* 'x86-bootmem-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (30 commits)
early_res: Need to save the allocation name in drop_range_partial()
sparsemem: Fix compilation on PowerPC
early_res: Add free_early_partial()
x86: Fix non-bootmem compilation on PowerPC
core: Move early_res from arch/x86 to kernel/
x86: Add find_fw_memmap_area
Move round_up/down to kernel.h
x86: Make 32bit support NO_BOOTMEM
early_res: Enhance check_and_double_early_res
x86: Move back find_e820_area to e820.c
x86: Add find_early_area_size
x86: Separate early_res related code from e820.c
x86: Move bios page reserve early to head32/64.c
sparsemem: Put mem map for one node together.
sparsemem: Put usemap for one node together
x86: Make 64 bit use early_res instead of bootmem before slab
x86: Only call dma32_reserve_bootmem 64bit !CONFIG_NUMA
x86: Make early_node_mem get mem > 4 GB if possible
x86: Dynamically increase early_res array size
x86: Introduce max_early_res and early_res_count
...
select HAVE_GENERIC_DMA_COHERENT if X86_32
select HAVE_EFFICIENT_UNALIGNED_ACCESS
select USER_STACKTRACE_SUPPORT
+ select HAVE_REGS_AND_STACK_ACCESS_API
select HAVE_DMA_API_DEBUG
select HAVE_KERNEL_GZIP
select HAVE_KERNEL_BZIP2
config ARCH_SUPPORTS_DEBUG_PAGEALLOC
def_bool y
+ config HAVE_EARLY_RES
+ def_bool y
+
config HAVE_INTEL_TXT
def_bool y
depends on EXPERIMENTAL && DMAR && ACPI
Enable to debug paravirt_ops internals. Specifically, BUG if
a paravirt_op is missing when it is called.
+ config NO_BOOTMEM
+ default y
+ bool "Disable Bootmem code"
+ ---help---
+ Use early_res directly instead of bootmem before slab is ready.
+ - allocator (buddy) [generic]
+ - early allocator (bootmem) [generic]
+ - very early allocator (reserve_early*()) [x86]
+ - very very early allocator (early brk model) [x86]
+ So reduce one layer between early allocator to final allocator
+
+
config MEMTEST
bool "Memtest"
---help---
unsigned long max_low_pfn_mapped;
unsigned long max_pfn_mapped;
+#ifdef CONFIG_DMI
RESERVE_BRK(dmi_alloc, 65536);
+#endif
unsigned int boot_cpu_id __read_mostly;
#endif
initmem_init(0, max_pfn, acpi, k8);
+ #ifndef CONFIG_NO_BOOTMEM
+ early_res_to_bootmem(0, max_low_pfn<<PAGE_SHIFT);
+ #endif
- #ifdef CONFIG_X86_64
- /*
- * dma32_reserve_bootmem() allocates bootmem which may conflict
- * with the crashkernel command line, so do that after
- * reserve_crashkernel()
- */
dma32_reserve_bootmem();
- #endif
reserve_ibft_region();
unsigned long page_size_mask)
{
int use_pse = page_size_mask == (1<<PG_LEVEL_2M);
+ unsigned long last_map_addr = end;
unsigned long start_pfn, end_pfn;
pgd_t *pgd_base = swapper_pg_dir;
int pgd_idx, pmd_idx, pte_ofs;
prot = PAGE_KERNEL_EXEC;
pages_4k++;
- if (mapping_iter == 1)
+ if (mapping_iter == 1) {
set_pte(pte, pfn_pte(pfn, init_prot));
- else
+ last_map_addr = (pfn << PAGE_SHIFT) + PAGE_SIZE;
+ } else
set_pte(pte, pfn_pte(pfn, prot));
}
}
mapping_iter = 2;
goto repeat;
}
- return 0;
+ return last_map_addr;
}
pte_t *kmap_pte;
free_area_init_nodes(max_zone_pfns);
}
+ #ifndef CONFIG_NO_BOOTMEM
static unsigned long __init setup_node_bootmem(int nodeid,
unsigned long start_pfn,
unsigned long end_pfn,
printk(KERN_INFO " node %d bootmap %08lx - %08lx\n",
nodeid, bootmap, bootmap + bootmap_size);
free_bootmem_with_active_regions(nodeid, end_pfn);
- early_res_to_bootmem(start_pfn<<PAGE_SHIFT, end_pfn<<PAGE_SHIFT);
return bootmap + bootmap_size;
}
+ #endif
void __init setup_bootmem_allocator(void)
{
+ #ifndef CONFIG_NO_BOOTMEM
int nodeid;
unsigned long bootmap_size, bootmap;
/*
if (bootmap == -1L)
panic("Cannot find bootmem map of size %ld\n", bootmap_size);
reserve_early(bootmap, bootmap + bootmap_size, "BOOTMAP");
+ #endif
printk(KERN_INFO " mapped low ram: 0 - %08lx\n",
max_pfn_mapped<<PAGE_SHIFT);
printk(KERN_INFO " low ram: 0 - %08lx\n", max_low_pfn<<PAGE_SHIFT);
+ #ifndef CONFIG_NO_BOOTMEM
for_each_online_node(nodeid) {
unsigned long start_pfn, end_pfn;
bootmap = setup_node_bootmem(nodeid, start_pfn, end_pfn,
bootmap);
}
+ #endif
after_bootmem = 1;
}
unsigned long end, unsigned long size,
unsigned long align)
{
- unsigned long mem = find_e820_area(start, end, size, align);
- void *ptr;
+ unsigned long mem;
+ /*
+ * put it on high as possible
+ * something will go with NODE_DATA
+ */
+ if (start < (MAX_DMA_PFN<<PAGE_SHIFT))
+ start = MAX_DMA_PFN<<PAGE_SHIFT;
+ if (start < (MAX_DMA32_PFN<<PAGE_SHIFT) &&
+ end > (MAX_DMA32_PFN<<PAGE_SHIFT))
+ start = MAX_DMA32_PFN<<PAGE_SHIFT;
+ mem = find_e820_area(start, end, size, align);
+ if (mem != -1L)
+ return __va(mem);
+
+ /* extend the search scope */
+ end = max_pfn_mapped << PAGE_SHIFT;
+ if (end > (MAX_DMA32_PFN<<PAGE_SHIFT))
+ start = MAX_DMA32_PFN<<PAGE_SHIFT;
+ else
+ start = MAX_DMA_PFN<<PAGE_SHIFT;
+ mem = find_e820_area(start, end, size, align);
if (mem != -1L)
return __va(mem);
- ptr = __alloc_bootmem_nopanic(size, align, __pa(MAX_DMA_ADDRESS));
- if (ptr == NULL) {
- printk(KERN_ERR "Cannot find %lu bytes in node %d\n",
+ printk(KERN_ERR "Cannot find %lu bytes in node %d\n",
size, nodeid);
- return NULL;
- }
- return ptr;
+
+ return NULL;
}
/* Initialize bootmem allocator for a node */
void __init
setup_node_bootmem(int nodeid, unsigned long start, unsigned long end)
{
- unsigned long start_pfn, last_pfn, bootmap_pages, bootmap_size;
+ unsigned long start_pfn, last_pfn, nodedata_phys;
const int pgdat_size = roundup(sizeof(pg_data_t), PAGE_SIZE);
- unsigned long bootmap_start, nodedata_phys;
- void *bootmap;
int nid;
+ #ifndef CONFIG_NO_BOOTMEM
+ unsigned long bootmap_start, bootmap_pages, bootmap_size;
+ void *bootmap;
+ #endif
if (!end)
return;
start = roundup(start, ZONE_ALIGN);
- printk(KERN_INFO "Bootmem setup node %d %016lx-%016lx\n", nodeid,
+ printk(KERN_INFO "Initmem setup node %d %016lx-%016lx\n", nodeid,
start, end);
start_pfn = start >> PAGE_SHIFT;
if (node_data[nodeid] == NULL)
return;
nodedata_phys = __pa(node_data[nodeid]);
+ reserve_early(nodedata_phys, nodedata_phys + pgdat_size, "NODE_DATA");
printk(KERN_INFO " NODE_DATA [%016lx - %016lx]\n", nodedata_phys,
nodedata_phys + pgdat_size - 1);
+ nid = phys_to_nid(nodedata_phys);
+ if (nid != nodeid)
+ printk(KERN_INFO " NODE_DATA(%d) on node %d\n", nodeid, nid);
memset(NODE_DATA(nodeid), 0, sizeof(pg_data_t));
- NODE_DATA(nodeid)->bdata = &bootmem_node_data[nodeid];
+ NODE_DATA(nodeid)->node_id = nodeid;
NODE_DATA(nodeid)->node_start_pfn = start_pfn;
NODE_DATA(nodeid)->node_spanned_pages = last_pfn - start_pfn;
+ #ifndef CONFIG_NO_BOOTMEM
+ NODE_DATA(nodeid)->bdata = &bootmem_node_data[nodeid];
+
/*
* Find a place for the bootmem map
* nodedata_phys could be on other nodes by alloc_bootmem,
* of alloc_bootmem, that could clash with reserved range
*/
bootmap_pages = bootmem_bootmap_pages(last_pfn - start_pfn);
- nid = phys_to_nid(nodedata_phys);
- if (nid == nodeid)
- bootmap_start = roundup(nodedata_phys + pgdat_size, PAGE_SIZE);
- else
- bootmap_start = roundup(start, PAGE_SIZE);
+ bootmap_start = roundup(nodedata_phys + pgdat_size, PAGE_SIZE);
/*
* SMP_CACHE_BYTES could be enough, but init_bootmem_node like
* to use that to align to PAGE_SIZE
bootmap = early_node_mem(nodeid, bootmap_start, end,
bootmap_pages<<PAGE_SHIFT, PAGE_SIZE);
if (bootmap == NULL) {
- if (nodedata_phys < start || nodedata_phys >= end) {
- /*
- * only need to free it if it is from other node
- * bootmem
- */
- if (nid != nodeid)
- free_bootmem(nodedata_phys, pgdat_size);
- }
+ free_early(nodedata_phys, nodedata_phys + pgdat_size);
node_data[nodeid] = NULL;
return;
}
bootmap_start = __pa(bootmap);
+ reserve_early(bootmap_start, bootmap_start+(bootmap_pages<<PAGE_SHIFT),
+ "BOOTMAP");
bootmap_size = init_bootmem_node(NODE_DATA(nodeid),
bootmap_start >> PAGE_SHIFT,
printk(KERN_INFO " bootmap [%016lx - %016lx] pages %lx\n",
bootmap_start, bootmap_start + bootmap_size - 1,
bootmap_pages);
-
- free_bootmem_with_active_regions(nodeid, end);
-
- /*
- * convert early reserve to bootmem reserve earlier
- * otherwise early_node_mem could use early reserved mem
- * on previous node
- */
- early_res_to_bootmem(start, end);
-
- /*
- * in some case early_node_mem could use alloc_bootmem
- * to get range on other node, don't reserve that again
- */
- if (nid != nodeid)
- printk(KERN_INFO " NODE_DATA(%d) on node %d\n", nodeid, nid);
- else
- reserve_bootmem_node(NODE_DATA(nodeid), nodedata_phys,
- pgdat_size, BOOTMEM_DEFAULT);
nid = phys_to_nid(bootmap_start);
if (nid != nodeid)
printk(KERN_INFO " bootmap(%d) on node %d\n", nodeid, nid);
- else
- reserve_bootmem_node(NODE_DATA(nodeid), bootmap_start,
- bootmap_pages<<PAGE_SHIFT, BOOTMEM_DEFAULT);
+
+ free_bootmem_with_active_regions(nodeid, end);
+ #endif
node_set_online(nodeid);
}
* Calculate the number of big nodes that can be allocated as a result
* of consolidating the remainder.
*/
- big = ((size & ~FAKE_NODE_MIN_HASH_MASK) & nr_nodes) /
+ big = ((size & ~FAKE_NODE_MIN_HASH_MASK) * nr_nodes) /
FAKE_NODE_MIN_SIZE;
size &= FAKE_NODE_MIN_HASH_MASK;
}
/*
- * 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.
+ * Returns the end address of a node so that there is at least `size' amount of
+ * non-reserved memory or `max_addr' is reached.
*/
-static int __init split_nodes_equally(u64 *addr, u64 max_addr, int node_start,
- int num_nodes)
+static u64 __init find_end_of_node(u64 start, u64 max_addr, u64 size)
{
- 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_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;
+ u64 end = start + 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)
+ while (end - start - e820_hole_size(start, end) < size) {
+ end += FAKE_NODE_MIN_SIZE;
+ if (end > max_addr) {
end = max_addr;
- else
- while (end - *addr - e820_hole_size(*addr, end) <
- size) {
- end += FAKE_NODE_MIN_SIZE;
- if (end > max_addr) {
- end = max_addr;
- break;
- }
- }
- if (setup_node_range(i, addr, end - *addr, max_addr) < 0)
break;
+ }
}
- return i - node_start + 1;
+ return end;
}
/*
- * Splits the remaining system RAM into chunks of size. The remaining memory is
- * always assigned to a final node and can be asymmetric. Returns the number of
- * nodes split.
+ * Sets up fake nodes of `size' interleaved over physical nodes ranging from
+ * `addr' to `max_addr'. The return value is the number of nodes allocated.
*/
-static int __init split_nodes_by_size(u64 *addr, u64 max_addr, int node_start,
- u64 size)
+static int __init split_nodes_size_interleave(u64 addr, u64 max_addr, u64 size)
{
- int i = node_start;
- size = (size << 20) & FAKE_NODE_MIN_HASH_MASK;
- while (!setup_node_range(i++, addr, size, max_addr))
- ;
- return i - node_start;
+ nodemask_t physnode_mask = NODE_MASK_NONE;
+ u64 min_size;
+ int ret = 0;
+ int i;
+
+ if (!size)
+ return -1;
+ /*
+ * The limit on emulated nodes is MAX_NUMNODES, so the size per node is
+ * increased accordingly if the requested size is too small. This
+ * creates a uniform distribution of node sizes across the entire
+ * machine (but not necessarily over physical nodes).
+ */
+ min_size = (max_addr - addr - e820_hole_size(addr, max_addr)) /
+ MAX_NUMNODES;
+ min_size = max(min_size, FAKE_NODE_MIN_SIZE);
+ if ((min_size & FAKE_NODE_MIN_HASH_MASK) < min_size)
+ min_size = (min_size + FAKE_NODE_MIN_SIZE) &
+ FAKE_NODE_MIN_HASH_MASK;
+ if (size < min_size) {
+ pr_err("Fake node size %LuMB too small, increasing to %LuMB\n",
+ size >> 20, min_size >> 20);
+ size = min_size;
+ }
+ size &= FAKE_NODE_MIN_HASH_MASK;
+
+ for (i = 0; i < MAX_NUMNODES; i++)
+ if (physnodes[i].start != physnodes[i].end)
+ node_set(i, physnode_mask);
+ /*
+ * Fill physical nodes with fake nodes of size until there is no memory
+ * left on any of them.
+ */
+ while (nodes_weight(physnode_mask)) {
+ for_each_node_mask(i, physnode_mask) {
+ u64 dma32_end = MAX_DMA32_PFN << PAGE_SHIFT;
+ u64 end;
+
+ end = find_end_of_node(physnodes[i].start,
+ physnodes[i].end, size);
+ /*
+ * If there won't be at least FAKE_NODE_MIN_SIZE of
+ * non-reserved memory in ZONE_DMA32 for the next node,
+ * this one must extend to the boundary.
+ */
+ if (end < dma32_end && dma32_end - end -
+ e820_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE)
+ end = dma32_end;
+
+ /*
+ * If there won't be enough non-reserved memory for the
+ * next node, this one must extend to the end of the
+ * physical node.
+ */
+ if (physnodes[i].end - end -
+ e820_hole_size(end, physnodes[i].end) < size)
+ end = physnodes[i].end;
+
+ /*
+ * Setup the fake node that will be allocated as bootmem
+ * later. If setup_node_range() returns non-zero, there
+ * is no more memory available on this physical node.
+ */
+ if (setup_node_range(ret++, &physnodes[i].start,
+ end - physnodes[i].start,
+ physnodes[i].end) < 0)
+ node_clear(i, physnode_mask);
+ }
+ }
+ return ret;
}
/*
static int __init numa_emulation(unsigned long start_pfn,
unsigned long last_pfn, int acpi, int k8)
{
- u64 size, addr = start_pfn << PAGE_SHIFT;
+ u64 addr = start_pfn << PAGE_SHIFT;
u64 max_addr = last_pfn << PAGE_SHIFT;
- int num_nodes = 0, num = 0, coeff_flag, coeff = -1, i;
int num_phys_nodes;
+ int num_nodes;
+ int i;
num_phys_nodes = setup_physnodes(addr, max_addr, acpi, k8);
/*
- * If the numa=fake command-line is just a single number N, split the
- * system RAM into N fake nodes.
+ * If the numa=fake command-line contains a 'M' or 'G', it represents
+ * the fixed node size. Otherwise, if it is just a single number N,
+ * split the system RAM into N fake nodes.
*/
- if (!strchr(cmdline, '*') && !strchr(cmdline, ',')) {
- long n = simple_strtol(cmdline, NULL, 0);
-
- num_nodes = split_nodes_interleave(addr, max_addr,
- num_phys_nodes, n);
- if (num_nodes < 0)
- return num_nodes;
- goto out;
- }
+ if (strchr(cmdline, 'M') || strchr(cmdline, 'G')) {
+ u64 size;
- /* Parse the command line. */
- for (coeff_flag = 0; ; cmdline++) {
- if (*cmdline && isdigit(*cmdline)) {
- num = num * 10 + *cmdline - '0';
- continue;
- }
- if (*cmdline == '*') {
- if (num > 0)
- coeff = num;
- coeff_flag = 1;
- }
- if (!*cmdline || *cmdline == ',') {
- if (!coeff_flag)
- coeff = 1;
- /*
- * 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, &addr,
- size, max_addr) < 0)
- goto done;
- if (!*cmdline)
- break;
- coeff_flag = 0;
- coeff = -1;
- }
- num = 0;
- }
-done:
- if (!num_nodes)
- return -1;
- /* Fill remainder of system RAM, if appropriate. */
- if (addr < max_addr) {
- if (coeff_flag && coeff < 0) {
- /* Split remaining nodes into num-sized chunks */
- num_nodes += split_nodes_by_size(&addr, max_addr,
- num_nodes, num);
- goto out;
- }
- switch (*(cmdline - 1)) {
- case '*':
- /* Split remaining nodes into coeff chunks */
- if (coeff <= 0)
- break;
- num_nodes += split_nodes_equally(&addr, max_addr,
- num_nodes, coeff);
- break;
- case ',':
- /* Do not allocate remaining system RAM */
- break;
- default:
- /* Give one final node */
- setup_node_range(num_nodes, &addr, max_addr - addr,
- max_addr);
- num_nodes++;
- }
+ size = memparse(cmdline, &cmdline);
+ num_nodes = split_nodes_size_interleave(addr, max_addr, size);
+ } else {
+ unsigned long n;
+
+ n = simple_strtoul(cmdline, NULL, 0);
+ num_nodes = split_nodes_interleave(addr, max_addr, num_phys_nodes, n);
}
-out:
+
+ if (num_nodes < 0)
+ return num_nodes;
memnode_shift = compute_hash_shift(nodes, num_nodes, NULL);
if (memnode_shift < 0) {
memnode_shift = 0;
for_each_online_node(i)
pages += free_all_bootmem_node(NODE_DATA(i));
+ #ifdef CONFIG_NO_BOOTMEM
+ pages += free_all_memory_core_early(MAX_NUMNODES);
+ #endif
+
return pages;
}
#include <linux/init.h>
#include <linux/pci.h>
+ #include <linux/range.h>
#include "bus_numa.h"
int pci_root_num;
struct pci_root_info pci_root_info[PCI_ROOT_NR];
- int found_all_numa_early;
void x86_pci_root_bus_res_quirks(struct pci_bus *b)
{
if (!pci_root_num)
return;
- /* for amd, if only one root bus, don't need to do anything */
- if (pci_root_num < 2 && found_all_numa_early)
- return;
-
for (i = 0; i < pci_root_num; i++) {
if (pci_root_info[i].bus_min == b->number)
break;
printk(KERN_DEBUG "PCI: peer root bus %02x res updated from pci conf\n",
b->number);
+ pci_bus_remove_resources(b);
info = &pci_root_info[i];
for (j = 0; j < info->res_num; j++) {
struct resource *res;
struct resource *root;
res = &info->res[j];
- b->resource[j] = res;
+ pci_bus_add_resource(b, res, 0);
if (res->flags & IORESOURCE_IO)
root = &ioport_resource;
else
}
}
- void __devinit update_res(struct pci_root_info *info, size_t start,
- size_t end, unsigned long flags, int merge)
+ void __devinit update_res(struct pci_root_info *info, resource_size_t start,
+ resource_size_t end, unsigned long flags, int merge)
{
int i;
struct resource *res;
if (start > end)
return;
+ if (start == MAX_RESOURCE)
+ return;
+
if (!merge)
goto addit;
/* try to merge it with old one */
for (i = 0; i < info->res_num; i++) {
- size_t final_start, final_end;
- size_t common_start, common_end;
+ resource_size_t final_start, final_end;
+ resource_size_t common_start, common_end;
res = &info->res[i];
if (res->flags != flags)
continue;
- common_start = max((size_t)res->start, start);
- common_end = min((size_t)res->end, end);
+ common_start = max(res->start, start);
+ common_end = min(res->end, end);
if (common_start > common_end + 1)
continue;
- final_start = min((size_t)res->start, start);
- final_end = max((size_t)res->end, end);
+ final_start = min(res->start, start);
+ final_end = max(res->end, end);
res->start = final_start;
res->end = final_end;
- #ifdef CONFIG_X86_64
-
+ #ifndef __BUS_NUMA_H
+ #define __BUS_NUMA_H
/*
* sub bus (transparent) will use entres from 3 to store extra from
- * root, so need to make sure we have enough slot there, Should we
- * increase PCI_BUS_NUM_RESOURCES?
+ * root, so need to make sure we have enough slot there.
*/
#define RES_NUM 16
struct pci_root_info {
#define PCI_ROOT_NR 4
extern int pci_root_num;
extern struct pci_root_info pci_root_info[PCI_ROOT_NR];
- extern int found_all_numa_early;
- extern void update_res(struct pci_root_info *info, size_t start,
- size_t end, unsigned long flags, int merge);
+ extern void update_res(struct pci_root_info *info, resource_size_t start,
+ resource_size_t end, unsigned long flags, int merge);
#endif
* but we want to try to avoid allocating at 0x2900-0x2bff
* which might have be mirrored at 0x0100-0x03ff..
*/
-void
-pcibios_align_resource(void *data, struct resource *res,
+resource_size_t
+pcibios_align_resource(void *data, const struct resource *res,
resource_size_t size, resource_size_t align)
{
struct pci_dev *dev = data;
+ resource_size_t start = res->start;
if (res->flags & IORESOURCE_IO) {
- resource_size_t start = res->start;
-
if (skip_isa_ioresource_align(dev))
- return;
- if (start & 0x300) {
+ return start;
+ if (start & 0x300)
start = (start + 0x3ff) & ~0x3ff;
- res->start = start;
- }
}
+ return start;
}
EXPORT_SYMBOL(pcibios_align_resource);
*/
fs_initcall(pcibios_assign_resources);
- void __weak x86_pci_root_bus_res_quirks(struct pci_bus *b)
- {
- }
-
/*
* If we set up a device for bus mastering, we need to check the latency
* timer as certain crappy BIOSes forget to set it properly.
#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]) + __must_be_array(arr))
+ /*
+ * This looks more complex than it should be. But we need to
+ * get the type for the ~ right in round_down (it needs to be
+ * as wide as the result!), and we want to evaluate the macro
+ * arguments just once each.
+ */
+ #define __round_mask(x, y) ((__typeof__(x))((y)-1))
+ #define round_up(x, y) ((((x)-1) | __round_mask(x, y))+1)
+ #define round_down(x, y) ((x) & ~__round_mask(x, y))
+
#define FIELD_SIZEOF(t, f) (sizeof(((t*)0)->f))
#define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d))
#define roundup(x, y) ((((x) + ((y) - 1)) / (y)) * (y))
#endif
#ifdef CONFIG_DEBUG_SPINLOCK_SLEEP
- void __might_sleep(char *file, int line, int preempt_offset);
+ void __might_sleep(const char *file, int line, int preempt_offset);
/**
* might_sleep - annotation for functions that can sleep
*
# define might_sleep() \
do { __might_sleep(__FILE__, __LINE__, 0); might_resched(); } while (0)
#else
- static inline void __might_sleep(char *file, int line, int preempt_offset) { }
+ static inline void __might_sleep(const char *file, int line,
+ int preempt_offset) { }
# define might_sleep() do { might_resched(); } while (0)
#endif
#include <linux/prio_tree.h>
#include <linux/debug_locks.h>
#include <linux/mm_types.h>
+ #include <linux/range.h>
struct mempolicy;
struct anon_vma;
extern unsigned long find_min_pfn_with_active_regions(void);
extern void free_bootmem_with_active_regions(int nid,
unsigned long max_low_pfn);
+ int add_from_early_node_map(struct range *range, int az,
+ int nr_range, int nid);
+ void *__alloc_memory_core_early(int nodeid, u64 size, u64 align,
+ u64 goal, u64 limit);
typedef int (*work_fn_t)(unsigned long, unsigned long, void *);
extern void work_with_active_regions(int nid, work_fn_t work_fn, void *data);
extern void sparse_memory_present_with_active_regions(int nid);
extern void si_meminfo_node(struct sysinfo *val, int nid);
extern int after_bootmem;
-#ifdef CONFIG_NUMA
extern void setup_per_cpu_pageset(void);
-#else
-static inline void setup_per_cpu_pageset(void) {}
-#endif
extern void zone_pcp_update(struct zone *zone);
const char * arch_vma_name(struct vm_area_struct *vma);
void print_vma_addr(char *prefix, unsigned long rip);
+ void sparse_mem_maps_populate_node(struct page **map_map,
+ unsigned long pnum_begin,
+ unsigned long pnum_end,
+ unsigned long map_count,
+ int nodeid);
+
struct page *sparse_mem_map_populate(unsigned long pnum, int nid);
pgd_t *vmemmap_pgd_populate(unsigned long addr, int node);
pud_t *vmemmap_pud_populate(pgd_t *pgd, unsigned long addr, int node);
pmd_t *vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node);
pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node);
void *vmemmap_alloc_block(unsigned long size, int node);
+ void *vmemmap_alloc_block_buf(unsigned long size, int node);
void vmemmap_verify(pte_t *, int, unsigned long, unsigned long);
int vmemmap_populate_basepages(struct page *start_page,
unsigned long pages, int node);
s8 stat_threshold;
s8 vm_stat_diff[NR_VM_ZONE_STAT_ITEMS];
#endif
-} ____cacheline_aligned_in_smp;
-
-#ifdef CONFIG_NUMA
-#define zone_pcp(__z, __cpu) ((__z)->pageset[(__cpu)])
-#else
-#define zone_pcp(__z, __cpu) (&(__z)->pageset[(__cpu)])
-#endif
+};
#endif /* !__GENERATING_BOUNDS.H */
*/
unsigned long min_unmapped_pages;
unsigned long min_slab_pages;
- struct per_cpu_pageset *pageset[NR_CPUS];
-#else
- struct per_cpu_pageset pageset[NR_CPUS];
#endif
+ struct per_cpu_pageset __percpu *pageset;
/*
* free areas of different sizes
*/
struct page_cgroup *node_page_cgroup;
#endif
#endif
+ #ifndef CONFIG_NO_BOOTMEM
struct bootmem_data *bdata;
+ #endif
#ifdef CONFIG_MEMORY_HOTPLUG
/*
* Must be held any time you expect node_start_pfn, node_present_pages
kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \
hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \
notifier.o ksysfs.o pm_qos_params.o sched_clock.o cred.o \
- async.o
+ async.o range.o
+ obj-$(CONFIG_HAVE_EARLY_RES) += early_res.o
obj-y += groups.o
ifdef CONFIG_FUNCTION_TRACER
obj-$(CONFIG_PERF_EVENTS) += perf_event.o
obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o
obj-$(CONFIG_USER_RETURN_NOTIFIER) += user-return-notifier.o
+obj-$(CONFIG_PADATA) += padata.o
ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y)
# According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is
config SPARSEMEM_VMEMMAP_ENABLE
bool
+ config SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
+ def_bool y
+ depends on SPARSEMEM && X86_64
+
config SPARSEMEM_VMEMMAP
bool "Sparse Memory virtual memmap"
depends on SPARSEMEM && SPARSEMEM_VMEMMAP_ENABLE
config NR_QUICK
int
depends on QUICKLIST
- default "2" if SUPERH || AVR32
+ default "2" if AVR32
default "1"
config VIRT_TO_BUS
struct per_cpu_pageset *pset;
struct per_cpu_pages *pcp;
- pset = zone_pcp(zone, cpu);
+ local_irq_save(flags);
+ pset = per_cpu_ptr(zone->pageset, cpu);
pcp = &pset->pcp;
- local_irq_save(flags);
free_pcppages_bulk(zone, pcp->count, pcp);
pcp->count = 0;
local_irq_restore(flags);
arch_free_page(page, 0);
kernel_map_pages(page, 1, 0);
- pcp = &zone_pcp(zone, get_cpu())->pcp;
migratetype = get_pageblock_migratetype(page);
set_page_private(page, migratetype);
local_irq_save(flags);
migratetype = MIGRATE_MOVABLE;
}
+ pcp = &this_cpu_ptr(zone->pageset)->pcp;
if (cold)
list_add_tail(&page->lru, &pcp->lists[migratetype]);
else
out:
local_irq_restore(flags);
- put_cpu();
}
void free_hot_page(struct page *page)
unsigned long flags;
struct page *page;
int cold = !!(gfp_flags & __GFP_COLD);
- int cpu;
again:
- cpu = get_cpu();
if (likely(order == 0)) {
struct per_cpu_pages *pcp;
struct list_head *list;
- pcp = &zone_pcp(zone, cpu)->pcp;
- list = &pcp->lists[migratetype];
local_irq_save(flags);
+ pcp = &this_cpu_ptr(zone->pageset)->pcp;
+ list = &pcp->lists[migratetype];
if (list_empty(list)) {
pcp->count += rmqueue_bulk(zone, 0,
pcp->batch, list,
__count_zone_vm_events(PGALLOC, zone, 1 << order);
zone_statistics(preferred_zone, zone);
local_irq_restore(flags);
- put_cpu();
VM_BUG_ON(bad_range(zone, page));
if (prep_new_page(page, order, gfp_flags))
failed:
local_irq_restore(flags);
- put_cpu();
return NULL;
}
for_each_online_cpu(cpu) {
struct per_cpu_pageset *pageset;
- pageset = zone_pcp(zone, cpu);
+ pageset = per_cpu_ptr(zone->pageset, cpu);
printk("CPU %4d: hi:%5d, btch:%4d usd:%4d\n",
cpu, pageset->pcp.high,
#endif /* CONFIG_NUMA */
+/*
+ * Boot pageset table. One per cpu which is going to be used for all
+ * zones and all nodes. The parameters will be set in such a way
+ * that an item put on a list will immediately be handed over to
+ * the buddy list. This is safe since pageset manipulation is done
+ * with interrupts disabled.
+ *
+ * The boot_pagesets must be kept even after bootup is complete for
+ * unused processors and/or zones. They do play a role for bootstrapping
+ * hotplugged processors.
+ *
+ * zoneinfo_show() and maybe other functions do
+ * not check if the processor is online before following the pageset pointer.
+ * Other parts of the kernel may not check if the zone is available.
+ */
+static void setup_pageset(struct per_cpu_pageset *p, unsigned long batch);
+static DEFINE_PER_CPU(struct per_cpu_pageset, boot_pageset);
+
/* return values int ....just for stop_machine() */
static int __build_all_zonelists(void *dummy)
{
int nid;
+ int cpu;
#ifdef CONFIG_NUMA
memset(node_load, 0, sizeof(node_load));
build_zonelists(pgdat);
build_zonelist_cache(pgdat);
}
+
+ /*
+ * Initialize the boot_pagesets that are going to be used
+ * for bootstrapping processors. The real pagesets for
+ * each zone will be allocated later when the per cpu
+ * allocator is available.
+ *
+ * boot_pagesets are used also for bootstrapping offline
+ * cpus if the system is already booted because the pagesets
+ * are needed to initialize allocators on a specific cpu too.
+ * F.e. the percpu allocator needs the page allocator which
+ * needs the percpu allocator in order to allocate its pagesets
+ * (a chicken-egg dilemma).
+ */
+ for_each_possible_cpu(cpu)
+ setup_pageset(&per_cpu(boot_pageset, cpu), 0);
+
return 0;
}
pcp->batch = PAGE_SHIFT * 8;
}
-
-#ifdef CONFIG_NUMA
-/*
- * Boot pageset table. One per cpu which is going to be used for all
- * zones and all nodes. The parameters will be set in such a way
- * that an item put on a list will immediately be handed over to
- * the buddy list. This is safe since pageset manipulation is done
- * with interrupts disabled.
- *
- * Some NUMA counter updates may also be caught by the boot pagesets.
- *
- * The boot_pagesets must be kept even after bootup is complete for
- * unused processors and/or zones. They do play a role for bootstrapping
- * hotplugged processors.
- *
- * zoneinfo_show() and maybe other functions do
- * not check if the processor is online before following the pageset pointer.
- * Other parts of the kernel may not check if the zone is available.
- */
-static struct per_cpu_pageset boot_pageset[NR_CPUS];
-
/*
- * Dynamically allocate memory for the
- * per cpu pageset array in struct zone.
+ * Allocate per cpu pagesets and initialize them.
+ * Before this call only boot pagesets were available.
+ * Boot pagesets will no longer be used by this processorr
+ * after setup_per_cpu_pageset().
*/
-static int __cpuinit process_zones(int cpu)
+void __init setup_per_cpu_pageset(void)
{
- struct zone *zone, *dzone;
- int node = cpu_to_node(cpu);
-
- node_set_state(node, N_CPU); /* this node has a cpu */
+ struct zone *zone;
+ int cpu;
for_each_populated_zone(zone) {
- zone_pcp(zone, cpu) = kmalloc_node(sizeof(struct per_cpu_pageset),
- GFP_KERNEL, node);
- if (!zone_pcp(zone, cpu))
- goto bad;
-
- setup_pageset(zone_pcp(zone, cpu), zone_batchsize(zone));
-
- if (percpu_pagelist_fraction)
- setup_pagelist_highmark(zone_pcp(zone, cpu),
- (zone->present_pages / percpu_pagelist_fraction));
- }
-
- return 0;
-bad:
- for_each_zone(dzone) {
- if (!populated_zone(dzone))
- continue;
- if (dzone == zone)
- break;
- kfree(zone_pcp(dzone, cpu));
- zone_pcp(dzone, cpu) = &boot_pageset[cpu];
- }
- return -ENOMEM;
-}
+ zone->pageset = alloc_percpu(struct per_cpu_pageset);
-static inline void free_zone_pagesets(int cpu)
-{
- struct zone *zone;
-
- for_each_zone(zone) {
- struct per_cpu_pageset *pset = zone_pcp(zone, cpu);
+ for_each_possible_cpu(cpu) {
+ struct per_cpu_pageset *pcp = per_cpu_ptr(zone->pageset, cpu);
- /* Free per_cpu_pageset if it is slab allocated */
- if (pset != &boot_pageset[cpu])
- kfree(pset);
- zone_pcp(zone, cpu) = &boot_pageset[cpu];
- }
-}
+ setup_pageset(pcp, zone_batchsize(zone));
-static int __cpuinit pageset_cpuup_callback(struct notifier_block *nfb,
- unsigned long action,
- void *hcpu)
-{
- int cpu = (long)hcpu;
- int ret = NOTIFY_OK;
-
- switch (action) {
- case CPU_UP_PREPARE:
- case CPU_UP_PREPARE_FROZEN:
- if (process_zones(cpu))
- ret = NOTIFY_BAD;
- break;
- case CPU_UP_CANCELED:
- case CPU_UP_CANCELED_FROZEN:
- case CPU_DEAD:
- case CPU_DEAD_FROZEN:
- free_zone_pagesets(cpu);
- break;
- default:
- break;
+ if (percpu_pagelist_fraction)
+ setup_pagelist_highmark(pcp,
+ (zone->present_pages /
+ percpu_pagelist_fraction));
+ }
}
- return ret;
}
-static struct notifier_block __cpuinitdata pageset_notifier =
- { &pageset_cpuup_callback, NULL, 0 };
-
-void __init setup_per_cpu_pageset(void)
-{
- int err;
-
- /* Initialize per_cpu_pageset for cpu 0.
- * A cpuup callback will do this for every cpu
- * as it comes online
- */
- err = process_zones(smp_processor_id());
- BUG_ON(err);
- register_cpu_notifier(&pageset_notifier);
-}
-
-#endif
-
static noinline __init_refok
int zone_wait_table_init(struct zone *zone, unsigned long zone_size_pages)
{
struct per_cpu_pageset *pset;
struct per_cpu_pages *pcp;
- pset = zone_pcp(zone, cpu);
+ pset = per_cpu_ptr(zone->pageset, cpu);
pcp = &pset->pcp;
local_irq_save(flags);
static __meminit void zone_pcp_init(struct zone *zone)
{
- int cpu;
- unsigned long batch = zone_batchsize(zone);
+ /*
+ * per cpu subsystem is not up at this point. The following code
+ * relies on the ability of the linker to provide the
+ * offset of a (static) per cpu variable into the per cpu area.
+ */
+ zone->pageset = &boot_pageset;
- for (cpu = 0; cpu < NR_CPUS; cpu++) {
-#ifdef CONFIG_NUMA
- /* Early boot. Slab allocator not functional yet */
- zone_pcp(zone, cpu) = &boot_pageset[cpu];
- setup_pageset(&boot_pageset[cpu],0);
-#else
- setup_pageset(zone_pcp(zone,cpu), batch);
-#endif
- }
if (zone->present_pages)
- printk(KERN_DEBUG " %s zone: %lu pages, LIFO batch:%lu\n",
- zone->name, zone->present_pages, batch);
+ printk(KERN_DEBUG " %s zone: %lu pages, LIFO batch:%u\n",
+ zone->name, zone->present_pages,
+ zone_batchsize(zone));
}
__meminit int init_currently_empty_zone(struct zone *zone,
}
}
+ int __init add_from_early_node_map(struct range *range, int az,
+ int nr_range, int nid)
+ {
+ int i;
+ u64 start, end;
+
+ /* need to go over early_node_map to find out good range for node */
+ for_each_active_range_index_in_nid(i, nid) {
+ start = early_node_map[i].start_pfn;
+ end = early_node_map[i].end_pfn;
+ nr_range = add_range(range, az, nr_range, start, end);
+ }
+ return nr_range;
+ }
+
+ #ifdef CONFIG_NO_BOOTMEM
+ void * __init __alloc_memory_core_early(int nid, u64 size, u64 align,
+ u64 goal, u64 limit)
+ {
+ int i;
+ void *ptr;
+
+ /* need to go over early_node_map to find out good range for node */
+ for_each_active_range_index_in_nid(i, nid) {
+ u64 addr;
+ u64 ei_start, ei_last;
+
+ ei_last = early_node_map[i].end_pfn;
+ ei_last <<= PAGE_SHIFT;
+ ei_start = early_node_map[i].start_pfn;
+ ei_start <<= PAGE_SHIFT;
+ addr = find_early_area(ei_start, ei_last,
+ goal, limit, size, align);
+
+ if (addr == -1ULL)
+ continue;
+
+ #if 0
+ printk(KERN_DEBUG "alloc (nid=%d %llx - %llx) (%llx - %llx) %llx %llx => %llx\n",
+ nid,
+ ei_start, ei_last, goal, limit, size,
+ align, addr);
+ #endif
+
+ ptr = phys_to_virt(addr);
+ memset(ptr, 0, size);
+ reserve_early_without_check(addr, addr + size, "BOOTMEM");
+ return ptr;
+ }
+
+ return NULL;
+ }
+ #endif
+
+
void __init work_with_active_regions(int nid, work_fn_t work_fn, void *data)
{
int i;
}
#ifndef CONFIG_NEED_MULTIPLE_NODES
- struct pglist_data __refdata contig_page_data = { .bdata = &bootmem_node_data[0] };
+ struct pglist_data __refdata contig_page_data = {
+ #ifndef CONFIG_NO_BOOTMEM
+ .bdata = &bootmem_node_data[0]
+ #endif
+ };
EXPORT_SYMBOL(contig_page_data);
#endif
if (!write || (ret == -EINVAL))
return ret;
for_each_populated_zone(zone) {
- for_each_online_cpu(cpu) {
+ for_each_possible_cpu(cpu) {
unsigned long high;
high = zone->present_pages / percpu_pagelist_fraction;
- setup_pagelist_highmark(zone_pcp(zone, cpu), high);
+ setup_pagelist_highmark(
+ per_cpu_ptr(zone->pageset, cpu), high);
}
}
return 0;