24,6 @@ extern void mtrr_bp_init(void);
#define mtrr_bp_init() do {} while (0)
#endif
extern void init_memory_mapping(unsigned long start, unsigned long end);
-extern void size_zones(unsigned long *z, unsigned long *h,
- unsigned long start_pfn, unsigned long end_pfn);
extern void system_call(void);
extern int kernel_syscall(void);
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
[Index of Archives]
[Kernel Newbies]
[Netfilter]
[Bugtraq]
[Photo]
[Stuff]
[Gimp]
[Yosemite News]
[MIPS Linux]
[ARM Linux]
[Linux Security]
[Linux RAID]
[Video 4 Linux]
[Linux for the blind]
[Linux Resources]
