summaryrefslogtreecommitdiffstats
path: root/arch/x86/mm
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/mm')
-rw-r--r--arch/x86/mm/Makefile2
-rw-r--r--arch/x86/mm/extable.c2
-rw-r--r--arch/x86/mm/fault.c22
-rw-r--r--arch/x86/mm/init.c8
-rw-r--r--arch/x86/mm/init_32.c36
-rw-r--r--arch/x86/mm/init_64.c2
-rw-r--r--arch/x86/mm/memblock.c348
-rw-r--r--arch/x86/mm/memtest.c33
-rw-r--r--arch/x86/mm/numa.c37
-rw-r--r--arch/x86/mm/numa_32.c10
-rw-r--r--arch/x86/mm/numa_64.c2
-rw-r--r--arch/x86/mm/numa_emulation.c36
-rw-r--r--arch/x86/mm/pageattr.c2
-rw-r--r--arch/x86/mm/srat.c7
14 files changed, 99 insertions, 448 deletions
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 3d11327c9ab..23d8e5fecf7 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -27,6 +27,4 @@ obj-$(CONFIG_AMD_NUMA) += amdtopology.o
obj-$(CONFIG_ACPI_NUMA) += srat.o
obj-$(CONFIG_NUMA_EMU) += numa_emulation.o
-obj-$(CONFIG_HAVE_MEMBLOCK) += memblock.o
-
obj-$(CONFIG_MEMTEST) += memtest.o
diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c
index d0474ad2a6e..1fb85dbe390 100644
--- a/arch/x86/mm/extable.c
+++ b/arch/x86/mm/extable.c
@@ -25,7 +25,7 @@ int fixup_exception(struct pt_regs *regs)
if (fixup) {
/* If fixup is less than 16, it means uaccess error */
if (fixup->fixup < 16) {
- current_thread_info()->uaccess_err = -EFAULT;
+ current_thread_info()->uaccess_err = 1;
regs->ip += fixup->fixup;
return 1;
}
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 5db0490deb0..9d74824a708 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -626,7 +626,7 @@ pgtable_bad(struct pt_regs *regs, unsigned long error_code,
static noinline void
no_context(struct pt_regs *regs, unsigned long error_code,
- unsigned long address)
+ unsigned long address, int signal, int si_code)
{
struct task_struct *tsk = current;
unsigned long *stackend;
@@ -634,8 +634,17 @@ no_context(struct pt_regs *regs, unsigned long error_code,
int sig;
/* Are we prepared to handle this kernel fault? */
- if (fixup_exception(regs))
+ if (fixup_exception(regs)) {
+ if (current_thread_info()->sig_on_uaccess_error && signal) {
+ tsk->thread.trap_no = 14;
+ tsk->thread.error_code = error_code | PF_USER;
+ tsk->thread.cr2 = address;
+
+ /* XXX: hwpoison faults will set the wrong code. */
+ force_sig_info_fault(signal, si_code, address, tsk, 0);
+ }
return;
+ }
/*
* 32-bit:
@@ -755,7 +764,7 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
if (is_f00f_bug(regs, address))
return;
- no_context(regs, error_code, address);
+ no_context(regs, error_code, address, SIGSEGV, si_code);
}
static noinline void
@@ -819,7 +828,7 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address,
/* Kernel mode? Handle exceptions or die: */
if (!(error_code & PF_USER)) {
- no_context(regs, error_code, address);
+ no_context(regs, error_code, address, SIGBUS, BUS_ADRERR);
return;
}
@@ -854,7 +863,7 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code,
if (!(fault & VM_FAULT_RETRY))
up_read(&current->mm->mmap_sem);
if (!(error_code & PF_USER))
- no_context(regs, error_code, address);
+ no_context(regs, error_code, address, 0, 0);
return 1;
}
if (!(fault & VM_FAULT_ERROR))
@@ -864,7 +873,8 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code,
/* Kernel mode? Handle exceptions or die: */
if (!(error_code & PF_USER)) {
up_read(&current->mm->mmap_sem);
- no_context(regs, error_code, address);
+ no_context(regs, error_code, address,
+ SIGSEGV, SEGV_MAPERR);
return 1;
}
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 87488b93a65..a298914058f 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -67,7 +67,7 @@ static void __init find_early_table_space(unsigned long end, int use_pse,
good_end = max_pfn_mapped << PAGE_SHIFT;
base = memblock_find_in_range(start, good_end, tables, PAGE_SIZE);
- if (base == MEMBLOCK_ERROR)
+ if (!base)
panic("Cannot find space for the kernel page tables");
pgt_buf_start = base >> PAGE_SHIFT;
@@ -80,7 +80,7 @@ static void __init find_early_table_space(unsigned long end, int use_pse,
void __init native_pagetable_reserve(u64 start, u64 end)
{
- memblock_x86_reserve_range(start, end, "PGTABLE");
+ memblock_reserve(start, end - start);
}
struct map_range {
@@ -279,8 +279,8 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
* pgt_buf_end) and free the other ones (pgt_buf_end - pgt_buf_top)
* so that they can be reused for other purposes.
*
- * On native it just means calling memblock_x86_reserve_range, on Xen it
- * also means marking RW the pagetable pages that we allocated before
+ * On native it just means calling memblock_reserve, on Xen it also
+ * means marking RW the pagetable pages that we allocated before
* but that haven't been used.
*
* In fact on xen we mark RO the whole range pgt_buf_start -
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 29f7c6d9817..0c1da394a63 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -427,23 +427,17 @@ static void __init add_one_highpage_init(struct page *page)
void __init add_highpages_with_active_regions(int nid,
unsigned long start_pfn, unsigned long end_pfn)
{
- struct range *range;
- int nr_range;
- int i;
-
- nr_range = __get_free_all_memory_range(&range, nid, start_pfn, end_pfn);
-
- for (i = 0; i < nr_range; i++) {
- struct page *page;
- int node_pfn;
-
- for (node_pfn = range[i].start; node_pfn < range[i].end;
- node_pfn++) {
- if (!pfn_valid(node_pfn))
- continue;
- page = pfn_to_page(node_pfn);
- add_one_highpage_init(page);
- }
+ phys_addr_t start, end;
+ u64 i;
+
+ for_each_free_mem_range(i, nid, &start, &end, NULL) {
+ unsigned long pfn = clamp_t(unsigned long, PFN_UP(start),
+ start_pfn, end_pfn);
+ unsigned long e_pfn = clamp_t(unsigned long, PFN_DOWN(end),
+ start_pfn, end_pfn);
+ for ( ; pfn < e_pfn; pfn++)
+ if (pfn_valid(pfn))
+ add_one_highpage_init(pfn_to_page(pfn));
}
}
#else
@@ -650,18 +644,18 @@ void __init initmem_init(void)
highstart_pfn = highend_pfn = max_pfn;
if (max_pfn > max_low_pfn)
highstart_pfn = max_low_pfn;
- memblock_x86_register_active_regions(0, 0, highend_pfn);
- sparse_memory_present_with_active_regions(0);
printk(KERN_NOTICE "%ldMB HIGHMEM available.\n",
pages_to_mb(highend_pfn - highstart_pfn));
num_physpages = highend_pfn;
high_memory = (void *) __va(highstart_pfn * PAGE_SIZE - 1) + 1;
#else
- memblock_x86_register_active_regions(0, 0, max_low_pfn);
- sparse_memory_present_with_active_regions(0);
num_physpages = max_low_pfn;
high_memory = (void *) __va(max_low_pfn * PAGE_SIZE - 1) + 1;
#endif
+
+ memblock_set_node(0, (phys_addr_t)ULLONG_MAX, 0);
+ sparse_memory_present_with_active_regions(0);
+
#ifdef CONFIG_FLATMEM
max_mapnr = num_physpages;
#endif
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index bbaaa005bf0..a8a56ce3a96 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -608,7 +608,7 @@ kernel_physical_mapping_init(unsigned long start,
#ifndef CONFIG_NUMA
void __init initmem_init(void)
{
- memblock_x86_register_active_regions(0, 0, max_pfn);
+ memblock_set_node(0, (phys_addr_t)ULLONG_MAX, 0);
}
#endif
diff --git a/arch/x86/mm/memblock.c b/arch/x86/mm/memblock.c
deleted file mode 100644
index 992da5ec5a6..00000000000
--- a/arch/x86/mm/memblock.c
+++ /dev/null
@@ -1,348 +0,0 @@
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/init.h>
-#include <linux/bitops.h>
-#include <linux/memblock.h>
-#include <linux/bootmem.h>
-#include <linux/mm.h>
-#include <linux/range.h>
-
-/* Check for already reserved areas */
-bool __init memblock_x86_check_reserved_size(u64 *addrp, u64 *sizep, u64 align)
-{
- struct memblock_region *r;
- u64 addr = *addrp, last;
- u64 size = *sizep;
- bool changed = false;
-
-again:
- last = addr + size;
- for_each_memblock(reserved, r) {
- if (last > r->base && addr < r->base) {
- size = r->base - addr;
- changed = true;
- goto again;
- }
- if (last > (r->base + r->size) && addr < (r->base + r->size)) {
- addr = round_up(r->base + r->size, align);
- size = last - addr;
- changed = true;
- goto again;
- }
- if (last <= (r->base + r->size) && addr >= r->base) {
- *sizep = 0;
- return false;
- }
- }
- if (changed) {
- *addrp = addr;
- *sizep = size;
- }
- return changed;
-}
-
-/*
- * Find next free range after start, and size is returned in *sizep
- */
-u64 __init memblock_x86_find_in_range_size(u64 start, u64 *sizep, u64 align)
-{
- struct memblock_region *r;
-
- for_each_memblock(memory, r) {
- u64 ei_start = r->base;
- u64 ei_last = ei_start + r->size;
- u64 addr;
-
- addr = round_up(ei_start, align);
- if (addr < start)
- addr = round_up(start, align);
- if (addr >= ei_last)
- continue;
- *sizep = ei_last - addr;
- while (memblock_x86_check_reserved_size(&addr, sizep, align))
- ;
-
- if (*sizep)
- return addr;
- }
-
- return MEMBLOCK_ERROR;
-}
-
-static __init struct range *find_range_array(int count)
-{
- u64 end, size, mem;
- struct range *range;
-
- size = sizeof(struct range) * count;
- end = memblock.current_limit;
-
- mem = memblock_find_in_range(0, end, size, sizeof(struct range));
- if (mem == MEMBLOCK_ERROR)
- panic("can not find more space for range array");
-
- /*
- * This range is tempoaray, so don't reserve it, it will not be
- * overlapped because We will not alloccate new buffer before
- * We discard this one
- */
- range = __va(mem);
- memset(range, 0, size);
-
- return range;
-}
-
-static void __init memblock_x86_subtract_reserved(struct range *range, int az)
-{
- u64 final_start, final_end;
- struct memblock_region *r;
-
- /* Take out region array itself at first*/
- memblock_free_reserved_regions();
-
- memblock_dbg("Subtract (%ld early reservations)\n", memblock.reserved.cnt);
-
- for_each_memblock(reserved, r) {
- memblock_dbg(" [%010llx-%010llx]\n", (u64)r->base, (u64)r->base + r->size - 1);
- final_start = PFN_DOWN(r->base);
- final_end = PFN_UP(r->base + r->size);
- if (final_start >= final_end)
- continue;
- subtract_range(range, az, final_start, final_end);
- }
-
- /* Put region array back ? */
- memblock_reserve_reserved_regions();
-}
-
-struct count_data {
- int nr;
-};
-
-static int __init count_work_fn(unsigned long start_pfn,
- unsigned long end_pfn, void *datax)
-{
- struct count_data *data = datax;
-
- data->nr++;
-
- return 0;
-}
-
-static int __init count_early_node_map(int nodeid)
-{
- struct count_data data;
-
- data.nr = 0;
- work_with_active_regions(nodeid, count_work_fn, &data);
-
- return data.nr;
-}
-
-int __init __get_free_all_memory_range(struct range **rangep, int nodeid,
- unsigned long start_pfn, unsigned long end_pfn)
-{
- int count;
- struct range *range;
- int nr_range;
-
- count = (memblock.reserved.cnt + count_early_node_map(nodeid)) * 2;
-
- range = find_range_array(count);
- nr_range = 0;
-
- /*
- * Use early_node_map[] and memblock.reserved.region to get range array
- * at first
- */
- nr_range = add_from_early_node_map(range, count, nr_range, nodeid);
- subtract_range(range, count, 0, start_pfn);
- subtract_range(range, count, end_pfn, -1ULL);
-
- memblock_x86_subtract_reserved(range, count);
- nr_range = clean_sort_range(range, count);
-
- *rangep = range;
- return nr_range;
-}
-
-int __init get_free_all_memory_range(struct range **rangep, int nodeid)
-{
- unsigned long end_pfn = -1UL;
-
-#ifdef CONFIG_X86_32
- end_pfn = max_low_pfn;
-#endif
- return __get_free_all_memory_range(rangep, nodeid, 0, end_pfn);
-}
-
-static u64 __init __memblock_x86_memory_in_range(u64 addr, u64 limit, bool get_free)
-{
- int i, count;
- struct range *range;
- int nr_range;
- u64 final_start, final_end;
- u64 free_size;
- struct memblock_region *r;
-
- count = (memblock.reserved.cnt + memblock.memory.cnt) * 2;
-
- range = find_range_array(count);
- nr_range = 0;
-
- addr = PFN_UP(addr);
- limit = PFN_DOWN(limit);
-
- for_each_memblock(memory, r) {
- final_start = PFN_UP(r->base);
- final_end = PFN_DOWN(r->base + r->size);
- if (final_start >= final_end)
- continue;
- if (final_start >= limit || final_end <= addr)
- continue;
-
- nr_range = add_range(range, count, nr_range, final_start, final_end);
- }
- subtract_range(range, count, 0, addr);
- subtract_range(range, count, limit, -1ULL);
-
- /* Subtract memblock.reserved.region in range ? */
- if (!get_free)
- goto sort_and_count_them;
- for_each_memblock(reserved, r) {
- final_start = PFN_DOWN(r->base);
- final_end = PFN_UP(r->base + r->size);
- if (final_start >= final_end)
- continue;
- if (final_start >= limit || final_end <= addr)
- continue;
-
- subtract_range(range, count, final_start, final_end);
- }
-
-sort_and_count_them:
- nr_range = clean_sort_range(range, count);
-
- free_size = 0;
- for (i = 0; i < nr_range; i++)
- free_size += range[i].end - range[i].start;
-
- return free_size << PAGE_SHIFT;
-}
-
-u64 __init memblock_x86_free_memory_in_range(u64 addr, u64 limit)
-{
- return __memblock_x86_memory_in_range(addr, limit, true);
-}
-
-u64 __init memblock_x86_memory_in_range(u64 addr, u64 limit)
-{
- return __memblock_x86_memory_in_range(addr, limit, false);
-}
-
-void __init memblock_x86_reserve_range(u64 start, u64 end, char *name)
-{
- if (start == end)
- return;
-
- if (WARN_ONCE(start > end, "memblock_x86_reserve_range: wrong range [%#llx, %#llx)\n", start, end))
- return;
-
- memblock_dbg(" memblock_x86_reserve_range: [%#010llx-%#010llx] %16s\n", start, end - 1, name);
-
- memblock_reserve(start, end - start);
-}
-
-void __init memblock_x86_free_range(u64 start, u64 end)
-{
- if (start == end)
- return;
-
- if (WARN_ONCE(start > end, "memblock_x86_free_range: wrong range [%#llx, %#llx)\n", start, end))
- return;
-
- memblock_dbg(" memblock_x86_free_range: [%#010llx-%#010llx]\n", start, end - 1);
-
- memblock_free(start, end - start);
-}
-
-/*
- * Need to call this function after memblock_x86_register_active_regions,
- * so early_node_map[] is filled already.
- */
-u64 __init memblock_x86_find_in_range_node(int nid, u64 start, u64 end, u64 size, u64 align)
-{
- u64 addr;
- addr = find_memory_core_early(nid, size, align, start, end);
- if (addr != MEMBLOCK_ERROR)
- return addr;
-
- /* Fallback, should already have start end within node range */
- return memblock_find_in_range(start, end, size, align);
-}
-
-/*
- * Finds an active region in the address range from start_pfn to last_pfn and
- * returns its range in ei_startpfn and ei_endpfn for the memblock entry.
- */
-static int __init memblock_x86_find_active_region(const struct memblock_region *ei,
- unsigned long start_pfn,
- unsigned long last_pfn,
- unsigned long *ei_startpfn,
- unsigned long *ei_endpfn)
-{
- u64 align = PAGE_SIZE;
-
- *ei_startpfn = round_up(ei->base, align) >> PAGE_SHIFT;
- *ei_endpfn = round_down(ei->base + ei->size, align) >> PAGE_SHIFT;
-
- /* Skip map entries smaller than a page */
- if (*ei_startpfn >= *ei_endpfn)
- return 0;
-
- /* Skip if map is outside the node */
- if (*ei_endpfn <= start_pfn || *ei_startpfn >= last_pfn)
- return 0;
-
- /* Check for overlaps */
- if (*ei_startpfn < start_pfn)
- *ei_startpfn = start_pfn;
- if (*ei_endpfn > last_pfn)
- *ei_endpfn = last_pfn;
-
- return 1;
-}
-
-/* Walk the memblock.memory map and register active regions within a node */
-void __init memblock_x86_register_active_regions(int nid, unsigned long start_pfn,
- unsigned long last_pfn)
-{
- unsigned long ei_startpfn;
- unsigned long ei_endpfn;
- struct memblock_region *r;
-
- for_each_memblock(memory, r)
- if (memblock_x86_find_active_region(r, start_pfn, last_pfn,
- &ei_startpfn, &ei_endpfn))
- add_active_range(nid, ei_startpfn, ei_endpfn);
-}
-
-/*
- * Find the hole size (in bytes) in the memory range.
- * @start: starting address of the memory range to scan
- * @end: ending address of the memory range to scan
- */
-u64 __init memblock_x86_hole_size(u64 start, u64 end)
-{
- unsigned long start_pfn = start >> PAGE_SHIFT;
- unsigned long last_pfn = end >> PAGE_SHIFT;
- unsigned long ei_startpfn, ei_endpfn, ram = 0;
- struct memblock_region *r;
-
- for_each_memblock(memory, r)
- if (memblock_x86_find_active_region(r, start_pfn, last_pfn,
- &ei_startpfn, &ei_endpfn))
- ram += ei_endpfn - ei_startpfn;
-
- return end - start - ((u64)ram << PAGE_SHIFT);
-}
diff --git a/arch/x86/mm/memtest.c b/arch/x86/mm/memtest.c
index 92faf3a1c53..c80b9fb9573 100644
--- a/arch/x86/mm/memtest.c
+++ b/arch/x86/mm/memtest.c
@@ -34,7 +34,7 @@ static void __init reserve_bad_mem(u64 pattern, u64 start_bad, u64 end_bad)
(unsigned long long) pattern,
(unsigned long long) start_bad,
(unsigned long long) end_bad);
- memblock_x86_reserve_range(start_bad, end_bad, "BAD RAM");
+ memblock_reserve(start_bad, end_bad - start_bad);
}
static void __init memtest(u64 pattern, u64 start_phys, u64 size)
@@ -70,24 +70,19 @@ static void __init memtest(u64 pattern, u64 start_phys, u64 size)
static void __init do_one_pass(u64 pattern, u64 start, u64 end)
{
- u64 size = 0;
-
- while (start < end) {
- start = memblock_x86_find_in_range_size(start, &size, 1);
-
- /* done ? */
- if (start >= end)
- break;
- if (start + size > end)
- size = end - start;
-
- printk(KERN_INFO " %010llx - %010llx pattern %016llx\n",
- (unsigned long long) start,
- (unsigned long long) start + size,
- (unsigned long long) cpu_to_be64(pattern));
- memtest(pattern, start, size);
-
- start += size;
+ u64 i;
+ phys_addr_t this_start, this_end;
+
+ for_each_free_mem_range(i, MAX_NUMNODES, &this_start, &this_end, NULL) {
+ this_start = clamp_t(phys_addr_t, this_start, start, end);
+ this_end = clamp_t(phys_addr_t, this_end, start, end);
+ if (this_start < this_end) {
+ printk(KERN_INFO " %010llx - %010llx pattern %016llx\n",
+ (unsigned long long)this_start,
+ (unsigned long long)this_end,
+ (unsigned long long)cpu_to_be64(pattern));
+ memtest(pattern, this_start, this_end - this_start);
+ }
}
}
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index fbeaaf41661..496f494593b 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -192,8 +192,6 @@ int __init numa_add_memblk(int nid, u64 start, u64 end)
/* Initialize NODE_DATA for a node on the local memory */
static void __init setup_node_data(int nid, u64 start, u64 end)
{
- const u64 nd_low = PFN_PHYS(MAX_DMA_PFN);
- const u64 nd_high = PFN_PHYS(max_pfn_mapped);
const size_t nd_size = roundup(sizeof(pg_data_t), PAGE_SIZE);
bool remapped = false;
u64 nd_pa;
@@ -224,17 +222,12 @@ static void __init setup_node_data(int nid, u64 start, u64 end)
nd_pa = __pa(nd);
remapped = true;
} else {
- nd_pa = memblock_x86_find_in_range_node(nid, nd_low, nd_high,
- nd_size, SMP_CACHE_BYTES);
- if (nd_pa == MEMBLOCK_ERROR)
- nd_pa = memblock_find_in_range(nd_low, nd_high,
- nd_size, SMP_CACHE_BYTES);
- if (nd_pa == MEMBLOCK_ERROR) {
+ nd_pa = memblock_alloc_nid(nd_size, SMP_CACHE_BYTES, nid);
+ if (!nd_pa) {
pr_err("Cannot find %zu bytes in node %d\n",
nd_size, nid);
return;
}
- memblock_x86_reserve_range(nd_pa, nd_pa + nd_size, "NODE_DATA");
nd = __va(nd_pa);
}
@@ -371,8 +364,7 @@ void __init numa_reset_distance(void)
/* numa_distance could be 1LU marking allocation failure, test cnt */
if (numa_distance_cnt)
- memblock_x86_free_range(__pa(numa_distance),
- __pa(numa_distance) + size);
+ memblock_free(__pa(numa_distance), size);
numa_distance_cnt = 0;
numa_distance = NULL; /* enable table creation */
}
@@ -395,13 +387,13 @@ static int __init numa_alloc_distance(void)
phys = memblock_find_in_range(0, PFN_PHYS(max_pfn_mapped),
size, PAGE_SIZE);
- if (phys == MEMBLOCK_ERROR) {
+ if (!phys) {
pr_warning("NUMA: Warning: can't allocate distance table!\n");
/* don't retry until explicitly reset */
numa_distance = (void *)1LU;
return -ENOMEM;
}
- memblock_x86_reserve_range(phys, phys + size, "NUMA DIST");
+ memblock_reserve(phys, size);
numa_distance = __va(phys);
numa_distance_cnt = cnt;
@@ -482,8 +474,8 @@ static bool __init numa_meminfo_cover_memory(const struct numa_meminfo *mi)
numaram = 0;
}
- e820ram = max_pfn - (memblock_x86_hole_size(0,
- PFN_PHYS(max_pfn)) >> PAGE_SHIFT);
+ e820ram = max_pfn - absent_pages_in_range(0, max_pfn);
+
/* We seem to lose 3 pages somewhere. Allow 1M of slack. */
if ((s64)(e820ram - numaram) >= (1 << (20 - PAGE_SHIFT))) {
printk(KERN_ERR "NUMA: nodes only cover %LuMB of your %LuMB e820 RAM. Not used.\n",
@@ -505,13 +497,10 @@ static int __init numa_register_memblks(struct numa_meminfo *mi)
if (WARN_ON(nodes_empty(node_possible_map)))
return -EINVAL;
- for (i = 0; i < mi->nr_blks; i++)
- memblock_x86_register_active_regions(mi->blk[i].nid,
- mi->blk[i].start >> PAGE_SHIFT,
- mi->blk[i].end >> PAGE_SHIFT);
-
- /* for out of order entries */
- sort_node_map();
+ for (i = 0; i < mi->nr_blks; i++) {
+ struct numa_memblk *mb = &mi->blk[i];
+ memblock_set_node(mb->start, mb->end - mb->start, mb->nid);
+ }
/*
* If sections array is gonna be used for pfn -> nid mapping, check
@@ -545,6 +534,8 @@ static int __init numa_register_memblks(struct numa_meminfo *mi)
setup_node_data(nid, start, end);
}
+ /* Dump memblock with node info and return. */
+ memblock_dump_all();
return 0;
}
@@ -582,7 +573,7 @@ static int __init numa_init(int (*init_func)(void))
nodes_clear(node_possible_map);
nodes_clear(node_online_map);
memset(&numa_meminfo, 0, sizeof(numa_meminfo));
- remove_all_active_ranges();
+ WARN_ON(memblock_set_node(0, ULLONG_MAX, MAX_NUMNODES));
numa_reset_distance();
ret = init_func();
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index 3adebe7e536..534255a36b6 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -199,23 +199,23 @@ void __init init_alloc_remap(int nid, u64 start, u64 end)
/* allocate node memory and the lowmem remap area */
node_pa = memblock_find_in_range(start, end, size, LARGE_PAGE_BYTES);
- if (node_pa == MEMBLOCK_ERROR) {
+ if (!node_pa) {
pr_warning("remap_alloc: failed to allocate %lu bytes for node %d\n",
size, nid);
return;
}
- memblock_x86_reserve_range(node_pa, node_pa + size, "KVA RAM");
+ memblock_reserve(node_pa, size);
remap_pa = memblock_find_in_range(min_low_pfn << PAGE_SHIFT,
max_low_pfn << PAGE_SHIFT,
size, LARGE_PAGE_BYTES);
- if (remap_pa == MEMBLOCK_ERROR) {
+ if (!remap_pa) {
pr_warning("remap_alloc: failed to allocate %lu bytes remap area for node %d\n",
size, nid);
- memblock_x86_free_range(node_pa, node_pa + size);
+ memblock_free(node_pa, size);
return;
}
- memblock_x86_reserve_range(remap_pa, remap_pa + size, "KVA PG");
+ memblock_reserve(remap_pa, size);
remap_va = phys_to_virt(remap_pa);
/* perform actual remap */
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index dd27f401f0a..92e27119ee1 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -19,7 +19,7 @@ unsigned long __init numa_free_all_bootmem(void)
for_each_online_node(i)
pages += free_all_bootmem_node(NODE_DATA(i));
- pages += free_all_memory_core_early(MAX_NUMNODES);
+ pages += free_low_memory_core_early(MAX_NUMNODES);
return pages;
}
diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c
index d0ed086b624..46db56845f1 100644
--- a/arch/x86/mm/numa_emulation.c
+++ b/arch/x86/mm/numa_emulation.c
@@ -28,6 +28,16 @@ static int __init emu_find_memblk_by_nid(int nid, const struct numa_meminfo *mi)
return -ENOENT;
}
+static u64 mem_hole_size(u64 start, u64 end)
+{
+ unsigned long start_pfn = PFN_UP(start);
+ unsigned long end_pfn = PFN_DOWN(end);
+
+ if (start_pfn < end_pfn)
+ return PFN_PHYS(absent_pages_in_range(start_pfn, end_pfn));
+ return 0;
+}
+
/*
* Sets up nid to range from @start to @end. The return value is -errno if
* something went wrong, 0 otherwise.
@@ -89,7 +99,7 @@ static int __init split_nodes_interleave(struct numa_meminfo *ei,
* Calculate target node size. x86_32 freaks on __udivdi3() so do
* the division in ulong number of pages and convert back.
*/
- size = max_addr - addr - memblock_x86_hole_size(addr, max_addr);
+ size = max_addr - addr - mem_hole_size(addr, max_addr);
size = PFN_PHYS((unsigned long)(size >> PAGE_SHIFT) / nr_nodes);
/*
@@ -135,8 +145,7 @@ static int __init split_nodes_interleave(struct numa_meminfo *ei,
* Continue to add memory to this fake node if its
* non-reserved memory is less than the per-node size.
*/
- while (end - start -
- memblock_x86_hole_size(start, end) < size) {
+ while (end - start - mem_hole_size(start, end) < size) {
end += FAKE_NODE_MIN_SIZE;
if (end > limit) {
end = limit;
@@ -150,7 +159,7 @@ static int __init split_nodes_interleave(struct numa_meminfo *ei,
* this one must extend to the boundary.
*/
if (end < dma32_end && dma32_end - end -
- memblock_x86_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE)
+ mem_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE)
end = dma32_end;
/*
@@ -158,8 +167,7 @@ static int __init split_nodes_interleave(struct numa_meminfo *ei,
* next node, this one must extend to the end of the
* physical node.
*/
- if (limit - end -
- memblock_x86_hole_size(end, limit) < size)
+ if (limit - end - mem_hole_size(end, limit) < size)
end = limit;
ret = emu_setup_memblk(ei, pi, nid++ % nr_nodes,
@@ -180,7 +188,7 @@ static u64 __init find_end_of_node(u64 start, u64 max_addr, u64 size)
{
u64 end = start + size;
- while (end - start - memblock_x86_hole_size(start, end) < size) {
+ while (end - start - mem_hole_size(start, end) < size) {
end += FAKE_NODE_MIN_SIZE;
if (end > max_addr) {
end = max_addr;
@@ -211,8 +219,7 @@ static int __init split_nodes_size_interleave(struct numa_meminfo *ei,
* creates a uniform distribution of node sizes across the entire
* machine (but not necessarily over physical nodes).
*/
- min_size = (max_addr - addr - memblock_x86_hole_size(addr, max_addr)) /
- MAX_NUMNODES;
+ min_size = (max_addr - addr - mem_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) &
@@ -252,7 +259,7 @@ static int __init split_nodes_size_interleave(struct numa_meminfo *ei,
* this one must extend to the boundary.
*/
if (end < dma32_end && dma32_end - end -
- memblock_x86_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE)
+ mem_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE)
end = dma32_end;
/*
@@ -260,8 +267,7 @@ static int __init split_nodes_size_interleave(struct numa_meminfo *ei,
* next node, this one must extend to the end of the
* physical node.
*/
- if (limit - end -
- memblock_x86_hole_size(end, limit) < size)
+ if (limit - end - mem_hole_size(end, limit) < size)
end = limit;
ret = emu_setup_memblk(ei, pi, nid++ % MAX_NUMNODES,
@@ -351,11 +357,11 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt)
phys = memblock_find_in_range(0, PFN_PHYS(max_pfn_mapped),
phys_size, PAGE_SIZE);
- if (phys == MEMBLOCK_ERROR) {
+ if (!phys) {
pr_warning("NUMA: Warning: can't allocate copy of distance table, disabling emulation\n");
goto no_emu;
}
- memblock_x86_reserve_range(phys, phys + phys_size, "TMP NUMA DIST");
+ memblock_reserve(phys, phys_size);
phys_dist = __va(phys);
for (i = 0; i < numa_dist_cnt; i++)
@@ -424,7 +430,7 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt)
/* free the copied physical distance table */
if (phys_dist)
- memblock_x86_free_range(__pa(phys_dist), __pa(phys_dist) + phys_size);
+ memblock_free(__pa(phys_dist), phys_size);
return;
no_emu:
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index f9e526742fa..eda2acbb6e8 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -998,7 +998,7 @@ out_err:
}
EXPORT_SYMBOL(set_memory_uc);
-int _set_memory_array(unsigned long *addr, int addrinarray,
+static int _set_memory_array(unsigned long *addr, int addrinarray,
unsigned long new_type)
{
int i, j;
diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c
index 81dbfdeb080..fd61b3fb734 100644
--- a/arch/x86/mm/srat.c
+++ b/arch/x86/mm/srat.c
@@ -69,6 +69,12 @@ acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa)
if ((pa->flags & ACPI_SRAT_CPU_ENABLED) == 0)
return;
pxm = pa->proximity_domain;
+ apic_id = pa->apic_id;
+ if (!cpu_has_x2apic && (apic_id >= 0xff)) {
+ printk(KERN_INFO "SRAT: PXM %u -> X2APIC 0x%04x ignored\n",
+ pxm, apic_id);
+ return;
+ }
node = setup_node(pxm);
if (node < 0) {
printk(KERN_ERR "SRAT: Too many proximity domains %x\n", pxm);
@@ -76,7 +82,6 @@ acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa)
return;
}
- apic_id = pa->apic_id;
if (apic_id >= MAX_LOCAL_APIC) {
printk(KERN_INFO "SRAT: PXM %u -> APIC 0x%04x -> Node %u skipped apicid that is too big\n", pxm, apic_id, node);
return;
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2024-11-30 21:52:58 +0000