aboutsummaryrefslogtreecommitdiffstats
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/gup.c16
-rw-r--r--arch/x86/mm/highmem_32.c69
-rw-r--r--arch/x86/mm/init.c344
-rw-r--r--arch/x86/mm/init_32.c291
-rw-r--r--arch/x86/mm/init_64.c317
-rw-r--r--arch/x86/mm/iomap_32.c30
-rw-r--r--arch/x86/mm/ioremap.c83
-rw-r--r--arch/x86/mm/kmmio.c4
-rw-r--r--arch/x86/mm/memtest.c3
-rw-r--r--arch/x86/mm/mmio-mod.c19
-rw-r--r--arch/x86/mm/numa.c67
-rw-r--r--arch/x86/mm/numa_32.c7
-rw-r--r--arch/x86/mm/numa_64.c114
-rw-r--r--arch/x86/mm/pageattr.c272
-rw-r--r--arch/x86/mm/pat.c196
-rw-r--r--arch/x86/mm/pgtable.c3
-rw-r--r--arch/x86/mm/pgtable_32.c2
-rw-r--r--arch/x86/mm/srat_64.c36
-rw-r--r--arch/x86/mm/tlb.c5
20 files changed, 931 insertions, 949 deletions
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 08537747cb58..fdd30d08ab52 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -14,7 +14,7 @@ obj-$(CONFIG_MMIOTRACE) += mmiotrace.o
mmiotrace-y := kmmio.o pf_in.o mmio-mod.o
obj-$(CONFIG_MMIOTRACE_TEST) += testmmiotrace.o
-obj-$(CONFIG_NUMA) += numa_$(BITS).o
+obj-$(CONFIG_NUMA) += numa.o numa_$(BITS).o
obj-$(CONFIG_K8_NUMA) += k8topology_64.o
obj-$(CONFIG_ACPI_NUMA) += srat_$(BITS).o
diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c
index be54176e9eb2..6340cef6798a 100644
--- a/arch/x86/mm/gup.c
+++ b/arch/x86/mm/gup.c
@@ -219,6 +219,22 @@ static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end,
return 1;
}
+/**
+ * get_user_pages_fast() - pin user pages in memory
+ * @start: starting user address
+ * @nr_pages: number of pages from start to pin
+ * @write: whether pages will be written to
+ * @pages: array that receives pointers to the pages pinned.
+ * Should be at least nr_pages long.
+ *
+ * Attempt to pin user pages in memory without taking mm->mmap_sem.
+ * If not successful, it will fall back to taking the lock and
+ * calling get_user_pages().
+ *
+ * Returns number of pages pinned. This may be fewer than the number
+ * requested. If nr_pages is 0 or negative, returns 0. If no pages
+ * were pinned, returns -errno.
+ */
int get_user_pages_fast(unsigned long start, int nr_pages, int write,
struct page **pages)
{
diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c
index 00f127c80b0e..8126e8d1a2a4 100644
--- a/arch/x86/mm/highmem_32.c
+++ b/arch/x86/mm/highmem_32.c
@@ -19,49 +19,6 @@ void kunmap(struct page *page)
kunmap_high(page);
}
-static void debug_kmap_atomic_prot(enum km_type type)
-{
-#ifdef CONFIG_DEBUG_HIGHMEM
- static unsigned warn_count = 10;
-
- if (unlikely(warn_count == 0))
- return;
-
- if (unlikely(in_interrupt())) {
- if (in_irq()) {
- if (type != KM_IRQ0 && type != KM_IRQ1 &&
- type != KM_BIO_SRC_IRQ && type != KM_BIO_DST_IRQ &&
- type != KM_BOUNCE_READ) {
- WARN_ON(1);
- warn_count--;
- }
- } else if (!irqs_disabled()) { /* softirq */
- if (type != KM_IRQ0 && type != KM_IRQ1 &&
- type != KM_SOFTIRQ0 && type != KM_SOFTIRQ1 &&
- type != KM_SKB_SUNRPC_DATA &&
- type != KM_SKB_DATA_SOFTIRQ &&
- type != KM_BOUNCE_READ) {
- WARN_ON(1);
- warn_count--;
- }
- }
- }
-
- if (type == KM_IRQ0 || type == KM_IRQ1 || type == KM_BOUNCE_READ ||
- type == KM_BIO_SRC_IRQ || type == KM_BIO_DST_IRQ) {
- if (!irqs_disabled()) {
- WARN_ON(1);
- warn_count--;
- }
- } else if (type == KM_SOFTIRQ0 || type == KM_SOFTIRQ1) {
- if (irq_count() == 0 && !irqs_disabled()) {
- WARN_ON(1);
- warn_count--;
- }
- }
-#endif
-}
-
/*
* kmap_atomic/kunmap_atomic is significantly faster than kmap/kunmap because
* no global lock is needed and because the kmap code must perform a global TLB
@@ -81,7 +38,7 @@ void *kmap_atomic_prot(struct page *page, enum km_type type, pgprot_t prot)
if (!PageHighMem(page))
return page_address(page);
- debug_kmap_atomic_prot(type);
+ debug_kmap_atomic(type);
idx = type + KM_TYPE_NR*smp_processor_id();
vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
@@ -121,22 +78,13 @@ void kunmap_atomic(void *kvaddr, enum km_type type)
pagefault_enable();
}
-/* This is the same as kmap_atomic() but can map memory that doesn't
+/*
+ * This is the same as kmap_atomic() but can map memory that doesn't
* have a struct page associated with it.
*/
void *kmap_atomic_pfn(unsigned long pfn, enum km_type type)
{
- enum fixed_addresses idx;
- unsigned long vaddr;
-
- pagefault_disable();
-
- idx = type + KM_TYPE_NR*smp_processor_id();
- vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
- set_pte(kmap_pte-idx, pfn_pte(pfn, kmap_prot));
- arch_flush_lazy_mmu_mode();
-
- return (void*) vaddr;
+ return kmap_atomic_prot_pfn(pfn, type, kmap_prot);
}
EXPORT_SYMBOL_GPL(kmap_atomic_pfn); /* temporarily in use by i915 GEM until vmap */
@@ -158,7 +106,6 @@ EXPORT_SYMBOL(kunmap);
EXPORT_SYMBOL(kmap_atomic);
EXPORT_SYMBOL(kunmap_atomic);
-#ifdef CONFIG_NUMA
void __init set_highmem_pages_init(void)
{
struct zone *zone;
@@ -182,11 +129,3 @@ void __init set_highmem_pages_init(void)
}
totalram_pages += totalhigh_pages;
}
-#else
-void __init set_highmem_pages_init(void)
-{
- add_highpages_with_active_regions(0, highstart_pfn, highend_pfn);
-
- totalram_pages += totalhigh_pages;
-}
-#endif /* CONFIG_NUMA */
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index ce6a722587d8..fd3da1dda1c9 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -1,8 +1,345 @@
+#include <linux/ioport.h>
#include <linux/swap.h>
+
#include <asm/cacheflush.h>
+#include <asm/e820.h>
+#include <asm/init.h>
#include <asm/page.h>
+#include <asm/page_types.h>
#include <asm/sections.h>
#include <asm/system.h>
+#include <asm/tlbflush.h>
+
+unsigned long __initdata e820_table_start;
+unsigned long __meminitdata e820_table_end;
+unsigned long __meminitdata e820_table_top;
+
+int after_bootmem;
+
+int direct_gbpages
+#ifdef CONFIG_DIRECT_GBPAGES
+ = 1
+#endif
+;
+
+static void __init find_early_table_space(unsigned long end, int use_pse,
+ int use_gbpages)
+{
+ unsigned long puds, pmds, ptes, tables, start;
+
+ puds = (end + PUD_SIZE - 1) >> PUD_SHIFT;
+ tables = roundup(puds * sizeof(pud_t), PAGE_SIZE);
+
+ if (use_gbpages) {
+ unsigned long extra;
+
+ extra = end - ((end>>PUD_SHIFT) << PUD_SHIFT);
+ pmds = (extra + PMD_SIZE - 1) >> PMD_SHIFT;
+ } else
+ pmds = (end + PMD_SIZE - 1) >> PMD_SHIFT;
+
+ tables += roundup(pmds * sizeof(pmd_t), PAGE_SIZE);
+
+ if (use_pse) {
+ unsigned long extra;
+
+ extra = end - ((end>>PMD_SHIFT) << PMD_SHIFT);
+#ifdef CONFIG_X86_32
+ extra += PMD_SIZE;
+#endif
+ ptes = (extra + PAGE_SIZE - 1) >> PAGE_SHIFT;
+ } else
+ ptes = (end + PAGE_SIZE - 1) >> PAGE_SHIFT;
+
+ tables += roundup(ptes * sizeof(pte_t), PAGE_SIZE);
+
+#ifdef CONFIG_X86_32
+ /* for fixmap */
+ tables += roundup(__end_of_fixed_addresses * sizeof(pte_t), PAGE_SIZE);
+#endif
+
+ /*
+ * RED-PEN putting page tables only on node 0 could
+ * cause a hotspot and fill up ZONE_DMA. The page tables
+ * need roughly 0.5KB per GB.
+ */
+#ifdef CONFIG_X86_32
+ start = 0x7000;
+ e820_table_start = find_e820_area(start, max_pfn_mapped<<PAGE_SHIFT,
+ tables, PAGE_SIZE);
+#else /* CONFIG_X86_64 */
+ start = 0x8000;
+ e820_table_start = find_e820_area(start, end, tables, PAGE_SIZE);
+#endif
+ if (e820_table_start == -1UL)
+ panic("Cannot find space for the kernel page tables");
+
+ e820_table_start >>= PAGE_SHIFT;
+ e820_table_end = e820_table_start;
+ e820_table_top = e820_table_start + (tables >> PAGE_SHIFT);
+
+ printk(KERN_DEBUG "kernel direct mapping tables up to %lx @ %lx-%lx\n",
+ end, e820_table_start << PAGE_SHIFT, e820_table_top << PAGE_SHIFT);
+}
+
+struct map_range {
+ unsigned long start;
+ unsigned long end;
+ unsigned page_size_mask;
+};
+
+#ifdef CONFIG_X86_32
+#define NR_RANGE_MR 3
+#else /* CONFIG_X86_64 */
+#define NR_RANGE_MR 5
+#endif
+
+static int __meminit save_mr(struct map_range *mr, int nr_range,
+ unsigned long start_pfn, unsigned long end_pfn,
+ unsigned long page_size_mask)
+{
+ if (start_pfn < end_pfn) {
+ if (nr_range >= NR_RANGE_MR)
+ panic("run out of range for init_memory_mapping\n");
+ mr[nr_range].start = start_pfn<<PAGE_SHIFT;
+ mr[nr_range].end = end_pfn<<PAGE_SHIFT;
+ mr[nr_range].page_size_mask = page_size_mask;
+ nr_range++;
+ }
+
+ return nr_range;
+}
+
+#ifdef CONFIG_X86_64
+static void __init init_gbpages(void)
+{
+ if (direct_gbpages && cpu_has_gbpages)
+ printk(KERN_INFO "Using GB pages for direct mapping\n");
+ else
+ direct_gbpages = 0;
+}
+#else
+static inline void init_gbpages(void)
+{
+}
+#endif
+
+/*
+ * Setup the direct mapping of the physical memory at PAGE_OFFSET.
+ * This runs before bootmem is initialized and gets pages directly from
+ * the physical memory. To access them they are temporarily mapped.
+ */
+unsigned long __init_refok init_memory_mapping(unsigned long start,
+ unsigned long end)
+{
+ unsigned long page_size_mask = 0;
+ unsigned long start_pfn, end_pfn;
+ unsigned long ret = 0;
+ unsigned long pos;
+
+ struct map_range mr[NR_RANGE_MR];
+ int nr_range, i;
+ int use_pse, use_gbpages;
+
+ printk(KERN_INFO "init_memory_mapping: %016lx-%016lx\n", start, end);
+
+ if (!after_bootmem)
+ init_gbpages();
+
+#ifdef CONFIG_DEBUG_PAGEALLOC
+ /*
+ * For CONFIG_DEBUG_PAGEALLOC, identity mapping will use small pages.
+ * This will simplify cpa(), which otherwise needs to support splitting
+ * large pages into small in interrupt context, etc.
+ */
+ use_pse = use_gbpages = 0;
+#else
+ use_pse = cpu_has_pse;
+ use_gbpages = direct_gbpages;
+#endif
+
+#ifdef CONFIG_X86_32
+#ifdef CONFIG_X86_PAE
+ set_nx();
+ if (nx_enabled)
+ printk(KERN_INFO "NX (Execute Disable) protection: active\n");
+#endif
+
+ /* Enable PSE if available */
+ if (cpu_has_pse)
+ set_in_cr4(X86_CR4_PSE);
+
+ /* Enable PGE if available */
+ if (cpu_has_pge) {
+ set_in_cr4(X86_CR4_PGE);
+ __supported_pte_mask |= _PAGE_GLOBAL;
+ }
+#endif
+
+ if (use_gbpages)
+ page_size_mask |= 1 << PG_LEVEL_1G;
+ if (use_pse)
+ page_size_mask |= 1 << PG_LEVEL_2M;
+
+ memset(mr, 0, sizeof(mr));
+ nr_range = 0;
+
+ /* head if not big page alignment ? */
+ start_pfn = start >> PAGE_SHIFT;
+ pos = start_pfn << PAGE_SHIFT;
+#ifdef CONFIG_X86_32
+ /*
+ * Don't use a large page for the first 2/4MB of memory
+ * because there are often fixed size MTRRs in there
+ * and overlapping MTRRs into large pages can cause
+ * slowdowns.
+ */
+ if (pos == 0)
+ end_pfn = 1<<(PMD_SHIFT - PAGE_SHIFT);
+ else
+ end_pfn = ((pos + (PMD_SIZE - 1))>>PMD_SHIFT)
+ << (PMD_SHIFT - PAGE_SHIFT);
+#else /* CONFIG_X86_64 */
+ end_pfn = ((pos + (PMD_SIZE - 1)) >> PMD_SHIFT)
+ << (PMD_SHIFT - PAGE_SHIFT);
+#endif
+ if (end_pfn > (end >> PAGE_SHIFT))
+ end_pfn = end >> PAGE_SHIFT;
+ if (start_pfn < end_pfn) {
+ nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0);
+ pos = end_pfn << PAGE_SHIFT;
+ }
+
+ /* big page (2M) range */
+ start_pfn = ((pos + (PMD_SIZE - 1))>>PMD_SHIFT)
+ << (PMD_SHIFT - PAGE_SHIFT);
+#ifdef CONFIG_X86_32
+ end_pfn = (end>>PMD_SHIFT) << (PMD_SHIFT - PAGE_SHIFT);
+#else /* CONFIG_X86_64 */
+ end_pfn = ((pos + (PUD_SIZE - 1))>>PUD_SHIFT)
+ << (PUD_SHIFT - PAGE_SHIFT);
+ if (end_pfn > ((end>>PMD_SHIFT)<<(PMD_SHIFT - PAGE_SHIFT)))
+ end_pfn = ((end>>PMD_SHIFT)<<(PMD_SHIFT - PAGE_SHIFT));
+#endif
+
+ if (start_pfn < end_pfn) {
+ nr_range = save_mr(mr, nr_range, start_pfn, end_pfn,
+ page_size_mask & (1<<PG_LEVEL_2M));
+ pos = end_pfn << PAGE_SHIFT;
+ }
+
+#ifdef CONFIG_X86_64
+ /* big page (1G) range */
+ start_pfn = ((pos + (PUD_SIZE - 1))>>PUD_SHIFT)
+ << (PUD_SHIFT - PAGE_SHIFT);
+ end_pfn = (end >> PUD_SHIFT) << (PUD_SHIFT - PAGE_SHIFT);
+ if (start_pfn < end_pfn) {
+ nr_range = save_mr(mr, nr_range, start_pfn, end_pfn,
+ page_size_mask &
+ ((1<<PG_LEVEL_2M)|(1<<PG_LEVEL_1G)));
+ pos = end_pfn << PAGE_SHIFT;
+ }
+
+ /* tail is not big page (1G) alignment */
+ start_pfn = ((pos + (PMD_SIZE - 1))>>PMD_SHIFT)
+ << (PMD_SHIFT - PAGE_SHIFT);
+ end_pfn = (end >> PMD_SHIFT) << (PMD_SHIFT - PAGE_SHIFT);
+ if (start_pfn < end_pfn) {
+ nr_range = save_mr(mr, nr_range, start_pfn, end_pfn,
+ page_size_mask & (1<<PG_LEVEL_2M));
+ pos = end_pfn << PAGE_SHIFT;
+ }
+#endif
+
+ /* tail is not big page (2M) alignment */
+ start_pfn = pos>>PAGE_SHIFT;
+ end_pfn = end>>PAGE_SHIFT;
+ nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0);
+
+ /* try to merge same page size and continuous */
+ for (i = 0; nr_range > 1 && i < nr_range - 1; i++) {
+ unsigned long old_start;
+ if (mr[i].end != mr[i+1].start ||
+ mr[i].page_size_mask != mr[i+1].page_size_mask)
+ continue;
+ /* move it */
+ old_start = mr[i].start;
+ memmove(&mr[i], &mr[i+1],
+ (nr_range - 1 - i) * sizeof(struct map_range));
+ mr[i--].start = old_start;
+ nr_range--;
+ }
+
+ for (i = 0; i < nr_range; i++)
+ printk(KERN_DEBUG " %010lx - %010lx page %s\n",
+ mr[i].start, mr[i].end,
+ (mr[i].page_size_mask & (1<<PG_LEVEL_1G))?"1G":(
+ (mr[i].page_size_mask & (1<<PG_LEVEL_2M))?"2M":"4k"));
+
+ /*
+ * Find space for the kernel direct mapping tables.
+ *
+ * Later we should allocate these tables in the local node of the
+ * memory mapped. Unfortunately this is done currently before the
+ * nodes are discovered.
+ */
+ if (!after_bootmem)
+ find_early_table_space(end, use_pse, use_gbpages);
+
+#ifdef CONFIG_X86_32
+ for (i = 0; i < nr_range; i++)
+ kernel_physical_mapping_init(mr[i].start, mr[i].end,
+ mr[i].page_size_mask);
+ ret = end;
+#else /* CONFIG_X86_64 */
+ for (i = 0; i < nr_range; i++)
+ ret = kernel_physical_mapping_init(mr[i].start, mr[i].end,
+ mr[i].page_size_mask);
+#endif
+
+#ifdef CONFIG_X86_32
+ early_ioremap_page_table_range_init();
+
+ load_cr3(swapper_pg_dir);
+#endif
+
+#ifdef CONFIG_X86_64
+ if (!after_bootmem)
+ mmu_cr4_features = read_cr4();
+#endif
+ __flush_tlb_all();
+
+ if (!after_bootmem && e820_table_end > e820_table_start)
+ reserve_early(e820_table_start << PAGE_SHIFT,
+ e820_table_end << PAGE_SHIFT, "PGTABLE");
+
+ if (!after_bootmem)
+ early_memtest(start, end);
+
+ return ret >> PAGE_SHIFT;
+}
+
+
+/*
+ * devmem_is_allowed() checks to see if /dev/mem access to a certain address
+ * is valid. The argument is a physical page number.
+ *
+ *
+ * On x86, access has to be given to the first megabyte of ram because that area
+ * contains bios code and data regions used by X and dosemu and similar apps.
+ * Access has to be given to non-kernel-ram areas as well, these contain the PCI
+ * mmio resources as well as potential bios/acpi data regions.
+ */
+int devmem_is_allowed(unsigned long pagenr)
+{
+ if (pagenr <= 256)
+ return 1;
+ if (iomem_is_exclusive(pagenr << PAGE_SHIFT))
+ return 0;
+ if (!page_is_ram(pagenr))
+ return 1;
+ return 0;
+}
void free_init_pages(char *what, unsigned long begin, unsigned long end)
{
@@ -47,3 +384,10 @@ void free_initmem(void)
(unsigned long)(&__init_begin),
(unsigned long)(&__init_end));
}
+
+#ifdef CONFIG_BLK_DEV_INITRD
+void free_initrd_mem(unsigned long start, unsigned long end)
+{
+ free_init_pages("initrd memory", start, end);
+}
+#endif
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 47df0e1bbeb9..749559ed80f5 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -49,6 +49,7 @@
#include <asm/paravirt.h>
#include <asm/setup.h>
#include <asm/cacheflush.h>
+#include <asm/init.h>
unsigned long max_low_pfn_mapped;
unsigned long max_pfn_mapped;
@@ -58,19 +59,14 @@ unsigned long highstart_pfn, highend_pfn;
static noinline int do_test_wp_bit(void);
-
-static unsigned long __initdata table_start;
-static unsigned long __meminitdata table_end;
-static unsigned long __meminitdata table_top;
-
-static int __initdata after_init_bootmem;
+bool __read_mostly __vmalloc_start_set = false;
static __init void *alloc_low_page(void)
{
- unsigned long pfn = table_end++;
+ unsigned long pfn = e820_table_end++;
void *adr;
- if (pfn >= table_top)
+ if (pfn >= e820_table_top)
panic("alloc_low_page: ran out of memory");
adr = __va(pfn * PAGE_SIZE);
@@ -90,7 +86,7 @@ static pmd_t * __init one_md_table_init(pgd_t *pgd)
#ifdef CONFIG_X86_PAE
if (!(pgd_val(*pgd) & _PAGE_PRESENT)) {
- if (after_init_bootmem)
+ if (after_bootmem)
pmd_table = (pmd_t *)alloc_bootmem_low_pages(PAGE_SIZE);
else
pmd_table = (pmd_t *)alloc_low_page();
@@ -117,7 +113,7 @@ static pte_t * __init one_page_table_init(pmd_t *pmd)
if (!(pmd_val(*pmd) & _PAGE_PRESENT)) {
pte_t *page_table = NULL;
- if (after_init_bootmem) {
+ if (after_bootmem) {
#ifdef CONFIG_DEBUG_PAGEALLOC
page_table = (pte_t *) alloc_bootmem_pages(PAGE_SIZE);
#endif
@@ -168,12 +164,12 @@ static pte_t *__init page_table_kmap_check(pte_t *pte, pmd_t *pmd,
if (pmd_idx_kmap_begin != pmd_idx_kmap_end
&& (vaddr >> PMD_SHIFT) >= pmd_idx_kmap_begin
&& (vaddr >> PMD_SHIFT) <= pmd_idx_kmap_end
- && ((__pa(pte) >> PAGE_SHIFT) < table_start
- || (__pa(pte) >> PAGE_SHIFT) >= table_end)) {
+ && ((__pa(pte) >> PAGE_SHIFT) < e820_table_start
+ || (__pa(pte) >> PAGE_SHIFT) >= e820_table_end)) {
pte_t *newpte;
int i;
- BUG_ON(after_init_bootmem);
+ BUG_ON(after_bootmem);
newpte = alloc_low_page();
for (i = 0; i < PTRS_PER_PTE; i++)
set_pte(newpte + i, pte[i]);
@@ -242,11 +238,14 @@ static inline int is_kernel_text(unsigned long addr)
* of max_low_pfn pages, by creating page tables starting from address
* PAGE_OFFSET:
*/
-static void __init kernel_physical_mapping_init(pgd_t *pgd_base,
- unsigned long start_pfn,
- unsigned long end_pfn,
- int use_pse)
+unsigned long __init
+kernel_physical_mapping_init(unsigned long start,
+ unsigned long end,
+ unsigned long page_size_mask)
{
+ int use_pse = page_size_mask == (1<<PG_LEVEL_2M);
+ unsigned long start_pfn, end_pfn;
+ pgd_t *pgd_base = swapper_pg_dir;
int pgd_idx, pmd_idx, pte_ofs;
unsigned long pfn;
pgd_t *pgd;
@@ -255,6 +254,9 @@ static void __init kernel_physical_mapping_init(pgd_t *pgd_base,
unsigned pages_2m, pages_4k;
int mapping_iter;
+ start_pfn = start >> PAGE_SHIFT;
+ end_pfn = end >> PAGE_SHIFT;
+
/*
* First iteration will setup identity mapping using large/small pages
* based on use_pse, with other attributes same as set by
@@ -369,26 +371,6 @@ repeat:
mapping_iter = 2;
goto repeat;
}
-}
-
-/*
- * devmem_is_allowed() checks to see if /dev/mem access to a certain address
- * is valid. The argument is a physical page number.
- *
- *
- * On x86, access has to be given to the first megabyte of ram because that area
- * contains bios code and data regions used by X and dosemu and similar apps.
- * Access has to be given to non-kernel-ram areas as well, these contain the PCI
- * mmio resources as well as potential bios/acpi data regions.
- */
-int devmem_is_allowed(unsigned long pagenr)
-{
- if (pagenr <= 256)
- return 1;
- if (iomem_is_exclusive(pagenr << PAGE_SHIFT))
- return 0;
- if (!page_is_ram(pagenr))
- return 1;
return 0;
}
@@ -545,8 +527,9 @@ void __init native_pagetable_setup_done(pgd_t *base)
* be partially populated, and so it avoids stomping on any existing
* mappings.
*/
-static void __init early_ioremap_page_table_range_init(pgd_t *pgd_base)
+void __init early_ioremap_page_table_range_init(void)
{
+ pgd_t *pgd_base = swapper_pg_dir;
unsigned long vaddr, end;
/*
@@ -641,7 +624,7 @@ static int __init noexec_setup(char *str)
}
early_param("noexec", noexec_setup);
-static void __init set_nx(void)
+void __init set_nx(void)
{
unsigned int v[4], l, h;
@@ -793,6 +776,8 @@ void __init initmem_init(unsigned long start_pfn,
#ifdef CONFIG_FLATMEM
max_mapnr = num_physpages;
#endif
+ __vmalloc_start_set = true;
+
printk(KERN_NOTICE "%ldMB LOWMEM available.\n",
pages_to_mb(max_low_pfn));
@@ -814,176 +799,66 @@ static void __init zone_sizes_init(void)
free_area_init_nodes(max_zone_pfns);
}
+static unsigned long __init setup_node_bootmem(int nodeid,
+ unsigned long start_pfn,
+ unsigned long end_pfn,
+ unsigned long bootmap)
+{
+ unsigned long bootmap_size;
+
+ /* don't touch min_low_pfn */
+ bootmap_size = init_bootmem_node(NODE_DATA(nodeid),
+ bootmap >> PAGE_SHIFT,
+ start_pfn, end_pfn);
+ printk(KERN_INFO " node %d low ram: %08lx - %08lx\n",
+ nodeid, start_pfn<<PAGE_SHIFT, end_pfn<<PAGE_SHIFT);
+ 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;
+}
+
void __init setup_bootmem_allocator(void)
{
- int i;
+ int nodeid;
unsigned long bootmap_size, bootmap;
/*
* Initialize the boot-time allocator (with low memory only):
*/
bootmap_size = bootmem_bootmap_pages(max_low_pfn)<<PAGE_SHIFT;
- bootmap = find_e820_area(min_low_pfn<<PAGE_SHIFT,
- max_pfn_mapped<<PAGE_SHIFT, bootmap_size,
+ bootmap = find_e820_area(0, max_pfn_mapped<<PAGE_SHIFT, bootmap_size,
PAGE_SIZE);
if (bootmap == -1L)
panic("Cannot find bootmem map of size %ld\n", bootmap_size);
reserve_early(bootmap, bootmap + bootmap_size, "BOOTMAP");
- /* don't touch min_low_pfn */
- bootmap_size = init_bootmem_node(NODE_DATA(0), bootmap >> PAGE_SHIFT,
- min_low_pfn, max_low_pfn);
printk(KERN_INFO " mapped low ram: 0 - %08lx\n",
max_pfn_mapped<<PAGE_SHIFT);
- printk(KERN_INFO " low ram: %08lx - %08lx\n",
- min_low_pfn<<PAGE_SHIFT, max_low_pfn<<PAGE_SHIFT);
- printk(KERN_INFO " bootmap %08lx - %08lx\n",
- bootmap, bootmap + bootmap_size);
- for_each_online_node(i)
- free_bootmem_with_active_regions(i, max_low_pfn);
- early_res_to_bootmem(0, max_low_pfn<<PAGE_SHIFT);
-
- after_init_bootmem = 1;
-}
-
-static void __init find_early_table_space(unsigned long end, int use_pse)
-{
- unsigned long puds, pmds, ptes, tables, start;
-
- puds = (end + PUD_SIZE - 1) >> PUD_SHIFT;
- tables = roundup(puds * sizeof(pud_t), PAGE_SIZE);
-
- pmds = (end + PMD_SIZE - 1) >> PMD_SHIFT;
- tables += roundup(pmds * sizeof(pmd_t), PAGE_SIZE);
+ printk(KERN_INFO " low ram: 0 - %08lx\n", max_low_pfn<<PAGE_SHIFT);
- if (use_pse) {
- unsigned long extra;
-
- extra = end - ((end>>PMD_SHIFT) << PMD_SHIFT);
- extra += PMD_SIZE;
- ptes = (extra + PAGE_SIZE - 1) >> PAGE_SHIFT;
- } else
- ptes = (end + PAGE_SIZE - 1) >> PAGE_SHIFT;
-
- tables += roundup(ptes * sizeof(pte_t), PAGE_SIZE);
-
- /* for fixmap */
- tables += roundup(__end_of_fixed_addresses * sizeof(pte_t), PAGE_SIZE);
-
- /*
- * RED-PEN putting page tables only on node 0 could
- * cause a hotspot and fill up ZONE_DMA. The page tables
- * need roughly 0.5KB per GB.
- */
- start = 0x7000;
- table_start = find_e820_area(start, max_pfn_mapped<<PAGE_SHIFT,
- tables, PAGE_SIZE);
- if (table_start == -1UL)
- panic("Cannot find space for the kernel page tables");
-
- table_start >>= PAGE_SHIFT;
- table_end = table_start;
- table_top = table_start + (tables>>PAGE_SHIFT);
-
- printk(KERN_DEBUG "kernel direct mapping tables up to %lx @ %lx-%lx\n",
- end, table_start << PAGE_SHIFT,
- (table_start << PAGE_SHIFT) + tables);
-}
+ for_each_online_node(nodeid) {
+ unsigned long start_pfn, end_pfn;
-unsigned long __init_refok init_memory_mapping(unsigned long start,
- unsigned long end)
-{
- pgd_t *pgd_base = swapper_pg_dir;
- unsigned long start_pfn, end_pfn;
- unsigned long big_page_start;
-#ifdef CONFIG_DEBUG_PAGEALLOC
- /*
- * For CONFIG_DEBUG_PAGEALLOC, identity mapping will use small pages.
- * This will simplify cpa(), which otherwise needs to support splitting
- * large pages into small in interrupt context, etc.
- */
- int use_pse = 0;
+#ifdef CONFIG_NEED_MULTIPLE_NODES
+ start_pfn = node_start_pfn[nodeid];
+ end_pfn = node_end_pfn[nodeid];
+ if (start_pfn > max_low_pfn)
+ continue;
+ if (end_pfn > max_low_pfn)
+ end_pfn = max_low_pfn;
#else
- int use_pse = cpu_has_pse;
+ start_pfn = 0;
+ end_pfn = max_low_pfn;
#endif
-
- /*
- * Find space for the kernel direct mapping tables.
- */
- if (!after_init_bootmem)
- find_early_table_space(end, use_pse);
-
-#ifdef CONFIG_X86_PAE
- set_nx();
- if (nx_enabled)
- printk(KERN_INFO "NX (Execute Disable) protection: active\n");
-#endif
-
- /* Enable PSE if available */
- if (cpu_has_pse)
- set_in_cr4(X86_CR4_PSE);
-
- /* Enable PGE if available */
- if (cpu_has_pge) {
- set_in_cr4(X86_CR4_PGE);
- __supported_pte_mask |= _PAGE_GLOBAL;
- }
-
- /*
- * Don't use a large page for the first 2/4MB of memory
- * because there are often fixed size MTRRs in there
- * and overlapping MTRRs into large pages can cause
- * slowdowns.
- */
- big_page_start = PMD_SIZE;
-
- if (start < big_page_start) {
- start_pfn = start >> PAGE_SHIFT;
- end_pfn = min(big_page_start>>PAGE_SHIFT, end>>PAGE_SHIFT);
- } else {
- /* head is not big page alignment ? */
- start_pfn = start >> PAGE_SHIFT;
- end_pfn = ((start + (PMD_SIZE - 1))>>PMD_SHIFT)
- << (PMD_SHIFT - PAGE_SHIFT);
- }
- if (start_pfn < end_pfn)
- kernel_physical_mapping_init(pgd_base, start_pfn, end_pfn, 0);
-
- /* big page range */
- start_pfn = ((start + (PMD_SIZE - 1))>>PMD_SHIFT)
- << (PMD_SHIFT - PAGE_SHIFT);
- if (start_pfn < (big_page_start >> PAGE_SHIFT))
- start_pfn = big_page_start >> PAGE_SHIFT;
- end_pfn = (end>>PMD_SHIFT) << (PMD_SHIFT - PAGE_SHIFT);
- if (start_pfn < end_pfn)
- kernel_physical_mapping_init(pgd_base, start_pfn, end_pfn,
- use_pse);
-
- /* tail is not big page alignment ? */
- start_pfn = end_pfn;
- if (start_pfn > (big_page_start>>PAGE_SHIFT)) {
- end_pfn = end >> PAGE_SHIFT;
- if (start_pfn < end_pfn)
- kernel_physical_mapping_init(pgd_base, start_pfn,
- end_pfn, 0);
+ bootmap = setup_node_bootmem(nodeid, start_pfn, end_pfn,
+ bootmap);
}
- early_ioremap_page_table_range_init(pgd_base);
-
- load_cr3(swapper_pg_dir);
-
- __flush_tlb_all();
-
- if (!after_init_bootmem)
- reserve_early(table_start << PAGE_SHIFT,
- table_end << PAGE_SHIFT, "PGTABLE");
-
- if (!after_init_bootmem)
- early_memtest(start, end);
-
- return end >> PAGE_SHIFT;
+ after_bootmem = 1;
}
-
/*
* paging_init() sets up the page tables - note that the first 8MB are
* already mapped by head.S.
@@ -1179,17 +1054,47 @@ static noinline int do_test_wp_bit(void)
const int rodata_test_data = 0xC3;
EXPORT_SYMBOL_GPL(rodata_test_data);
+static int kernel_set_to_readonly;
+
+void set_kernel_text_rw(void)
+{
+ unsigned long start = PFN_ALIGN(_text);
+ unsigned long size = PFN_ALIGN(_etext) - start;
+
+ if (!kernel_set_to_readonly)
+ return;
+
+ pr_debug("Set kernel text: %lx - %lx for read write\n",
+ start, start+size);
+
+ set_pages_rw(virt_to_page(start), size >> PAGE_SHIFT);
+}
+
+void set_kernel_text_ro(void)
+{
+ unsigned long start = PFN_ALIGN(_text);
+ unsigned long size = PFN_ALIGN(_etext) - start;
+
+ if (!kernel_set_to_readonly)
+ return;
+
+ pr_debug("Set kernel text: %lx - %lx for read only\n",
+ start, start+size);
+
+ set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT);
+}
+
void mark_rodata_ro(void)
{
unsigned long start = PFN_ALIGN(_text);
unsigned long size = PFN_ALIGN(_etext) - start;
-#ifndef CONFIG_DYNAMIC_FTRACE
- /* Dynamic tracing modifies the kernel text section */
set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT);
printk(KERN_INFO "Write protecting the kernel text: %luk\n",
size >> 10);
+ kernel_set_to_readonly = 1;
+
#ifdef CONFIG_CPA_DEBUG
printk(KERN_INFO "Testing CPA: Reverting %lx-%lx\n",
start, start+size);
@@ -1198,7 +1103,6 @@ void mark_rodata_ro(void)
printk(KERN_INFO "Testing CPA: write protecting again\n");
set_pages_ro(virt_to_page(start), size>>PAGE_SHIFT);
#endif
-#endif /* CONFIG_DYNAMIC_FTRACE */
start += size;
size = (unsigned long)__end_rodata - start;
@@ -1217,13 +1121,6 @@ void mark_rodata_ro(void)
}
#endif
-#ifdef CONFIG_BLK_DEV_INITRD
-void free_initrd_mem(unsigned long start, unsigned long end)
-{
- free_init_pages("initrd memory", start, end);
-}
-#endif
-
int __init reserve_bootmem_generic(unsigned long phys, unsigned long len,
int flags)
{
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 07f44d491df1..1753e8020df6 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -48,6 +48,7 @@
#include <asm/kdebug.h>
#include <asm/numa.h>
#include <asm/cacheflush.h>
+#include <asm/init.h>
/*
* end_pfn only includes RAM, while max_pfn_mapped includes all e820 entries.
@@ -61,12 +62,6 @@ static unsigned long dma_reserve __initdata;
DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
-int direct_gbpages
-#ifdef CONFIG_DIRECT_GBPAGES
- = 1
-#endif
-;
-
static int __init parse_direct_gbpages_off(char *arg)
{
direct_gbpages = 0;
@@ -87,12 +82,10 @@ early_param("gbpages", parse_direct_gbpages_on);
* around without checking the pgd every time.
*/
-int after_bootmem;
-
pteval_t __supported_pte_mask __read_mostly = ~_PAGE_IOMAP;
EXPORT_SYMBOL_GPL(__supported_pte_mask);
-static int do_not_nx __cpuinitdata;
+static int disable_nx __cpuinitdata;
/*
* noexec=on|off
@@ -107,9 +100,9 @@ static int __init nonx_setup(char *str)
return -EINVAL;
if (!strncmp(str, "on", 2)) {
__supported_pte_mask |= _PAGE_NX;
- do_not_nx = 0;
+ disable_nx = 0;
} else if (!strncmp(str, "off", 3)) {
- do_not_nx = 1;
+ disable_nx = 1;
__supported_pte_mask &= ~_PAGE_NX;
}
return 0;
@@ -121,7 +114,7 @@ void __cpuinit check_efer(void)
unsigned long efer;
rdmsrl(MSR_EFER, efer);
- if (!(efer & EFER_NX) || do_not_nx)
+ if (!(efer & EFER_NX) || disable_nx)
__supported_pte_mask &= ~_PAGE_NX;
}
@@ -325,13 +318,9 @@ void __init cleanup_highmap(void)
}
}
-static unsigned long __initdata table_start;
-static unsigned long __meminitdata table_end;
-static unsigned long __meminitdata table_top;
-
static __ref void *alloc_low_page(unsigned long *phys)
{
- unsigned long pfn = table_end++;
+ unsigned long pfn = e820_table_end++;
void *adr;
if (after_bootmem) {
@@ -341,7 +330,7 @@ static __ref void *alloc_low_page(unsigned long *phys)
return adr;
}
- if (pfn >= table_top)
+ if (pfn >= e820_table_top)
panic("alloc_low_page: ran out of memory");
adr = early_memremap(pfn * PAGE_SIZE, PAGE_SIZE);
@@ -581,58 +570,10 @@ phys_pud_update(pgd_t *pgd, unsigned long addr, unsigned long end,
return phys_pud_init(pud, addr, end, page_size_mask);
}
-static void __init find_early_table_space(unsigned long end, int use_pse,
- int use_gbpages)
-{
- unsigned long puds, pmds, ptes, tables, start;
-
- puds = (end + PUD_SIZE - 1) >> PUD_SHIFT;
- tables = roundup(puds * sizeof(pud_t), PAGE_SIZE);
- if (use_gbpages) {
- unsigned long extra;
- extra = end - ((end>>PUD_SHIFT) << PUD_SHIFT);
- pmds = (extra + PMD_SIZE - 1) >> PMD_SHIFT;
- } else
- pmds = (end + PMD_SIZE - 1) >> PMD_SHIFT;
- tables += roundup(pmds * sizeof(pmd_t), PAGE_SIZE);
-
- if (use_pse) {
- unsigned long extra;
- extra = end - ((end>>PMD_SHIFT) << PMD_SHIFT);
- ptes = (extra + PAGE_SIZE - 1) >> PAGE_SHIFT;
- } else
- ptes = (end + PAGE_SIZE - 1) >> PAGE_SHIFT;
- tables += roundup(ptes * sizeof(pte_t), PAGE_SIZE);
-
- /*
- * RED-PEN putting page tables only on node 0 could
- * cause a hotspot and fill up ZONE_DMA. The page tables
- * need roughly 0.5KB per GB.
- */
- start = 0x8000;
- table_start = find_e820_area(start, end, tables, PAGE_SIZE);
- if (table_start == -1UL)
- panic("Cannot find space for the kernel page tables");
-
- table_start >>= PAGE_SHIFT;
- table_end = table_start;
- table_top = table_start + (tables >> PAGE_SHIFT);
-
- printk(KERN_DEBUG "kernel direct mapping tables up to %lx @ %lx-%lx\n",
- end, table_start << PAGE_SHIFT, table_top << PAGE_SHIFT);
-}
-
-static void __init init_gbpages(void)
-{
- if (direct_gbpages && cpu_has_gbpages)
- printk(KERN_INFO "Using GB pages for direct mapping\n");
- else
- direct_gbpages = 0;
-}
-
-static unsigned long __meminit kernel_physical_mapping_init(unsigned long start,
- unsigned long end,
- unsigned long page_size_mask)
+unsigned long __init
+kernel_physical_mapping_init(unsigned long start,
+ unsigned long end,
+ unsigned long page_size_mask)
{
unsigned long next, last_map_addr = end;
@@ -669,176 +610,6 @@ static unsigned long __meminit kernel_physical_mapping_init(unsigned long start,
return last_map_addr;
}
-struct map_range {
- unsigned long start;
- unsigned long end;
- unsigned page_size_mask;
-};
-
-#define NR_RANGE_MR 5
-
-static int save_mr(struct map_range *mr, int nr_range,
- unsigned long start_pfn, unsigned long end_pfn,
- unsigned long page_size_mask)
-{
-
- if (start_pfn < end_pfn) {
- if (nr_range >= NR_RANGE_MR)
- panic("run out of range for init_memory_mapping\n");
- mr[nr_range].start = start_pfn<<PAGE_SHIFT;
- mr[nr_range].end = end_pfn<<PAGE_SHIFT;
- mr[nr_range].page_size_mask = page_size_mask;
- nr_range++;
- }
-
- return nr_range;
-}
-
-/*
- * Setup the direct mapping of the physical memory at PAGE_OFFSET.
- * This runs before bootmem is initialized and gets pages directly from
- * the physical memory. To access them they are temporarily mapped.
- */
-unsigned long __init_refok init_memory_mapping(unsigned long start,
- unsigned long end)
-{
- unsigned long last_map_addr = 0;
- unsigned long page_size_mask = 0;
- unsigned long start_pfn, end_pfn;
- unsigned long pos;
-
- struct map_range mr[NR_RANGE_MR];
- int nr_range, i;
- int use_pse, use_gbpages;
-
- printk(KERN_INFO "init_memory_mapping: %016lx-%016lx\n", start, end);
-
- /*
- * Find space for the kernel direct mapping tables.
- *
- * Later we should allocate these tables in the local node of the
- * memory mapped. Unfortunately this is done currently before the
- * nodes are discovered.
- */
- if (!after_bootmem)
- init_gbpages();
-
-#ifdef CONFIG_DEBUG_PAGEALLOC
- /*
- * For CONFIG_DEBUG_PAGEALLOC, identity mapping will use small pages.
- * This will simplify cpa(), which otherwise needs to support splitting
- * large pages into small in interrupt context, etc.
- */
- use_pse = use_gbpages = 0;
-#else
- use_pse = cpu_has_pse;
- use_gbpages = direct_gbpages;
-#endif
-
- if (use_gbpages)
- page_size_mask |= 1 << PG_LEVEL_1G;
- if (use_pse)
- page_size_mask |= 1 << PG_LEVEL_2M;
-
- memset(mr, 0, sizeof(mr));
- nr_range = 0;
-
- /* head if not big page alignment ?*/
- start_pfn = start >> PAGE_SHIFT;
- pos = start_pfn << PAGE_SHIFT;
- end_pfn = ((pos + (PMD_SIZE - 1)) >> PMD_SHIFT)
- << (PMD_SHIFT - PAGE_SHIFT);
- if (end_pfn > (end >> PAGE_SHIFT))
- end_pfn = end >> PAGE_SHIFT;
- if (start_pfn < end_pfn) {
- nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0);
- pos = end_pfn << PAGE_SHIFT;
- }
-
- /* big page (2M) range*/
- start_pfn = ((pos + (PMD_SIZE - 1))>>PMD_SHIFT)
- << (PMD_SHIFT - PAGE_SHIFT);
- end_pfn = ((pos + (PUD_SIZE - 1))>>PUD_SHIFT)
- << (PUD_SHIFT - PAGE_SHIFT);
- if (end_pfn > ((end>>PMD_SHIFT)<<(PMD_SHIFT - PAGE_SHIFT)))
- end_pfn = ((end>>PMD_SHIFT)<<(PMD_SHIFT - PAGE_SHIFT));
- if (start_pfn < end_pfn) {
- nr_range = save_mr(mr, nr_range, start_pfn, end_pfn,
- page_size_mask & (1<<PG_LEVEL_2M));
- pos = end_pfn << PAGE_SHIFT;
- }
-
- /* big page (1G) range */
- start_pfn = ((pos + (PUD_SIZE - 1))>>PUD_SHIFT)
- << (PUD_SHIFT - PAGE_SHIFT);
- end_pfn = (end >> PUD_SHIFT) << (PUD_SHIFT - PAGE_SHIFT);
- if (start_pfn < end_pfn) {
- nr_range = save_mr(mr, nr_range, start_pfn, end_pfn,
- page_size_mask &
- ((1<<PG_LEVEL_2M)|(1<<PG_LEVEL_1G)));
- pos = end_pfn << PAGE_SHIFT;
- }
-
- /* tail is not big page (1G) alignment */
- start_pfn = ((pos + (PMD_SIZE - 1))>>PMD_SHIFT)
- << (PMD_SHIFT - PAGE_SHIFT);
- end_pfn = (end >> PMD_SHIFT) << (PMD_SHIFT - PAGE_SHIFT);
- if (start_pfn < end_pfn) {
- nr_range = save_mr(mr, nr_range, start_pfn, end_pfn,
- page_size_mask & (1<<PG_LEVEL_2M));
- pos = end_pfn << PAGE_SHIFT;
- }
-
- /* tail is not big page (2M) alignment */
- start_pfn = pos>>PAGE_SHIFT;
- end_pfn = end>>PAGE_SHIFT;
- nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0);
-
- /* try to merge same page size and continuous */
- for (i = 0; nr_range > 1 && i < nr_range - 1; i++) {
- unsigned long old_start;
- if (mr[i].end != mr[i+1].start ||
- mr[i].page_size_mask != mr[i+1].page_size_mask)
- continue;
- /* move it */
- old_start = mr[i].start;
- memmove(&mr[i], &mr[i+1],
- (nr_range - 1 - i) * sizeof (struct map_range));
- mr[i--].start = old_start;
- nr_range--;
- }
-
- for (i = 0; i < nr_range; i++)
- printk(KERN_DEBUG " %010lx - %010lx page %s\n",
- mr[i].start, mr[i].end,
- (mr[i].page_size_mask & (1<<PG_LEVEL_1G))?"1G":(
- (mr[i].page_size_mask & (1<<PG_LEVEL_2M))?"2M":"4k"));
-
- if (!after_bootmem)
- find_early_table_space(end, use_pse, use_gbpages);
-
- for (i = 0; i < nr_range; i++)
- last_map_addr = kernel_physical_mapping_init(
- mr[i].start, mr[i].end,
- mr[i].page_size_mask);
-
- if (!after_bootmem)
- mmu_cr4_features = read_cr4();
- __flush_tlb_all();
-
- if (!after_bootmem && table_end > table_start)
- reserve_early(table_start << PAGE_SHIFT,
- table_end << PAGE_SHIFT, "PGTABLE");
-
- printk(KERN_INFO "last_map_addr: %lx end: %lx\n",
- last_map_addr, end);
-
- if (!after_bootmem)
- early_memtest(start, end);
-
- return last_map_addr >> PAGE_SHIFT;
-}
-
#ifndef CONFIG_NUMA
void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn)
{
@@ -910,28 +681,6 @@ EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
#endif /* CONFIG_MEMORY_HOTPLUG */
-/*
- * devmem_is_allowed() checks to see if /dev/mem access to a certain address
- * is valid. The argument is a physical page number.
- *
- *
- * On x86, access has to be given to the first megabyte of ram because that area
- * contains bios code and data regions used by X and dosemu and similar apps.
- * Access has to be given to non-kernel-ram areas as well, these contain the PCI
- * mmio resources as well as potential bios/acpi data regions.
- */
-int devmem_is_allowed(unsigned long pagenr)
-{
- if (pagenr <= 256)
- return 1;
- if (iomem_is_exclusive(pagenr << PAGE_SHIFT))
- return 0;
- if (!page_is_ram(pagenr))
- return 1;
- return 0;
-}
-
-
static struct kcore_list kcore_mem, kcore_vmalloc, kcore_kernel,
kcore_modules, kcore_vsyscall;
@@ -985,21 +734,48 @@ void __init mem_init(void)
const int rodata_test_data = 0xC3;
EXPORT_SYMBOL_GPL(rodata_test_data);
+static int kernel_set_to_readonly;
+
+void set_kernel_text_rw(void)
+{
+ unsigned long start = PFN_ALIGN(_stext);
+ unsigned long end = PFN_ALIGN(__start_rodata);
+
+ if (!kernel_set_to_readonly)
+ return;
+
+ pr_debug("Set kernel text: %lx - %lx for read write\n",
+ start, end);
+
+ set_memory_rw(start, (end - start) >> PAGE_SHIFT);
+}
+
+void set_kernel_text_ro(void)
+{
+ unsigned long start = PFN_ALIGN(_stext);
+ unsigned long end = PFN_ALIGN(__start_rodata);
+
+ if (!kernel_set_to_readonly)
+ return;
+
+ pr_debug("Set kernel text: %lx - %lx for read only\n",
+ start, end);
+
+ set_memory_ro(start, (end - start) >> PAGE_SHIFT);
+}
+
void mark_rodata_ro(void)
{
unsigned long start = PFN_ALIGN(_stext), end = PFN_ALIGN(__end_rodata);
unsigned long rodata_start =
((unsigned long)__start_rodata + PAGE_SIZE - 1) & PAGE_MASK;
-#ifdef CONFIG_DYNAMIC_FTRACE
- /* Dynamic tracing modifies the kernel text section */
- start = rodata_start;
-#endif
-
printk(KERN_INFO "Write protecting the kernel read-only data: %luk\n",
(end - start) >> 10);
set_memory_ro(start, (end - start) >> PAGE_SHIFT);
+ kernel_set_to_readonly = 1;
+
/*
* The rodata section (but not the kernel text!) should also be
* not-executable.
@@ -1019,13 +795,6 @@ void mark_rodata_ro(void)
#endif
-#ifdef CONFIG_BLK_DEV_INITRD
-void free_initrd_mem(unsigned long start, unsigned long end)
-{
- free_init_pages("initrd memory", start, end);
-}
-#endif
-
int __init reserve_bootmem_generic(unsigned long phys, unsigned long len,
int flags)
{
diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c
index 04102d42ff42..8056545e2d39 100644
--- a/arch/x86/mm/iomap_32.c
+++ b/arch/x86/mm/iomap_32.c
@@ -19,10 +19,11 @@
#include <asm/iomap.h>
#include <asm/pat.h>
#include <linux/module.h>
+#include <linux/highmem.h>
int is_io_mapping_possible(resource_size_t base, unsigned long size)
{
-#ifndef CONFIG_X86_PAE
+#if !defined(CONFIG_X86_PAE) && defined(CONFIG_PHYS_ADDR_T_64BIT)
/* There is no way to map greater than 1 << 32 address without PAE */
if (base + size > 0x100000000ULL)
return 0;
@@ -31,16 +32,28 @@ int is_io_mapping_possible(resource_size_t base, unsigned long size)
}
EXPORT_SYMBOL_GPL(is_io_mapping_possible);
-/* Map 'pfn' using fixed map 'type' and protections 'prot'
- */
-void *
-iomap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot)
+void *kmap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot)
{
enum fixed_addresses idx;
unsigned long vaddr;
pagefault_disable();
+ debug_kmap_atomic(type);
+ idx = type + KM_TYPE_NR * smp_processor_id();
+ vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
+ set_pte(kmap_pte - idx, pfn_pte(pfn, prot));
+ arch_flush_lazy_mmu_mode();
+
+ return (void *)vaddr;
+}
+
+/*
+ * Map 'pfn' using fixed map 'type' and protections 'prot'
+ */
+void *
+iomap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot)
+{
/*
* For non-PAT systems, promote PAGE_KERNEL_WC to PAGE_KERNEL_UC_MINUS.
* PAGE_KERNEL_WC maps to PWT, which translates to uncached if the
@@ -50,12 +63,7 @@ iomap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot)
if (!pat_enabled && pgprot_val(prot) == pgprot_val(PAGE_KERNEL_WC))
prot = PAGE_KERNEL_UC_MINUS;
- idx = type + KM_TYPE_NR*smp_processor_id();
- vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
- set_pte(kmap_pte-idx, pfn_pte(pfn, prot));
- arch_flush_lazy_mmu_mode();
-
- return (void*) vaddr;
+ return kmap_atomic_prot_pfn(pfn, type, prot);
}
EXPORT_SYMBOL_GPL(iomap_atomic_prot_pfn);
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 433f7bd4648a..8a450930834f 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -22,13 +22,17 @@
#include <asm/pgalloc.h>
#include <asm/pat.h>
-#ifdef CONFIG_X86_64
-
-static inline int phys_addr_valid(unsigned long addr)
+static inline int phys_addr_valid(resource_size_t addr)
{
- return addr < (1UL << boot_cpu_data.x86_phys_bits);
+#ifdef CONFIG_PHYS_ADDR_T_64BIT
+ return !(addr >> boot_cpu_data.x86_phys_bits);
+#else
+ return 1;
+#endif
}
+#ifdef CONFIG_X86_64
+
unsigned long __phys_addr(unsigned long x)
{
if (x >= __START_KERNEL_map) {
@@ -38,8 +42,7 @@ unsigned long __phys_addr(unsigned long x)
} else {
VIRTUAL_BUG_ON(x < PAGE_OFFSET);
x -= PAGE_OFFSET;
- VIRTUAL_BUG_ON(system_state == SYSTEM_BOOTING ? x > MAXMEM :
- !phys_addr_valid(x));
+ VIRTUAL_BUG_ON(!phys_addr_valid(x));
}
return x;
}
@@ -56,10 +59,8 @@ bool __virt_addr_valid(unsigned long x)
if (x < PAGE_OFFSET)
return false;
x -= PAGE_OFFSET;
- if (system_state == SYSTEM_BOOTING ?
- x > MAXMEM : !phys_addr_valid(x)) {
+ if (!phys_addr_valid(x))
return false;
- }
}
return pfn_valid(x >> PAGE_SHIFT);
@@ -68,18 +69,12 @@ EXPORT_SYMBOL(__virt_addr_valid);
#else
-static inline int phys_addr_valid(unsigned long addr)
-{
- return 1;
-}
-
#ifdef CONFIG_DEBUG_VIRTUAL
unsigned long __phys_addr(unsigned long x)
{
- /* VMALLOC_* aren't constants; not available at the boot time */
+ /* VMALLOC_* aren't constants */
VIRTUAL_BUG_ON(x < PAGE_OFFSET);
- VIRTUAL_BUG_ON(system_state != SYSTEM_BOOTING &&
- is_vmalloc_addr((void *) x));
+ VIRTUAL_BUG_ON(__vmalloc_start_set && is_vmalloc_addr((void *) x));
return x - PAGE_OFFSET;
}
EXPORT_SYMBOL(__phys_addr);
@@ -89,7 +84,9 @@ bool __virt_addr_valid(unsigned long x)
{
if (x < PAGE_OFFSET)
return false;
- if (system_state != SYSTEM_BOOTING && is_vmalloc_addr((void *) x))
+ if (__vmalloc_start_set && is_vmalloc_addr((void *) x))
+ return false;
+ if (x >= FIXADDR_START)
return false;
return pfn_valid((x - PAGE_OFFSET) >> PAGE_SHIFT);
}
@@ -283,15 +280,16 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
return NULL;
area->phys_addr = phys_addr;
vaddr = (unsigned long) area->addr;
- if (ioremap_page_range(vaddr, vaddr + size, phys_addr, prot)) {
+
+ if (kernel_map_sync_memtype(phys_addr, size, prot_val)) {
free_memtype(phys_addr, phys_addr + size);
free_vm_area(area);
return NULL;
}
- if (ioremap_change_attr(vaddr, size, prot_val) < 0) {
+ if (ioremap_page_range(vaddr, vaddr + size, phys_addr, prot)) {
free_memtype(phys_addr, phys_addr + size);
- vunmap(area->addr);
+ free_vm_area(area);
return NULL;
}
@@ -377,7 +375,8 @@ static void __iomem *ioremap_default(resource_size_t phys_addr,
* - UC_MINUS for non-WB-able memory with no other conflicting mappings
* - Inherit from confliting mappings otherwise
*/
- err = reserve_memtype(phys_addr, phys_addr + size, -1, &flags);
+ err = reserve_memtype(phys_addr, phys_addr + size,
+ _PAGE_CACHE_WB, &flags);
if (err < 0)
return NULL;
@@ -508,13 +507,19 @@ static inline pte_t * __init early_ioremap_pte(unsigned long addr)
return &bm_pte[pte_index(addr)];
}
+static unsigned long slot_virt[FIX_BTMAPS_SLOTS] __initdata;
+
void __init early_ioremap_init(void)
{
pmd_t *pmd;
+ int i;
if (early_ioremap_debug)
printk(KERN_INFO "early_ioremap_init()\n");
+ for (i = 0; i < FIX_BTMAPS_SLOTS; i++)
+ slot_virt[i] = __fix_to_virt(FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*i);
+
pmd = early_ioremap_pmd(fix_to_virt(FIX_BTMAP_BEGIN));
memset(bm_pte, 0, sizeof(bm_pte));
pmd_populate_kernel(&init_mm, pmd, bm_pte);
@@ -544,7 +549,7 @@ void __init early_ioremap_reset(void)
}
static void __init __early_set_fixmap(enum fixed_addresses idx,
- unsigned long phys, pgprot_t flags)
+ phys_addr_t phys, pgprot_t flags)
{
unsigned long addr = __fix_to_virt(idx);
pte_t *pte;
@@ -563,7 +568,7 @@ static void __init __early_set_fixmap(enum fixed_addresses idx,
}
static inline void __init early_set_fixmap(enum fixed_addresses idx,
- unsigned long phys, pgprot_t prot)
+ phys_addr_t phys, pgprot_t prot)
{
if (after_paging_init)
__set_fixmap(idx, phys, prot);
@@ -581,6 +586,7 @@ static inline void __init early_clear_fixmap(enum fixed_addresses idx)
static void __iomem *prev_map[FIX_BTMAPS_SLOTS] __initdata;
static unsigned long prev_size[FIX_BTMAPS_SLOTS] __initdata;
+
static int __init check_early_ioremap_leak(void)
{
int count = 0;
@@ -602,9 +608,11 @@ static int __init check_early_ioremap_leak(void)
}
late_initcall(check_early_ioremap_leak);
-static void __init __iomem *__early_ioremap(unsigned long phys_addr, unsigned long size, pgprot_t prot)
+static void __init __iomem *
+__early_ioremap(resource_size_t phys_addr, unsigned long size, pgprot_t prot)
{
- unsigned long offset, last_addr;
+ unsigned long offset;
+ resource_size_t last_addr;
unsigned int nrpages;
enum fixed_addresses idx0, idx;
int i, slot;
@@ -620,15 +628,15 @@ static void __init __iomem *__early_ioremap(unsigned long phys_addr, unsigned lo
}
if (slot < 0) {
- printk(KERN_INFO "early_iomap(%08lx, %08lx) not found slot\n",
- phys_addr, size);
+ printk(KERN_INFO "early_iomap(%08llx, %08lx) not found slot\n",
+ (u64)phys_addr, size);
WARN_ON(1);
return NULL;
}
if (early_ioremap_debug) {
- printk(KERN_INFO "early_ioremap(%08lx, %08lx) [%d] => ",
- phys_addr, size, slot);
+ printk(KERN_INFO "early_ioremap(%08llx, %08lx) [%d] => ",
+ (u64)phys_addr, size, slot);
dump_stack();
}
@@ -668,20 +676,22 @@ static void __init __iomem *__early_ioremap(unsigned long phys_addr, unsigned lo
--nrpages;
}
if (early_ioremap_debug)
- printk(KERN_CONT "%08lx + %08lx\n", offset, fix_to_virt(idx0));
+ printk(KERN_CONT "%08lx + %08lx\n", offset, slot_virt[slot]);
- prev_map[slot] = (void __iomem *)(offset + fix_to_virt(idx0));
+ prev_map[slot] = (void __iomem *)(offset + slot_virt[slot]);
return prev_map[slot];
}
/* Remap an IO device */
-void __init __iomem *early_ioremap(unsigned long phys_addr, unsigned long size)
+void __init __iomem *
+early_ioremap(resource_size_t phys_addr, unsigned long size)
{
return __early_ioremap(phys_addr, size, PAGE_KERNEL_IO);
}
/* Remap memory */
-void __init __iomem *early_memremap(unsigned long phys_addr, unsigned long size)
+void __init __iomem *
+early_memremap(resource_size_t phys_addr, unsigned long size)
{
return __early_ioremap(phys_addr, size, PAGE_KERNEL);
}
@@ -738,8 +748,3 @@ void __init early_iounmap(void __iomem *addr, unsigned long size)
}
prev_map[slot] = NULL;
}
-
-void __this_fixmap_does_not_exist(void)
-{
- WARN_ON(1);
-}
diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c
index 6a518dd08a36..50dc802a1c46 100644
--- a/arch/x86/mm/kmmio.c
+++ b/arch/x86/mm/kmmio.c
@@ -87,7 +87,7 @@ static struct kmmio_probe *get_kmmio_probe(unsigned long addr)
{
struct kmmio_probe *p;
list_for_each_entry_rcu(p, &kmmio_probes, list) {
- if (addr >= p->addr && addr <= (p->addr + p->len))
+ if (addr >= p->addr && addr < (p->addr + p->len))
return p;
}
return NULL;
@@ -310,7 +310,7 @@ static int post_kmmio_handler(unsigned long condition, struct pt_regs *regs)
struct kmmio_context *ctx = &get_cpu_var(kmmio_ctx);
if (!ctx->active) {
- pr_warning("kmmio: spurious debug trap on CPU %d.\n",
+ pr_debug("kmmio: spurious debug trap on CPU %d.\n",
smp_processor_id());
goto out;
}
diff --git a/arch/x86/mm/memtest.c b/arch/x86/mm/memtest.c
index 0bcd7883d036..605c8be06217 100644
--- a/arch/x86/mm/memtest.c
+++ b/arch/x86/mm/memtest.c
@@ -100,6 +100,9 @@ static int __init parse_memtest(char *arg)
{
if (arg)
memtest_pattern = simple_strtoul(arg, NULL, 0);
+ else
+ memtest_pattern = ARRAY_SIZE(patterns);
+
return 0;
}
diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c
index 2c4baa88f2cb..c9342ed8b402 100644
--- a/arch/x86/mm/mmio-mod.c
+++ b/arch/x86/mm/mmio-mod.c
@@ -378,27 +378,34 @@ static void clear_trace_list(void)
}
#ifdef CONFIG_HOTPLUG_CPU
-static cpumask_t downed_cpus;
+static cpumask_var_t downed_cpus;
static void enter_uniprocessor(void)
{
int cpu;
int err;
+ if (downed_cpus == NULL &&
+ !alloc_cpumask_var(&downed_cpus, GFP_KERNEL)) {
+ pr_notice(NAME "Failed to allocate mask\n");
+ goto out;
+ }
+
get_online_cpus();
- downed_cpus = cpu_online_map;
- cpu_clear(first_cpu(cpu_online_map), downed_cpus);
+ cpumask_copy(downed_cpus, cpu_online_mask);
+ cpumask_clear_cpu(cpumask_first(cpu_online_mask), downed_cpus);
if (num_online_cpus() > 1)
pr_notice(NAME "Disabling non-boot CPUs...\n");
put_online_cpus();
- for_each_cpu_mask(cpu, downed_cpus) {
+ for_each_cpu(cpu, downed_cpus) {
err = cpu_down(cpu);
if (!err)
pr_info(NAME "CPU%d is down.\n", cpu);
else
pr_err(NAME "Error taking CPU%d down: %d\n", cpu, err);
}
+out:
if (num_online_cpus() > 1)
pr_warning(NAME "multiple CPUs still online, "
"may miss events.\n");
@@ -411,10 +418,10 @@ static void __ref leave_uniprocessor(void)
int cpu;
int err;
- if (cpus_weight(downed_cpus) == 0)
+ if (downed_cpus == NULL || cpumask_weight(downed_cpus) == 0)
return;
pr_notice(NAME "Re-enabling CPUs...\n");
- for_each_cpu_mask(cpu, downed_cpus) {
+ for_each_cpu(cpu, downed_cpus) {
err = cpu_up(cpu);
if (!err)
pr_info(NAME "enabled CPU%d.\n", cpu);
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
new file mode 100644
index 000000000000..550df481accd
--- /dev/null
+++ b/arch/x86/mm/numa.c
@@ -0,0 +1,67 @@
+/* Common code for 32 and 64-bit NUMA */
+#include <linux/topology.h>
+#include <linux/module.h>
+#include <linux/bootmem.h>
+
+#ifdef CONFIG_DEBUG_PER_CPU_MAPS
+# define DBG(x...) printk(KERN_DEBUG x)
+#else
+# define DBG(x...)
+#endif
+
+/*
+ * Which logical CPUs are on which nodes
+ */
+cpumask_var_t node_to_cpumask_map[MAX_NUMNODES];
+EXPORT_SYMBOL(node_to_cpumask_map);
+
+/*
+ * Allocate node_to_cpumask_map based on number of available nodes
+ * Requires node_possible_map to be valid.
+ *
+ * Note: node_to_cpumask() is not valid until after this is done.
+ * (Use CONFIG_DEBUG_PER_CPU_MAPS to check this.)
+ */
+void __init setup_node_to_cpumask_map(void)
+{
+ unsigned int node, num = 0;
+
+ /* setup nr_node_ids if not done yet */
+ if (nr_node_ids == MAX_NUMNODES) {
+ for_each_node_mask(node, node_possible_map)
+ num = node;
+ nr_node_ids = num + 1;
+ }
+
+ /* allocate the map */
+ for (node = 0; node < nr_node_ids; node++)
+ alloc_bootmem_cpumask_var(&node_to_cpumask_map[node]);
+
+ /* cpumask_of_node() will now work */
+ pr_debug("Node to cpumask map for %d nodes\n", nr_node_ids);
+}
+
+#ifdef CONFIG_DEBUG_PER_CPU_MAPS
+/*
+ * Returns a pointer to the bitmask of CPUs on Node 'node'.
+ */
+const struct cpumask *cpumask_of_node(int node)
+{
+ if (node >= nr_node_ids) {
+ printk(KERN_WARNING
+ "cpumask_of_node(%d): node > nr_node_ids(%d)\n",
+ node, nr_node_ids);
+ dump_stack();
+ return cpu_none_mask;
+ }
+ if (node_to_cpumask_map[node] == NULL) {
+ printk(KERN_WARNING
+ "cpumask_of_node(%d): no node_to_cpumask_map!\n",
+ node);
+ dump_stack();
+ return cpu_online_mask;
+ }
+ return node_to_cpumask_map[node];
+}
+EXPORT_SYMBOL(cpumask_of_node);
+#endif
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index 451fe95a0352..d2530062fe00 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -257,7 +257,7 @@ void resume_map_numa_kva(pgd_t *pgd_base)
}
#endif
-static unsigned long calculate_numa_remap_pages(void)
+static __init unsigned long calculate_numa_remap_pages(void)
{
int nid;
unsigned long size, reserve_pages = 0;
@@ -416,10 +416,11 @@ void __init initmem_init(unsigned long start_pfn,
for_each_online_node(nid)
propagate_e820_map_node(nid);
- for_each_online_node(nid)
+ for_each_online_node(nid) {
memset(NODE_DATA(nid), 0, sizeof(struct pglist_data));
+ NODE_DATA(nid)->bdata = &bootmem_node_data[nid];
+ }
- NODE_DATA(0)->bdata = &bootmem_node_data[0];
setup_bootmem_allocator();
}
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index 64c9cf043cdd..2d05a12029dc 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -20,12 +20,6 @@
#include <asm/acpi.h>
#include <asm/k8.h>
-#ifdef CONFIG_DEBUG_PER_CPU_MAPS
-# define DBG(x...) printk(KERN_DEBUG x)
-#else
-# define DBG(x...)
-#endif
-
struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;
EXPORT_SYMBOL(node_data);
@@ -49,12 +43,6 @@ DEFINE_EARLY_PER_CPU(int, x86_cpu_to_node_map, NUMA_NO_NODE);
EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_node_map);
/*
- * Which logical CPUs are on which nodes
- */
-cpumask_t *node_to_cpumask_map;
-EXPORT_SYMBOL(node_to_cpumask_map);
-
-/*
* Given a shift value, try to populate memnodemap[]
* Returns :
* 1 if OK
@@ -200,6 +188,9 @@ void __init setup_node_bootmem(int nodeid, unsigned long start,
const int pgdat_size = roundup(sizeof(pg_data_t), PAGE_SIZE);
int nid;
+ if (!end)
+ return;
+
start = roundup(start, ZONE_ALIGN);
printk(KERN_INFO "Bootmem setup node %d %016lx-%016lx\n", nodeid,
@@ -661,36 +652,6 @@ void __init init_cpu_to_node(void)
#endif
-/*
- * Allocate node_to_cpumask_map based on number of available nodes
- * Requires node_possible_map to be valid.
- *
- * Note: node_to_cpumask() is not valid until after this is done.
- * (Use CONFIG_DEBUG_PER_CPU_MAPS to check this.)
- */
-void __init setup_node_to_cpumask_map(void)
-{
- unsigned int node, num = 0;
- cpumask_t *map;
-
- /* setup nr_node_ids if not done yet */
- if (nr_node_ids == MAX_NUMNODES) {
- for_each_node_mask(node, node_possible_map)
- num = node;
- nr_node_ids = num + 1;
- }
-
- /* allocate the map */
- map = alloc_bootmem_low(nr_node_ids * sizeof(cpumask_t));
- DBG("node_to_cpumask_map at %p for %d nodes\n", map, nr_node_ids);
-
- pr_debug("Node to cpumask map at %p for %d nodes\n",
- map, nr_node_ids);
-
- /* node_to_cpumask() will now work */
- node_to_cpumask_map = map;
-}
-
void __cpuinit numa_set_node(int cpu, int node)
{
int *cpu_to_node_map = early_per_cpu_ptr(x86_cpu_to_node_map);
@@ -723,12 +684,12 @@ void __cpuinit numa_clear_node(int cpu)
void __cpuinit numa_add_cpu(int cpu)
{
- cpu_set(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]);
+ cpumask_set_cpu(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]);
}
void __cpuinit numa_remove_cpu(int cpu)
{
- cpu_clear(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]);
+ cpumask_clear_cpu(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]);
}
#else /* CONFIG_DEBUG_PER_CPU_MAPS */
@@ -739,20 +700,20 @@ void __cpuinit numa_remove_cpu(int cpu)
static void __cpuinit numa_set_cpumask(int cpu, int enable)
{
int node = early_cpu_to_node(cpu);
- cpumask_t *mask;
+ struct cpumask *mask;
char buf[64];
- if (node_to_cpumask_map == NULL) {
- printk(KERN_ERR "node_to_cpumask_map NULL\n");
+ mask = node_to_cpumask_map[node];
+ if (mask == NULL) {
+ printk(KERN_ERR "node_to_cpumask_map[%i] NULL\n", node);
dump_stack();
return;
}
- mask = &node_to_cpumask_map[node];
if (enable)
- cpu_set(cpu, *mask);
+ cpumask_set_cpu(cpu, mask);
else
- cpu_clear(cpu, *mask);
+ cpumask_clear_cpu(cpu, mask);
cpulist_scnprintf(buf, sizeof(buf), mask);
printk(KERN_DEBUG "%s cpu %d node %d: mask now %s\n",
@@ -799,59 +760,6 @@ int early_cpu_to_node(int cpu)
return per_cpu(x86_cpu_to_node_map, cpu);
}
-
-/* empty cpumask */
-static const cpumask_t cpu_mask_none;
-
-/*
- * Returns a pointer to the bitmask of CPUs on Node 'node'.
- */
-const cpumask_t *cpumask_of_node(int node)
-{
- if (node_to_cpumask_map == NULL) {
- printk(KERN_WARNING
- "cpumask_of_node(%d): no node_to_cpumask_map!\n",
- node);
- dump_stack();
- return (const cpumask_t *)&cpu_online_map;
- }
- if (node >= nr_node_ids) {
- printk(KERN_WARNING
- "cpumask_of_node(%d): node > nr_node_ids(%d)\n",
- node, nr_node_ids);
- dump_stack();
- return &cpu_mask_none;
- }
- return &node_to_cpumask_map[node];
-}
-EXPORT_SYMBOL(cpumask_of_node);
-
-/*
- * Returns a bitmask of CPUs on Node 'node'.
- *
- * Side note: this function creates the returned cpumask on the stack
- * so with a high NR_CPUS count, excessive stack space is used. The
- * node_to_cpumask_ptr function should be used whenever possible.
- */
-cpumask_t node_to_cpumask(int node)
-{
- if (node_to_cpumask_map == NULL) {
- printk(KERN_WARNING
- "node_to_cpumask(%d): no node_to_cpumask_map!\n", node);
- dump_stack();
- return cpu_online_map;
- }
- if (node >= nr_node_ids) {
- printk(KERN_WARNING
- "node_to_cpumask(%d): node > nr_node_ids(%d)\n",
- node, nr_node_ids);
- dump_stack();
- return cpu_mask_none;
- }
- return node_to_cpumask_map[node];
-}
-EXPORT_SYMBOL(node_to_cpumask);
-
/*
* --------- end of debug versions of the numa functions ---------
*/
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 9c4294986af7..797f9f107cb6 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -16,6 +16,7 @@
#include <asm/processor.h>
#include <asm/tlbflush.h>
#include <asm/sections.h>
+#include <asm/setup.h>
#include <asm/uaccess.h>
#include <asm/pgalloc.h>
#include <asm/proto.h>
@@ -33,6 +34,7 @@ struct cpa_data {
unsigned long pfn;
unsigned force_split : 1;
int curpage;
+ struct page **pages;
};
/*
@@ -45,6 +47,7 @@ static DEFINE_SPINLOCK(cpa_lock);
#define CPA_FLUSHTLB 1
#define CPA_ARRAY 2
+#define CPA_PAGES_ARRAY 4
#ifdef CONFIG_PROC_FS
static unsigned long direct_pages_count[PG_LEVEL_NUM];
@@ -95,7 +98,7 @@ static inline unsigned long highmap_start_pfn(void)
static inline unsigned long highmap_end_pfn(void)
{
- return __pa(roundup((unsigned long)_end, PMD_SIZE)) >> PAGE_SHIFT;
+ return __pa(roundup(_brk_end, PMD_SIZE)) >> PAGE_SHIFT;
}
#endif
@@ -201,10 +204,10 @@ static void cpa_flush_range(unsigned long start, int numpages, int cache)
}
}
-static void cpa_flush_array(unsigned long *start, int numpages, int cache)
+static void cpa_flush_array(unsigned long *start, int numpages, int cache,
+ int in_flags, struct page **pages)
{
unsigned int i, level;
- unsigned long *addr;
BUG_ON(irqs_disabled());
@@ -225,14 +228,22 @@ static void cpa_flush_array(unsigned long *start, int numpages, int cache)
* will cause all other CPUs to flush the same
* cachelines:
*/
- for (i = 0, addr = start; i < numpages; i++, addr++) {
- pte_t *pte = lookup_address(*addr, &level);
+ for (i = 0; i < numpages; i++) {
+ unsigned long addr;
+ pte_t *pte;
+
+ if (in_flags & CPA_PAGES_ARRAY)
+ addr = (unsigned long)page_address(pages[i]);
+ else
+ addr = start[i];
+
+ pte = lookup_address(addr, &level);
/*
* Only flush present addresses:
*/
if (pte && (pte_val(*pte) & _PAGE_PRESENT))
- clflush_cache_range((void *) *addr, PAGE_SIZE);
+ clflush_cache_range((void *)addr, PAGE_SIZE);
}
}
@@ -584,7 +595,9 @@ static int __change_page_attr(struct cpa_data *cpa, int primary)
unsigned int level;
pte_t *kpte, old_pte;
- if (cpa->flags & CPA_ARRAY)
+ if (cpa->flags & CPA_PAGES_ARRAY)
+ address = (unsigned long)page_address(cpa->pages[cpa->curpage]);
+ else if (cpa->flags & CPA_ARRAY)
address = cpa->vaddr[cpa->curpage];
else
address = *cpa->vaddr;
@@ -687,7 +700,9 @@ static int cpa_process_alias(struct cpa_data *cpa)
* No need to redo, when the primary call touched the direct
* mapping already:
*/
- if (cpa->flags & CPA_ARRAY)
+ if (cpa->flags & CPA_PAGES_ARRAY)
+ vaddr = (unsigned long)page_address(cpa->pages[cpa->curpage]);
+ else if (cpa->flags & CPA_ARRAY)
vaddr = cpa->vaddr[cpa->curpage];
else
vaddr = *cpa->vaddr;
@@ -698,7 +713,7 @@ static int cpa_process_alias(struct cpa_data *cpa)
alias_cpa = *cpa;
temp_cpa_vaddr = (unsigned long) __va(cpa->pfn << PAGE_SHIFT);
alias_cpa.vaddr = &temp_cpa_vaddr;
- alias_cpa.flags &= ~CPA_ARRAY;
+ alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY);
ret = __change_page_attr_set_clr(&alias_cpa, 0);
@@ -711,7 +726,7 @@ static int cpa_process_alias(struct cpa_data *cpa)
* No need to redo, when the primary call touched the high
* mapping already:
*/
- if (within(vaddr, (unsigned long) _text, (unsigned long) _end))
+ if (within(vaddr, (unsigned long) _text, _brk_end))
return 0;
/*
@@ -724,7 +739,7 @@ static int cpa_process_alias(struct cpa_data *cpa)
alias_cpa = *cpa;
temp_cpa_vaddr = (cpa->pfn << PAGE_SHIFT) + __START_KERNEL_map - phys_base;
alias_cpa.vaddr = &temp_cpa_vaddr;
- alias_cpa.flags &= ~CPA_ARRAY;
+ alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY);
/*
* The high mapping range is imprecise, so ignore the return value.
@@ -745,7 +760,7 @@ static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias)
*/
cpa->numpages = numpages;
/* for array changes, we can't use large page */
- if (cpa->flags & CPA_ARRAY)
+ if (cpa->flags & (CPA_ARRAY | CPA_PAGES_ARRAY))
cpa->numpages = 1;
if (!debug_pagealloc)
@@ -769,7 +784,7 @@ static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias)
*/
BUG_ON(cpa->numpages > numpages);
numpages -= cpa->numpages;
- if (cpa->flags & CPA_ARRAY)
+ if (cpa->flags & (CPA_PAGES_ARRAY | CPA_ARRAY))
cpa->curpage++;
else
*cpa->vaddr += cpa->numpages * PAGE_SIZE;
@@ -786,7 +801,8 @@ static inline int cache_attr(pgprot_t attr)
static int change_page_attr_set_clr(unsigned long *addr, int numpages,
pgprot_t mask_set, pgprot_t mask_clr,
- int force_split, int array)
+ int force_split, int in_flag,
+ struct page **pages)
{
struct cpa_data cpa;
int ret, cache, checkalias;
@@ -801,15 +817,7 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages,
return 0;
/* Ensure we are PAGE_SIZE aligned */
- if (!array) {
- if (*addr & ~PAGE_MASK) {
- *addr &= PAGE_MASK;
- /*
- * People should not be passing in unaligned addresses:
- */
- WARN_ON_ONCE(1);
- }
- } else {
+ if (in_flag & CPA_ARRAY) {
int i;
for (i = 0; i < numpages; i++) {
if (addr[i] & ~PAGE_MASK) {
@@ -817,6 +825,18 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages,
WARN_ON_ONCE(1);
}
}
+ } else if (!(in_flag & CPA_PAGES_ARRAY)) {
+ /*
+ * in_flag of CPA_PAGES_ARRAY implies it is aligned.
+ * No need to cehck in that case
+ */
+ if (*addr & ~PAGE_MASK) {
+ *addr &= PAGE_MASK;
+ /*
+ * People should not be passing in unaligned addresses:
+ */
+ WARN_ON_ONCE(1);
+ }
}
/* Must avoid aliasing mappings in the highmem code */
@@ -832,6 +852,7 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages,
arch_flush_lazy_mmu_mode();
cpa.vaddr = addr;
+ cpa.pages = pages;
cpa.numpages = numpages;
cpa.mask_set = mask_set;
cpa.mask_clr = mask_clr;
@@ -839,8 +860,8 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages,
cpa.curpage = 0;
cpa.force_split = force_split;
- if (array)
- cpa.flags |= CPA_ARRAY;
+ if (in_flag & (CPA_ARRAY | CPA_PAGES_ARRAY))
+ cpa.flags |= in_flag;
/* No alias checking for _NX bit modifications */
checkalias = (pgprot_val(mask_set) | pgprot_val(mask_clr)) != _PAGE_NX;
@@ -866,9 +887,10 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages,
* wbindv):
*/
if (!ret && cpu_has_clflush) {
- if (cpa.flags & CPA_ARRAY)
- cpa_flush_array(addr, numpages, cache);
- else
+ if (cpa.flags & (CPA_PAGES_ARRAY | CPA_ARRAY)) {
+ cpa_flush_array(addr, numpages, cache,
+ cpa.flags, pages);
+ } else
cpa_flush_range(*addr, numpages, cache);
} else
cpa_flush_all(cache);
@@ -888,14 +910,28 @@ static inline int change_page_attr_set(unsigned long *addr, int numpages,
pgprot_t mask, int array)
{
return change_page_attr_set_clr(addr, numpages, mask, __pgprot(0), 0,
- array);
+ (array ? CPA_ARRAY : 0), NULL);
}
static inline int change_page_attr_clear(unsigned long *addr, int numpages,
pgprot_t mask, int array)
{
return change_page_attr_set_clr(addr, numpages, __pgprot(0), mask, 0,
- array);
+ (array ? CPA_ARRAY : 0), NULL);
+}
+
+static inline int cpa_set_pages_array(struct page **pages, int numpages,
+ pgprot_t mask)
+{
+ return change_page_attr_set_clr(NULL, numpages, mask, __pgprot(0), 0,
+ CPA_PAGES_ARRAY, pages);
+}
+
+static inline int cpa_clear_pages_array(struct page **pages, int numpages,
+ pgprot_t mask)
+{
+ return change_page_attr_set_clr(NULL, numpages, __pgprot(0), mask, 0,
+ CPA_PAGES_ARRAY, pages);
}
int _set_memory_uc(unsigned long addr, int numpages)
@@ -909,71 +945,94 @@ int _set_memory_uc(unsigned long addr, int numpages)
int set_memory_uc(unsigned long addr, int numpages)
{
+ int ret;
+
/*
* for now UC MINUS. see comments in ioremap_nocache()
*/
- if (reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE,
- _PAGE_CACHE_UC_MINUS, NULL))
- return -EINVAL;
+ ret = reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE,
+ _PAGE_CACHE_UC_MINUS, NULL);
+ if (ret)
+ goto out_err;
+
+ ret = _set_memory_uc(addr, numpages);
+ if (ret)
+ goto out_free;
- return _set_memory_uc(addr, numpages);
+ return 0;
+
+out_free:
+ free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE);
+out_err:
+ return ret;
}
EXPORT_SYMBOL(set_memory_uc);
int set_memory_array_uc(unsigned long *addr, int addrinarray)
{
- unsigned long start;
- unsigned long end;
- int i;
+ int i, j;
+ int ret;
+
/*
* for now UC MINUS. see comments in ioremap_nocache()
*/
for (i = 0; i < addrinarray; i++) {
- start = __pa(addr[i]);
- for (end = start + PAGE_SIZE; i < addrinarray - 1; end += PAGE_SIZE) {
- if (end != __pa(addr[i + 1]))
- break;
- i++;
- }
- if (reserve_memtype(start, end, _PAGE_CACHE_UC_MINUS, NULL))
- goto out;
+ ret = reserve_memtype(__pa(addr[i]), __pa(addr[i]) + PAGE_SIZE,
+ _PAGE_CACHE_UC_MINUS, NULL);
+ if (ret)
+ goto out_free;
}
- return change_page_attr_set(addr, addrinarray,
+ ret = change_page_attr_set(addr, addrinarray,
__pgprot(_PAGE_CACHE_UC_MINUS), 1);
-out:
- for (i = 0; i < addrinarray; i++) {
- unsigned long tmp = __pa(addr[i]);
-
- if (tmp == start)
- break;
- for (end = tmp + PAGE_SIZE; i < addrinarray - 1; end += PAGE_SIZE) {
- if (end != __pa(addr[i + 1]))
- break;
- i++;
- }
- free_memtype(tmp, end);
- }
- return -EINVAL;
+ if (ret)
+ goto out_free;
+
+ return 0;
+
+out_free:
+ for (j = 0; j < i; j++)
+ free_memtype(__pa(addr[j]), __pa(addr[j]) + PAGE_SIZE);
+
+ return ret;
}
EXPORT_SYMBOL(set_memory_array_uc);
int _set_memory_wc(unsigned long addr, int numpages)
{
- return change_page_attr_set(&addr, numpages,
+ int ret;
+ ret = change_page_attr_set(&addr, numpages,
+ __pgprot(_PAGE_CACHE_UC_MINUS), 0);
+
+ if (!ret) {
+ ret = change_page_attr_set(&addr, numpages,
__pgprot(_PAGE_CACHE_WC), 0);
+ }
+ return ret;
}
int set_memory_wc(unsigned long addr, int numpages)
{
+ int ret;
+
if (!pat_enabled)
return set_memory_uc(addr, numpages);
- if (reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE,
- _PAGE_CACHE_WC, NULL))
- return -EINVAL;
+ ret = reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE,
+ _PAGE_CACHE_WC, NULL);
+ if (ret)
+ goto out_err;
+
+ ret = _set_memory_wc(addr, numpages);
+ if (ret)
+ goto out_free;
+
+ return 0;
- return _set_memory_wc(addr, numpages);
+out_free:
+ free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE);
+out_err:
+ return ret;
}
EXPORT_SYMBOL(set_memory_wc);
@@ -985,29 +1044,31 @@ int _set_memory_wb(unsigned long addr, int numpages)
int set_memory_wb(unsigned long addr, int numpages)
{
- free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE);
+ int ret;
+
+ ret = _set_memory_wb(addr, numpages);
+ if (ret)
+ return ret;
- return _set_memory_wb(addr, numpages);
+ free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE);
+ return 0;
}
EXPORT_SYMBOL(set_memory_wb);
int set_memory_array_wb(unsigned long *addr, int addrinarray)
{
int i;
+ int ret;
- for (i = 0; i < addrinarray; i++) {
- unsigned long start = __pa(addr[i]);
- unsigned long end;
-
- for (end = start + PAGE_SIZE; i < addrinarray - 1; end += PAGE_SIZE) {
- if (end != __pa(addr[i + 1]))
- break;
- i++;
- }
- free_memtype(start, end);
- }
- return change_page_attr_clear(addr, addrinarray,
+ ret = change_page_attr_clear(addr, addrinarray,
__pgprot(_PAGE_CACHE_MASK), 1);
+ if (ret)
+ return ret;
+
+ for (i = 0; i < addrinarray; i++)
+ free_memtype(__pa(addr[i]), __pa(addr[i]) + PAGE_SIZE);
+
+ return 0;
}
EXPORT_SYMBOL(set_memory_array_wb);
@@ -1043,7 +1104,7 @@ int set_memory_np(unsigned long addr, int numpages)
int set_memory_4k(unsigned long addr, int numpages)
{
return change_page_attr_set_clr(&addr, numpages, __pgprot(0),
- __pgprot(0), 1, 0);
+ __pgprot(0), 1, 0, NULL);
}
int set_pages_uc(struct page *page, int numpages)
@@ -1054,6 +1115,35 @@ int set_pages_uc(struct page *page, int numpages)
}
EXPORT_SYMBOL(set_pages_uc);
+int set_pages_array_uc(struct page **pages, int addrinarray)
+{
+ unsigned long start;
+ unsigned long end;
+ int i;
+ int free_idx;
+
+ for (i = 0; i < addrinarray; i++) {
+ start = (unsigned long)page_address(pages[i]);
+ end = start + PAGE_SIZE;
+ if (reserve_memtype(start, end, _PAGE_CACHE_UC_MINUS, NULL))
+ goto err_out;
+ }
+
+ if (cpa_set_pages_array(pages, addrinarray,
+ __pgprot(_PAGE_CACHE_UC_MINUS)) == 0) {
+ return 0; /* Success */
+ }
+err_out:
+ free_idx = i;
+ for (i = 0; i < free_idx; i++) {
+ start = (unsigned long)page_address(pages[i]);
+ end = start + PAGE_SIZE;
+ free_memtype(start, end);
+ }
+ return -EINVAL;
+}
+EXPORT_SYMBOL(set_pages_array_uc);
+
int set_pages_wb(struct page *page, int numpages)
{
unsigned long addr = (unsigned long)page_address(page);
@@ -1062,6 +1152,28 @@ int set_pages_wb(struct page *page, int numpages)
}
EXPORT_SYMBOL(set_pages_wb);
+int set_pages_array_wb(struct page **pages, int addrinarray)
+{
+ int retval;
+ unsigned long start;
+ unsigned long end;
+ int i;
+
+ retval = cpa_clear_pages_array(pages, addrinarray,
+ __pgprot(_PAGE_CACHE_MASK));
+ if (retval)
+ return retval;
+
+ for (i = 0; i < addrinarray; i++) {
+ start = (unsigned long)page_address(pages[i]);
+ end = start + PAGE_SIZE;
+ free_memtype(start, end);
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL(set_pages_array_wb);
+
int set_pages_x(struct page *page, int numpages)
{
unsigned long addr = (unsigned long)page_address(page);
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 2ed37158012d..e6718bb28065 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -31,7 +31,7 @@
#ifdef CONFIG_X86_PAT
int __read_mostly pat_enabled = 1;
-void __cpuinit pat_disable(const char *reason)
+static inline void pat_disable(const char *reason)
{
pat_enabled = 0;
printk(KERN_INFO "%s\n", reason);
@@ -182,10 +182,10 @@ static unsigned long pat_x_mtrr_type(u64 start, u64 end, unsigned long req_type)
u8 mtrr_type;
mtrr_type = mtrr_type_lookup(start, end);
- if (mtrr_type == MTRR_TYPE_UNCACHABLE)
- return _PAGE_CACHE_UC;
- if (mtrr_type == MTRR_TYPE_WRCOMB)
- return _PAGE_CACHE_WC;
+ if (mtrr_type != MTRR_TYPE_WRBACK)
+ return _PAGE_CACHE_UC_MINUS;
+
+ return _PAGE_CACHE_WB;
}
return req_type;
@@ -352,23 +352,13 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
return 0;
}
- if (req_type == -1) {
- /*
- * Call mtrr_lookup to get the type hint. This is an
- * optimization for /dev/mem mmap'ers into WB memory (BIOS
- * tools and ACPI tools). Use WB request for WB memory and use
- * UC_MINUS otherwise.
- */
- u8 mtrr_type = mtrr_type_lookup(start, end);
-
- if (mtrr_type == MTRR_TYPE_WRBACK)
- actual_type = _PAGE_CACHE_WB;
- else
- actual_type = _PAGE_CACHE_UC_MINUS;
- } else {
- actual_type = pat_x_mtrr_type(start, end,
- req_type & _PAGE_CACHE_MASK);
- }
+ /*
+ * Call mtrr_lookup to get the type hint. This is an
+ * optimization for /dev/mem mmap'ers into WB memory (BIOS
+ * tools and ACPI tools). Use WB request for WB memory and use
+ * UC_MINUS otherwise.
+ */
+ actual_type = pat_x_mtrr_type(start, end, req_type & _PAGE_CACHE_MASK);
if (new_type)
*new_type = actual_type;
@@ -546,9 +536,7 @@ static inline int range_is_allowed(unsigned long pfn, unsigned long size)
int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
unsigned long size, pgprot_t *vma_prot)
{
- u64 offset = ((u64) pfn) << PAGE_SHIFT;
- unsigned long flags = -1;
- int retval;
+ unsigned long flags = _PAGE_CACHE_WB;
if (!range_is_allowed(pfn, size))
return 0;
@@ -576,64 +564,11 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
}
#endif
- /*
- * With O_SYNC, we can only take UC_MINUS mapping. Fail if we cannot.
- *
- * Without O_SYNC, we want to get
- * - WB for WB-able memory and no other conflicting mappings
- * - UC_MINUS for non-WB-able memory with no other conflicting mappings
- * - Inherit from confliting mappings otherwise
- */
- if (flags != -1) {
- retval = reserve_memtype(offset, offset + size, flags, NULL);
- } else {
- retval = reserve_memtype(offset, offset + size, -1, &flags);
- }
-
- if (retval < 0)
- return 0;
-
- if (((pfn < max_low_pfn_mapped) ||
- (pfn >= (1UL<<(32 - PAGE_SHIFT)) && pfn < max_pfn_mapped)) &&
- ioremap_change_attr((unsigned long)__va(offset), size, flags) < 0) {
- free_memtype(offset, offset + size);
- printk(KERN_INFO
- "%s:%d /dev/mem ioremap_change_attr failed %s for %Lx-%Lx\n",
- current->comm, current->pid,
- cattr_name(flags),
- offset, (unsigned long long)(offset + size));
- return 0;
- }
-
*vma_prot = __pgprot((pgprot_val(*vma_prot) & ~_PAGE_CACHE_MASK) |
flags);
return 1;
}
-void map_devmem(unsigned long pfn, unsigned long size, pgprot_t vma_prot)
-{
- unsigned long want_flags = (pgprot_val(vma_prot) & _PAGE_CACHE_MASK);
- u64 addr = (u64)pfn << PAGE_SHIFT;
- unsigned long flags;
-
- reserve_memtype(addr, addr + size, want_flags, &flags);
- if (flags != want_flags) {
- printk(KERN_INFO
- "%s:%d /dev/mem expected mapping type %s for %Lx-%Lx, got %s\n",
- current->comm, current->pid,
- cattr_name(want_flags),
- addr, (unsigned long long)(addr + size),
- cattr_name(flags));
- }
-}
-
-void unmap_devmem(unsigned long pfn, unsigned long size, pgprot_t vma_prot)
-{
- u64 addr = (u64)pfn << PAGE_SHIFT;
-
- free_memtype(addr, addr + size);
-}
-
/*
* Change the memory type for the physial address range in kernel identity
* mapping space if that range is a part of identity map.
@@ -671,16 +606,17 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot,
{
int is_ram = 0;
int ret;
- unsigned long flags;
unsigned long want_flags = (pgprot_val(*vma_prot) & _PAGE_CACHE_MASK);
+ unsigned long flags = want_flags;
is_ram = pat_pagerange_is_ram(paddr, paddr + size);
/*
- * reserve_pfn_range() doesn't support RAM pages.
+ * reserve_pfn_range() doesn't support RAM pages. Maintain the current
+ * behavior with RAM pages by returning success.
*/
if (is_ram != 0)
- return -EINVAL;
+ return 0;
ret = reserve_memtype(paddr, paddr + size, want_flags, &flags);
if (ret)
@@ -733,29 +669,28 @@ static void free_pfn_range(u64 paddr, unsigned long size)
*
* If the vma has a linear pfn mapping for the entire range, we get the prot
* from pte and reserve the entire vma range with single reserve_pfn_range call.
- * Otherwise, we reserve the entire vma range, my ging through the PTEs page
- * by page to get physical address and protection.
*/
int track_pfn_vma_copy(struct vm_area_struct *vma)
{
- int retval = 0;
- unsigned long i, j;
resource_size_t paddr;
unsigned long prot;
- unsigned long vma_start = vma->vm_start;
- unsigned long vma_end = vma->vm_end;
- unsigned long vma_size = vma_end - vma_start;
+ unsigned long vma_size = vma->vm_end - vma->vm_start;
pgprot_t pgprot;
if (!pat_enabled)
return 0;
+ /*
+ * For now, only handle remap_pfn_range() vmas where
+ * is_linear_pfn_mapping() == TRUE. Handling of
+ * vm_insert_pfn() is TBD.
+ */
if (is_linear_pfn_mapping(vma)) {
/*
* reserve the whole chunk covered by vma. We need the
* starting address and protection from pte.
*/
- if (follow_phys(vma, vma_start, 0, &prot, &paddr)) {
+ if (follow_phys(vma, vma->vm_start, 0, &prot, &paddr)) {
WARN_ON_ONCE(1);
return -EINVAL;
}
@@ -763,28 +698,7 @@ int track_pfn_vma_copy(struct vm_area_struct *vma)
return reserve_pfn_range(paddr, vma_size, &pgprot, 1);
}
- /* reserve entire vma page by page, using pfn and prot from pte */
- for (i = 0; i < vma_size; i += PAGE_SIZE) {
- if (follow_phys(vma, vma_start + i, 0, &prot, &paddr))
- continue;
-
- pgprot = __pgprot(prot);
- retval = reserve_pfn_range(paddr, PAGE_SIZE, &pgprot, 1);
- if (retval)
- goto cleanup_ret;
- }
return 0;
-
-cleanup_ret:
- /* Reserve error: Cleanup partial reservation and return error */
- for (j = 0; j < i; j += PAGE_SIZE) {
- if (follow_phys(vma, vma_start + j, 0, &prot, &paddr))
- continue;
-
- free_pfn_range(paddr, PAGE_SIZE);
- }
-
- return retval;
}
/*
@@ -794,50 +708,28 @@ cleanup_ret:
* prot is passed in as a parameter for the new mapping. If the vma has a
* linear pfn mapping for the entire range reserve the entire vma range with
* single reserve_pfn_range call.
- * Otherwise, we look t the pfn and size and reserve only the specified range
- * page by page.
- *
- * Note that this function can be called with caller trying to map only a
- * subrange/page inside the vma.
*/
int track_pfn_vma_new(struct vm_area_struct *vma, pgprot_t *prot,
unsigned long pfn, unsigned long size)
{
- int retval = 0;
- unsigned long i, j;
- resource_size_t base_paddr;
resource_size_t paddr;
- unsigned long vma_start = vma->vm_start;
- unsigned long vma_end = vma->vm_end;
- unsigned long vma_size = vma_end - vma_start;
+ unsigned long vma_size = vma->vm_end - vma->vm_start;
if (!pat_enabled)
return 0;
+ /*
+ * For now, only handle remap_pfn_range() vmas where
+ * is_linear_pfn_mapping() == TRUE. Handling of
+ * vm_insert_pfn() is TBD.
+ */
if (is_linear_pfn_mapping(vma)) {
/* reserve the whole chunk starting from vm_pgoff */
paddr = (resource_size_t)vma->vm_pgoff << PAGE_SHIFT;
return reserve_pfn_range(paddr, vma_size, prot, 0);
}
- /* reserve page by page using pfn and size */
- base_paddr = (resource_size_t)pfn << PAGE_SHIFT;
- for (i = 0; i < size; i += PAGE_SIZE) {
- paddr = base_paddr + i;
- retval = reserve_pfn_range(paddr, PAGE_SIZE, prot, 0);
- if (retval)
- goto cleanup_ret;
- }
return 0;
-
-cleanup_ret:
- /* Reserve error: Cleanup partial reservation and return error */
- for (j = 0; j < i; j += PAGE_SIZE) {
- paddr = base_paddr + j;
- free_pfn_range(paddr, PAGE_SIZE);
- }
-
- return retval;
}
/*
@@ -848,39 +740,23 @@ cleanup_ret:
void untrack_pfn_vma(struct vm_area_struct *vma, unsigned long pfn,
unsigned long size)
{
- unsigned long i;
resource_size_t paddr;
- unsigned long prot;
- unsigned long vma_start = vma->vm_start;
- unsigned long vma_end = vma->vm_end;
- unsigned long vma_size = vma_end - vma_start;
+ unsigned long vma_size = vma->vm_end - vma->vm_start;
if (!pat_enabled)
return;
+ /*
+ * For now, only handle remap_pfn_range() vmas where
+ * is_linear_pfn_mapping() == TRUE. Handling of
+ * vm_insert_pfn() is TBD.
+ */
if (is_linear_pfn_mapping(vma)) {
/* free the whole chunk starting from vm_pgoff */
paddr = (resource_size_t)vma->vm_pgoff << PAGE_SHIFT;
free_pfn_range(paddr, vma_size);
return;
}
-
- if (size != 0 && size != vma_size) {
- /* free page by page, using pfn and size */
- paddr = (resource_size_t)pfn << PAGE_SHIFT;
- for (i = 0; i < size; i += PAGE_SIZE) {
- paddr = paddr + i;
- free_pfn_range(paddr, PAGE_SIZE);
- }
- } else {
- /* free entire vma, page by page, using the pfn from pte */
- for (i = 0; i < vma_size; i += PAGE_SIZE) {
- if (follow_phys(vma, vma_start + i, 0, &prot, &paddr))
- continue;
-
- free_pfn_range(paddr, PAGE_SIZE);
- }
- }
}
pgprot_t pgprot_writecombine(pgprot_t prot)
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 5b7c7c8464fe..7aa03a5389f5 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -345,7 +345,8 @@ void __native_set_fixmap(enum fixed_addresses idx, pte_t pte)
fixmaps_set++;
}
-void native_set_fixmap(enum fixed_addresses idx, unsigned long phys, pgprot_t flags)
+void native_set_fixmap(enum fixed_addresses idx, phys_addr_t phys,
+ pgprot_t flags)
{
__native_set_fixmap(idx, pfn_pte(phys >> PAGE_SHIFT, flags));
}
diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c
index f2e477c91c1b..46c8834aedc0 100644
--- a/arch/x86/mm/pgtable_32.c
+++ b/arch/x86/mm/pgtable_32.c
@@ -50,7 +50,7 @@ void set_pte_vaddr(unsigned long vaddr, pte_t pteval)
}
pte = pte_offset_kernel(pmd, vaddr);
if (pte_val(pteval))
- set_pte_present(&init_mm, vaddr, pte, pteval);
+ set_pte_at(&init_mm, vaddr, pte, pteval);
else
pte_clear(&init_mm, vaddr, pte);
diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c
index 574c8bc95ef0..33c5fa57e43d 100644
--- a/arch/x86/mm/srat_64.c
+++ b/arch/x86/mm/srat_64.c
@@ -28,6 +28,7 @@ int acpi_numa __initdata;
static struct acpi_table_slit *acpi_slit;
static nodemask_t nodes_parsed __initdata;
+static nodemask_t cpu_nodes_parsed __initdata;
static struct bootnode nodes[MAX_NUMNODES] __initdata;
static struct bootnode nodes_add[MAX_NUMNODES];
static int found_add_area __initdata;
@@ -116,6 +117,37 @@ void __init acpi_numa_slit_init(struct acpi_table_slit *slit)
reserve_early(phys, phys + length, "ACPI SLIT");
}
+/* Callback for Proximity Domain -> x2APIC mapping */
+void __init
+acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa)
+{
+ int pxm, node;
+ int apic_id;
+
+ if (srat_disabled())
+ return;
+ if (pa->header.length < sizeof(struct acpi_srat_x2apic_cpu_affinity)) {
+ bad_srat();
+ return;
+ }
+ if ((pa->flags & ACPI_SRAT_CPU_ENABLED) == 0)
+ return;
+ pxm = pa->proximity_domain;
+ node = setup_node(pxm);
+ if (node < 0) {
+ printk(KERN_ERR "SRAT: Too many proximity domains %x\n", pxm);
+ bad_srat();
+ return;
+ }
+
+ apic_id = pa->apic_id;
+ apicid_to_node[apic_id] = node;
+ node_set(node, cpu_nodes_parsed);
+ acpi_numa = 1;
+ printk(KERN_INFO "SRAT: PXM %u -> APIC %u -> Node %u\n",
+ pxm, apic_id, node);
+}
+
/* Callback for Proximity Domain -> LAPIC mapping */
void __init
acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa)
@@ -144,6 +176,7 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa)
else
apic_id = pa->apic_id;
apicid_to_node[apic_id] = node;
+ node_set(node, cpu_nodes_parsed);
acpi_numa = 1;
printk(KERN_INFO "SRAT: PXM %u -> APIC %u -> Node %u\n",
pxm, apic_id, node);
@@ -372,7 +405,8 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end)
return -1;
}
- node_possible_map = nodes_parsed;
+ /* Account for nodes with cpus and no memory */
+ nodes_or(node_possible_map, nodes_parsed, cpu_nodes_parsed);
/* Finally register nodes */
for_each_node_mask(i, node_possible_map)
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index a654d59e4483..821e97017e95 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -187,11 +187,6 @@ static void flush_tlb_others_ipi(const struct cpumask *cpumask,
cpumask, cpumask_of(smp_processor_id()));
/*
- * Make the above memory operations globally visible before
- * sending the IPI.
- */
- smp_mb();
- /*
* We have to send the IPI only to
* CPUs affected.
*/
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.