cpumask_t node_to_cpumask[MAX_NUMNODES] __read_mostly;
int numa_off __initdata;
+unsigned long __initdata nodemap_addr;
+unsigned long __initdata nodemap_size;
/*
int res = -1;
unsigned long addr, end;
- if (shift >= 64)
- return -1;
- memset(memnodemap, 0xff, sizeof(memnodemap));
+ memset(memnodemap, 0xff, memnodemapsize);
for (i = 0; i < numnodes; i++) {
addr = nodes[i].start;
end = nodes[i].end;
if (addr >= end)
continue;
- if ((end >> shift) >= NODEMAPSIZE)
+ if ((end >> shift) >= memnodemapsize)
return 0;
do {
if (memnodemap[addr >> shift] != 0xff)
return -1;
memnodemap[addr >> shift] = i;
- addr += (1UL << shift);
+ addr += (1UL << shift);
} while (addr < end);
res = 1;
}
return res;
}
-int __init compute_hash_shift(struct bootnode *nodes, int numnodes)
+static int __init allocate_cachealigned_memnodemap(void)
{
- int shift = 20;
+ unsigned long pad, pad_addr;
+
+ memnodemap = memnode.embedded_map;
+ if (memnodemapsize <= 48)
+ return 0;
+
+ pad = L1_CACHE_BYTES - 1;
+ pad_addr = 0x8000;
+ nodemap_size = pad + memnodemapsize;
+ nodemap_addr = find_e820_area(pad_addr, end_pfn<<PAGE_SHIFT,
+ nodemap_size);
+ if (nodemap_addr == -1UL) {
+ printk(KERN_ERR
+ "NUMA: Unable to allocate Memory to Node hash map\n");
+ nodemap_addr = nodemap_size = 0;
+ return -1;
+ }
+ pad_addr = (nodemap_addr + pad) & ~pad;
+ memnodemap = phys_to_virt(pad_addr);
- while (populate_memnodemap(nodes, numnodes, shift + 1) >= 0)
- shift++;
+ printk(KERN_DEBUG "NUMA: Allocated memnodemap from %lx - %lx\n",
+ nodemap_addr, nodemap_addr + nodemap_size);
+ return 0;
+}
+
+/*
+ * The LSB of all start and end addresses in the node map is the value of the
+ * maximum possible shift.
+ */
+static int __init
+extract_lsb_from_nodes (const struct bootnode *nodes, int numnodes)
+{
+ int i, nodes_used = 0;
+ unsigned long start, end;
+ unsigned long bitfield = 0, memtop = 0;
+
+ for (i = 0; i < numnodes; i++) {
+ start = nodes[i].start;
+ end = nodes[i].end;
+ if (start >= end)
+ continue;
+ bitfield |= start;
+ nodes_used++;
+ if (end > memtop)
+ memtop = end;
+ }
+ if (nodes_used <= 1)
+ i = 63;
+ else
+ i = find_first_bit(&bitfield, sizeof(unsigned long)*8);
+ memnodemapsize = (memtop >> i)+1;
+ return i;
+}
+int __init compute_hash_shift(struct bootnode *nodes, int numnodes)
+{
+ int shift;
+
+ shift = extract_lsb_from_nodes(nodes, numnodes);
+ if (allocate_cachealigned_memnodemap())
+ return -1;
printk(KERN_DEBUG "NUMA: Using %d for the hash shift.\n",
shift);
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);
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
round_down(limit - memmapsize, PAGE_SIZE),
limit);
#endif
-
- 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)
}
#ifdef CONFIG_NUMA_EMU
-int numa_fake __initdata = 0;
-
/* Numa emulation */
-static int numa_emulation(unsigned long start_pfn, unsigned long end_pfn)
+#define E820_ADDR_HOLE_SIZE(start, end) \
+ (e820_hole_size((start) >> PAGE_SHIFT, (end) >> PAGE_SHIFT) << \
+ PAGE_SHIFT)
+char *cmdline __initdata;
+
+/*
+ * Setups up nid to range from addr to addr + size. If the end boundary is
+ * greater than max_addr, then max_addr is used instead. The return value is 0
+ * if there is additional memory left for allocation past addr and -1 otherwise.
+ * addr is adjusted to be at the end of the node.
+ */
+static int __init setup_node_range(int nid, struct bootnode *nodes, u64 *addr,
+ u64 size, u64 max_addr)
{
- int i;
- struct bootnode nodes[MAX_NUMNODES];
- unsigned long sz = ((end_pfn - start_pfn)<<PAGE_SHIFT) / numa_fake;
-
- /* Kludge needed for the hash function */
- if (hweight64(sz) > 1) {
- unsigned long x = 1;
- while ((x << 1) < sz)
- x <<= 1;
- if (x < sz/2)
- printk(KERN_ERR "Numa emulation unbalanced. Complain to maintainer\n");
- sz = x;
- }
-
- memset(&nodes,0,sizeof(nodes));
- for (i = 0; i < numa_fake; i++) {
- nodes[i].start = (start_pfn<<PAGE_SHIFT) + i*sz;
- if (i == numa_fake-1)
- sz = (end_pfn<<PAGE_SHIFT) - nodes[i].start;
- nodes[i].end = nodes[i].start + sz;
- printk(KERN_INFO "Faking node %d at %016Lx-%016Lx (%LuMB)\n",
- i,
- nodes[i].start, nodes[i].end,
- (nodes[i].end - nodes[i].start) >> 20);
- node_set_online(i);
- }
- memnode_shift = compute_hash_shift(nodes, numa_fake);
- if (memnode_shift < 0) {
- memnode_shift = 0;
- printk(KERN_ERR "No NUMA hash function found. Emulation disabled.\n");
- return -1;
- }
- for_each_online_node(i)
+ int ret = 0;
+ nodes[nid].start = *addr;
+ *addr += size;
+ if (*addr >= max_addr) {
+ *addr = max_addr;
+ ret = -1;
+ }
+ nodes[nid].end = *addr;
+ node_set_online(nid);
+ printk(KERN_INFO "Faking node %d at %016Lx-%016Lx (%LuMB)\n", nid,
+ nodes[nid].start, nodes[nid].end,
+ (nodes[nid].end - nodes[nid].start) >> 20);
+ return ret;
+}
+
+/*
+ * Splits num_nodes nodes up equally starting at node_start. The return value
+ * is the number of nodes split up and addr is adjusted to be at the end of the
+ * last node allocated.
+ */
+static int __init split_nodes_equally(struct bootnode *nodes, u64 *addr,
+ u64 max_addr, int node_start,
+ int num_nodes)
+{
+ unsigned int big;
+ u64 size;
+ int i;
+
+ if (num_nodes <= 0)
+ return -1;
+ if (num_nodes > MAX_NUMNODES)
+ num_nodes = MAX_NUMNODES;
+ size = (max_addr - *addr - E820_ADDR_HOLE_SIZE(*addr, max_addr)) /
+ num_nodes;
+ /*
+ * Calculate the number of big nodes that can be allocated as a result
+ * of consolidating the leftovers.
+ */
+ big = ((size & ~FAKE_NODE_MIN_HASH_MASK) * num_nodes) /
+ FAKE_NODE_MIN_SIZE;
+
+ /* Round down to nearest FAKE_NODE_MIN_SIZE. */
+ size &= FAKE_NODE_MIN_HASH_MASK;
+ if (!size) {
+ printk(KERN_ERR "Not enough memory for each node. "
+ "NUMA emulation disabled.\n");
+ return -1;
+ }
+
+ for (i = node_start; i < num_nodes + node_start; i++) {
+ u64 end = *addr + size;
+ if (i < big)
+ end += FAKE_NODE_MIN_SIZE;
+ /*
+ * The final node can have the remaining system RAM. Other
+ * nodes receive roughly the same amount of available pages.
+ */
+ if (i == num_nodes + node_start - 1)
+ end = max_addr;
+ else
+ while (end - *addr - E820_ADDR_HOLE_SIZE(*addr, end) <
+ size) {
+ end += FAKE_NODE_MIN_SIZE;
+ if (end > max_addr) {
+ end = max_addr;
+ break;
+ }
+ }
+ if (setup_node_range(i, nodes, addr, end - *addr, max_addr) < 0)
+ break;
+ }
+ return i - node_start + 1;
+}
+
+/*
+ * Sets up the system RAM area from start_pfn to end_pfn according to the
+ * numa=fake command-line option.
+ */
+static int __init numa_emulation(unsigned long start_pfn, unsigned long end_pfn)
+{
+ struct bootnode nodes[MAX_NUMNODES];
+ u64 addr = start_pfn << PAGE_SHIFT;
+ u64 max_addr = end_pfn << PAGE_SHIFT;
+ unsigned int coeff;
+ unsigned int num = 0;
+ int num_nodes = 0;
+ u64 size;
+ int i;
+
+ memset(&nodes, 0, sizeof(nodes));
+ /*
+ * If the numa=fake command-line is just a single number N, split the
+ * system RAM into N fake nodes.
+ */
+ if (!strchr(cmdline, '*') && !strchr(cmdline, ',')) {
+ num_nodes = split_nodes_equally(nodes, &addr, max_addr, 0,
+ simple_strtol(cmdline, NULL, 0));
+ if (num_nodes < 0)
+ return num_nodes;
+ goto out;
+ }
+
+ /* Parse the command line. */
+ for (coeff = 1; ; cmdline++) {
+ if (*cmdline && isdigit(*cmdline)) {
+ num = num * 10 + *cmdline - '0';
+ continue;
+ }
+ if (*cmdline == '*')
+ coeff = num;
+ if (!*cmdline || *cmdline == ',') {
+ /*
+ * Round down to the nearest FAKE_NODE_MIN_SIZE.
+ * Command-line coefficients are in megabytes.
+ */
+ size = ((u64)num << 20) & FAKE_NODE_MIN_HASH_MASK;
+ if (size) {
+ for (i = 0; i < coeff; i++, num_nodes++)
+ if (setup_node_range(num_nodes, nodes,
+ &addr, size, max_addr) < 0)
+ goto done;
+ coeff = 1;
+ }
+ }
+ if (!*cmdline)
+ break;
+ num = 0;
+ }
+done:
+ if (!num_nodes)
+ return -1;
+ /* Fill remainder of system RAM with a final node, if appropriate. */
+ if (addr < max_addr) {
+ setup_node_range(num_nodes, nodes, &addr, max_addr - addr,
+ max_addr);
+ num_nodes++;
+ }
+out:
+ memnode_shift = compute_hash_shift(nodes, num_nodes);
+ if (memnode_shift < 0) {
+ memnode_shift = 0;
+ printk(KERN_ERR "No NUMA hash function found. NUMA emulation "
+ "disabled.\n");
+ return -1;
+ }
+
+ /*
+ * We need to vacate all active ranges that may have been registered by
+ * SRAT.
+ */
+ remove_all_active_ranges();
+ 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;
}
-#endif
+#undef E820_ADDR_HOLE_SIZE
+#endif /* CONFIG_NUMA_EMU */
void __init numa_initmem_init(unsigned long start_pfn, unsigned long end_pfn)
{
int i;
#ifdef CONFIG_NUMA_EMU
- if (numa_fake && !numa_emulation(start_pfn, end_pfn))
+ if (cmdline && !numa_emulation(start_pfn, end_pfn))
return;
#endif
end_pfn << PAGE_SHIFT);
/* setup dummy node covering all memory */
memnode_shift = 63;
+ memnodemap = memnode.embedded_map;
memnodemap[0] = 0;
nodes_clear(node_online_map);
node_set_online(0);
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);
}
return pages;
}
-#ifdef CONFIG_SPARSEMEM
-static void __init arch_sparse_init(void)
-{
- int i;
-
- for_each_online_node(i)
- memory_present(i, node_start_pfn(i), node_end_pfn(i));
-
- sparse_init();
-}
-#else
-#define arch_sparse_init() do {} while (0)
-#endif
-
void __init paging_init(void)
{
int i;
+ unsigned long max_zone_pfns[MAX_NR_ZONES];
+ memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
+ max_zone_pfns[ZONE_DMA] = MAX_DMA_PFN;
+ max_zone_pfns[ZONE_DMA32] = MAX_DMA32_PFN;
+ max_zone_pfns[ZONE_NORMAL] = end_pfn;
- arch_sparse_init();
+ sparse_memory_present_with_active_regions(MAX_NUMNODES);
+ sparse_init();
for_each_online_node(i) {
setup_node_zones(i);
}
+
+ free_area_init_nodes(max_zone_pfns);
}
-/* [numa=off] */
-__init int numa_setup(char *opt)
+static __init int numa_setup(char *opt)
{
+ if (!opt)
+ return -EINVAL;
if (!strncmp(opt,"off",3))
numa_off = 1;
#ifdef CONFIG_NUMA_EMU
- if(!strncmp(opt, "fake=", 5)) {
- numa_fake = simple_strtoul(opt+5,NULL,0); ;
- if (numa_fake >= MAX_NUMNODES)
- numa_fake = MAX_NUMNODES;
- }
+ if (!strncmp(opt, "fake=", 5))
+ cmdline = opt + 5;
#endif
#ifdef CONFIG_ACPI_NUMA
if (!strncmp(opt,"noacpi",6))
if (!strncmp(opt,"hotadd=", 7))
hotadd_percent = simple_strtoul(opt+7, NULL, 10);
#endif
- return 1;
+ return 0;
}
+early_param("numa", numa_setup);
+
/*
* Setup early cpu_to_node.
*
projects / linux-2.6-omap-h63xx.git / blobdiff