aboutsummaryrefslogtreecommitdiff
path: root/arch/x86_64/mm
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86_64/mm')
-rw-r--r--arch/x86_64/mm/fault.c10
-rw-r--r--arch/x86_64/mm/init.c79
-rw-r--r--arch/x86_64/mm/k8topology.c13
-rw-r--r--arch/x86_64/mm/numa.c9
-rw-r--r--arch/x86_64/mm/srat.c68
5 files changed, 80 insertions, 99 deletions
diff --git a/arch/x86_64/mm/fault.c b/arch/x86_64/mm/fault.c
index 816732d8858..b75b872ec15 100644
--- a/arch/x86_64/mm/fault.c
+++ b/arch/x86_64/mm/fault.c
@@ -221,12 +221,13 @@ int unhandled_signal(struct task_struct *tsk, int sig)
static noinline void pgtable_bad(unsigned long address, struct pt_regs *regs,
unsigned long error_code)
{
- oops_begin();
+ unsigned long flags = oops_begin();
+
printk(KERN_ALERT "%s: Corrupted page table at address %lx\n",
current->comm, address);
dump_pagetable(address);
__die("Bad pagetable", regs, error_code);
- oops_end();
+ oops_end(flags);
do_exit(SIGKILL);
}
@@ -304,6 +305,7 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
unsigned long address;
const struct exception_table_entry *fixup;
int write;
+ unsigned long flags;
siginfo_t info;
#ifdef CONFIG_CHECKING
@@ -521,7 +523,7 @@ no_context:
* terminate things with extreme prejudice.
*/
- oops_begin();
+ flags = oops_begin();
if (address < PAGE_SIZE)
printk(KERN_ALERT "Unable to handle kernel NULL pointer dereference");
@@ -534,7 +536,7 @@ no_context:
__die("Oops", regs, error_code);
/* Executive summary in case the body of the oops scrolled away */
printk(KERN_EMERG "CR2: %016lx\n", address);
- oops_end();
+ oops_end(flags);
do_exit(SIGKILL);
/*
diff --git a/arch/x86_64/mm/init.c b/arch/x86_64/mm/init.c
index aa4a5189ece..e60a1a848de 100644
--- a/arch/x86_64/mm/init.c
+++ b/arch/x86_64/mm/init.c
@@ -57,31 +57,31 @@ DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
void show_mem(void)
{
- int i, total = 0, reserved = 0;
- int shared = 0, cached = 0;
+ long i, total = 0, reserved = 0;
+ long shared = 0, cached = 0;
pg_data_t *pgdat;
struct page *page;
- printk("Mem-info:\n");
+ printk(KERN_INFO "Mem-info:\n");
show_free_areas();
- printk("Free swap: %6ldkB\n", nr_swap_pages<<(PAGE_SHIFT-10));
+ printk(KERN_INFO "Free swap: %6ldkB\n", nr_swap_pages<<(PAGE_SHIFT-10));
for_each_pgdat(pgdat) {
for (i = 0; i < pgdat->node_spanned_pages; ++i) {
page = pfn_to_page(pgdat->node_start_pfn + i);
total++;
- if (PageReserved(page))
- reserved++;
- else if (PageSwapCache(page))
- cached++;
- else if (page_count(page))
- shared += page_count(page) - 1;
+ if (PageReserved(page))
+ reserved++;
+ else if (PageSwapCache(page))
+ cached++;
+ else if (page_count(page))
+ shared += page_count(page) - 1;
}
}
- printk("%d pages of RAM\n", total);
- printk("%d reserved pages\n",reserved);
- printk("%d pages shared\n",shared);
- printk("%d pages swap cached\n",cached);
+ printk(KERN_INFO "%lu pages of RAM\n", total);
+ printk(KERN_INFO "%lu reserved pages\n",reserved);
+ printk(KERN_INFO "%lu pages shared\n",shared);
+ printk(KERN_INFO "%lu pages swap cached\n",cached);
}
/* References to section boundaries */
@@ -381,41 +381,14 @@ void __init clear_kernel_mapping(unsigned long address, unsigned long size)
__flush_tlb_all();
}
-static inline int page_is_ram (unsigned long pagenr)
-{
- int i;
-
- for (i = 0; i < e820.nr_map; i++) {
- unsigned long addr, end;
-
- if (e820.map[i].type != E820_RAM) /* not usable memory */
- continue;
- /*
- * !!!FIXME!!! Some BIOSen report areas as RAM that
- * are not. Notably the 640->1Mb area. We need a sanity
- * check here.
- */
- addr = (e820.map[i].addr+PAGE_SIZE-1) >> PAGE_SHIFT;
- end = (e820.map[i].addr+e820.map[i].size) >> PAGE_SHIFT;
- if ((pagenr >= addr) && (pagenr < end))
- return 1;
- }
- return 0;
-}
-
-extern int swiotlb_force;
-
static struct kcore_list kcore_mem, kcore_vmalloc, kcore_kernel, kcore_modules,
kcore_vsyscall;
void __init mem_init(void)
{
- int codesize, reservedpages, datasize, initsize;
- int tmp;
+ long codesize, reservedpages, datasize, initsize;
#ifdef CONFIG_SWIOTLB
- if (swiotlb_force)
- swiotlb = 1;
if (!iommu_aperture &&
(end_pfn >= 0xffffffff>>PAGE_SHIFT || force_iommu))
swiotlb = 1;
@@ -436,25 +409,11 @@ void __init mem_init(void)
/* this will put all low memory onto the freelists */
#ifdef CONFIG_NUMA
- totalram_pages += numa_free_all_bootmem();
- tmp = 0;
- /* should count reserved pages here for all nodes */
+ totalram_pages = numa_free_all_bootmem();
#else
-
-#ifdef CONFIG_FLATMEM
- max_mapnr = end_pfn;
- if (!mem_map) BUG();
-#endif
-
- totalram_pages += free_all_bootmem();
-
- for (tmp = 0; tmp < end_pfn; tmp++)
- /*
- * Only count reserved RAM pages
- */
- if (page_is_ram(tmp) && PageReserved(pfn_to_page(tmp)))
- reservedpages++;
+ totalram_pages = free_all_bootmem();
#endif
+ reservedpages = end_pfn - totalram_pages - e820_hole_size(0, end_pfn);
after_bootmem = 1;
@@ -471,7 +430,7 @@ void __init mem_init(void)
kclist_add(&kcore_vsyscall, (void *)VSYSCALL_START,
VSYSCALL_END - VSYSCALL_START);
- printk("Memory: %luk/%luk available (%dk kernel code, %dk reserved, %dk data, %dk init)\n",
+ printk("Memory: %luk/%luk available (%ldk kernel code, %ldk reserved, %ldk data, %ldk init)\n",
(unsigned long) nr_free_pages() << (PAGE_SHIFT-10),
end_pfn << (PAGE_SHIFT-10),
codesize >> 10,
diff --git a/arch/x86_64/mm/k8topology.c b/arch/x86_64/mm/k8topology.c
index ec35747aacd..65417b040c1 100644
--- a/arch/x86_64/mm/k8topology.c
+++ b/arch/x86_64/mm/k8topology.c
@@ -45,10 +45,12 @@ int __init k8_scan_nodes(unsigned long start, unsigned long end)
unsigned long prevbase;
struct node nodes[8];
int nodeid, i, nb;
+ unsigned char nodeids[8];
int found = 0;
u32 reg;
unsigned numnodes;
nodemask_t nodes_parsed;
+ unsigned dualcore = 0;
nodes_clear(nodes_parsed);
@@ -67,11 +69,15 @@ int __init k8_scan_nodes(unsigned long start, unsigned long end)
prevbase = 0;
for (i = 0; i < 8; i++) {
unsigned long base,limit;
-
+ u32 nodeid;
+
+ /* Undefined before E stepping, but hopefully 0 */
+ dualcore |= ((read_pci_config(0, nb, 3, 0xe8) >> 12) & 3) == 1;
base = read_pci_config(0, nb, 1, 0x40 + i*8);
limit = read_pci_config(0, nb, 1, 0x44 + i*8);
nodeid = limit & 7;
+ nodeids[i] = nodeid;
if ((base & 3) == 0) {
if (i < numnodes)
printk("Skipping disabled node %d\n", i);
@@ -157,8 +163,9 @@ int __init k8_scan_nodes(unsigned long start, unsigned long end)
for (i = 0; i < 8; i++) {
if (nodes[i].start != nodes[i].end) {
- /* assume 1:1 NODE:CPU */
- cpu_to_node[i] = i;
+ nodeid = nodeids[i];
+ apicid_to_node[nodeid << dualcore] = i;
+ apicid_to_node[(nodeid << dualcore) + dualcore] = i;
setup_node_bootmem(i, nodes[i].start, nodes[i].end);
}
}
diff --git a/arch/x86_64/mm/numa.c b/arch/x86_64/mm/numa.c
index 04f7a33e144..80a49d9bd8a 100644
--- a/arch/x86_64/mm/numa.c
+++ b/arch/x86_64/mm/numa.c
@@ -28,8 +28,13 @@ bootmem_data_t plat_node_bdata[MAX_NUMNODES];
int memnode_shift;
u8 memnodemap[NODEMAPSIZE];
-unsigned char cpu_to_node[NR_CPUS] __read_mostly = { [0 ... NR_CPUS-1] = NUMA_NO_NODE };
-cpumask_t node_to_cpumask[MAX_NUMNODES] __read_mostly;
+unsigned char cpu_to_node[NR_CPUS] __read_mostly = {
+ [0 ... NR_CPUS-1] = NUMA_NO_NODE
+};
+unsigned char apicid_to_node[MAX_LOCAL_APIC] __cpuinitdata = {
+ [0 ... MAX_LOCAL_APIC-1] = NUMA_NO_NODE
+};
+cpumask_t node_to_cpumask[MAX_NUMNODES] __read_mostly;
int numa_off __initdata;
diff --git a/arch/x86_64/mm/srat.c b/arch/x86_64/mm/srat.c
index 8e3d097a9dd..4b2e844c15a 100644
--- a/arch/x86_64/mm/srat.c
+++ b/arch/x86_64/mm/srat.c
@@ -20,14 +20,20 @@
static struct acpi_table_slit *acpi_slit;
-/* Internal processor count */
-static unsigned int __initdata num_processors = 0;
-
static nodemask_t nodes_parsed __initdata;
static nodemask_t nodes_found __initdata;
static struct node nodes[MAX_NUMNODES] __initdata;
static __u8 pxm2node[256] = { [0 ... 255] = 0xff };
+static int node_to_pxm(int n);
+
+int pxm_to_node(int pxm)
+{
+ if ((unsigned)pxm >= 256)
+ return 0;
+ return pxm2node[pxm];
+}
+
static __init int setup_node(int pxm)
{
unsigned node = pxm2node[pxm];
@@ -44,14 +50,14 @@ static __init int setup_node(int pxm)
static __init int conflicting_nodes(unsigned long start, unsigned long end)
{
int i;
- for_each_online_node(i) {
+ for_each_node_mask(i, nodes_parsed) {
struct node *nd = &nodes[i];
if (nd->start == nd->end)
continue;
if (nd->end > start && nd->start < end)
- return 1;
+ return i;
if (nd->end == end && nd->start == start)
- return 1;
+ return i;
}
return -1;
}
@@ -75,8 +81,11 @@ static __init void cutoff_node(int i, unsigned long start, unsigned long end)
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++)
+ apicid_to_node[i] = NUMA_NO_NODE;
}
static __init inline int srat_disabled(void)
@@ -104,18 +113,10 @@ acpi_numa_processor_affinity_init(struct acpi_table_processor_affinity *pa)
bad_srat();
return;
}
- if (num_processors >= NR_CPUS) {
- printk(KERN_ERR "SRAT: Processor #%d (lapic %u) INVALID. (Max ID: %d).\n",
- num_processors, pa->apic_id, NR_CPUS);
- bad_srat();
- return;
- }
- cpu_to_node[num_processors] = node;
+ apicid_to_node[pa->apic_id] = node;
acpi_numa = 1;
- printk(KERN_INFO "SRAT: PXM %u -> APIC %u -> CPU %u -> Node %u\n",
- pxm, pa->apic_id, num_processors, node);
-
- num_processors++;
+ printk(KERN_INFO "SRAT: PXM %u -> APIC %u -> Node %u\n",
+ pxm, pa->apic_id, node);
}
/* Callback for parsing of the Proximity Domain <-> Memory Area mappings */
@@ -143,10 +144,15 @@ acpi_numa_memory_affinity_init(struct acpi_table_memory_affinity *ma)
printk(KERN_INFO "SRAT: hot plug zone found %lx - %lx \n",
start, end);
i = conflicting_nodes(start, end);
- if (i >= 0) {
+ if (i == node) {
+ printk(KERN_WARNING
+ "SRAT: Warning: PXM %d (%lx-%lx) overlaps with itself (%Lx-%Lx)\n",
+ pxm, start, end, nodes[i].start, nodes[i].end);
+ } else if (i >= 0) {
printk(KERN_ERR
- "SRAT: pxm %d overlap %lx-%lx with node %d(%Lx-%Lx)\n",
- pxm, start, end, i, nodes[i].start, nodes[i].end);
+ "SRAT: PXM %d (%lx-%lx) overlaps with PXM %d (%Lx-%Lx)\n",
+ pxm, start, end, node_to_pxm(i),
+ nodes[i].start, nodes[i].end);
bad_srat();
return;
}
@@ -174,6 +180,14 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end)
int i;
if (acpi_numa <= 0)
return -1;
+
+ /* First clean up the node list */
+ for_each_node_mask(i, nodes_parsed) {
+ cutoff_node(i, start, end);
+ if (nodes[i].start == nodes[i].end)
+ node_clear(i, nodes_parsed);
+ }
+
memnode_shift = compute_hash_shift(nodes, nodes_weight(nodes_parsed));
if (memnode_shift < 0) {
printk(KERN_ERR
@@ -181,16 +195,10 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end)
bad_srat();
return -1;
}
- for (i = 0; i < MAX_NUMNODES; i++) {
- if (!node_isset(i, nodes_parsed))
- continue;
- cutoff_node(i, start, end);
- if (nodes[i].start == nodes[i].end) {
- node_clear(i, nodes_parsed);
- continue;
- }
+
+ /* Finally register nodes */
+ for_each_node_mask(i, nodes_parsed)
setup_node_bootmem(i, nodes[i].start, nodes[i].end);
- }
for (i = 0; i < NR_CPUS; i++) {
if (cpu_to_node[i] == NUMA_NO_NODE)
continue;
@@ -201,7 +209,7 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end)
return 0;
}
-int node_to_pxm(int n)
+static int node_to_pxm(int n)
{
int i;
if (pxm2node[n] == n)
generated by cgit v1.2.3 (git 2.25.1) at 2025-01-15 14:00:20 +0000