#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/mm.h>
+#include <linux/nmi.h>
#include <linux/swap.h>
#include <linux/smp.h>
#include <linux/highmem.h>
for_each_online_pgdat(pgdat) {
pgdat_resize_lock(pgdat, &flags);
for (i = 0; i < pgdat->node_spanned_pages; ++i) {
+ if (unlikely(i % MAX_ORDER_NR_PAGES == 0))
+ touch_nmi_watchdog();
page = pgdat_page_nr(pgdat, i);
total++;
if (PageHighMem(page))
}
pte = pte_offset_kernel(pmd, vaddr);
if (pgprot_val(flags))
- /* <pfn,flags> stored as-is, to permit clearing entries */
- set_pte(pte, pfn_pte(pfn, flags));
+ set_pte_present(&init_mm, vaddr, pte, pfn_pte(pfn, flags));
else
pte_clear(&init_mm, vaddr, pte);
return pte;
}
-void pmd_ctor(void *pmd, struct kmem_cache *cache, unsigned long flags)
+void pmd_ctor(struct kmem_cache *cache, void *pmd)
{
memset(pmd, 0, PTRS_PER_PMD*sizeof(pmd_t));
}
#define UNSHARED_PTRS_PER_PGD \
(SHARED_KERNEL_PMD ? USER_PTRS_PER_PGD : PTRS_PER_PGD)
+#ifdef CONFIG_X86_PAE
+/*
+ * Mop up any pmd pages which may still be attached to the pgd.
+ * Normally they will be freed by munmap/exit_mmap, but any pmd we
+ * preallocate which never got a corresponding vma will need to be
+ * freed manually.
+ */
+static void pgd_mop_up_pmds(pgd_t *pgdp)
+{
+ int i;
+
+ for(i = 0; i < UNSHARED_PTRS_PER_PGD; i++) {
+ pgd_t pgd = pgdp[i];
+
+ if (pgd_val(pgd) != 0) {
+ pmd_t *pmd = (pmd_t *)pgd_page_vaddr(pgd);
+
+ pgdp[i] = native_make_pgd(0);
+
+ paravirt_release_pd(pgd_val(pgd) >> PAGE_SHIFT);
+ pmd_free(pmd);
+ }
+ }
+}
+
+/*
+ * In PAE mode, we need to do a cr3 reload (=tlb flush) when
+ * updating the top-level pagetable entries to guarantee the
+ * processor notices the update. Since this is expensive, and
+ * all 4 top-level entries are used almost immediately in a
+ * new process's life, we just pre-populate them here.
+ *
+ * Also, if we're in a paravirt environment where the kernel pmd is
+ * not shared between pagetables (!SHARED_KERNEL_PMDS), we allocate
+ * and initialize the kernel pmds here.
+ */
+static int pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd)
+{
+ pud_t *pud;
+ unsigned long addr;
+ int i;
+
+ pud = pud_offset(pgd, 0);
+ for (addr = i = 0; i < UNSHARED_PTRS_PER_PGD;
+ i++, pud++, addr += PUD_SIZE) {
+ pmd_t *pmd = pmd_alloc_one(mm, addr);
+
+ if (!pmd) {
+ pgd_mop_up_pmds(pgd);
+ return 0;
+ }
+
+ if (i >= USER_PTRS_PER_PGD)
+ memcpy(pmd, (pmd_t *)pgd_page_vaddr(swapper_pg_dir[i]),
+ sizeof(pmd_t) * PTRS_PER_PMD);
+
+ pud_populate(mm, pud, pmd);
+ }
+
+ return 1;
+}
+#else /* !CONFIG_X86_PAE */
+/* No need to prepopulate any pagetable entries in non-PAE modes. */
+static int pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd)
+{
+ return 1;
+}
+
+static void pgd_mop_up_pmds(pgd_t *pgd)
+{
+}
+#endif /* CONFIG_X86_PAE */
+
/* If we allocate a pmd for part of the kernel address space, then
make sure its initialized with the appropriate kernel mappings.
Otherwise use a cached zeroed pmd. */
if (PTRS_PER_PMD == 1 || !pgd)
return pgd;
+ mm->pgd = pgd; /* so that alloc_pd can use it */
+
for (i = 0; i < UNSHARED_PTRS_PER_PGD; ++i) {
pmd_t *pmd = pmd_cache_alloc(i);
if (!pmd)
goto out_oom;
- paravirt_alloc_pd(__pa(pmd) >> PAGE_SHIFT);
+ paravirt_alloc_pd(mm, __pa(pmd) >> PAGE_SHIFT);
set_pgd(&pgd[i], __pgd(1 + __pa(pmd)));
}
+ if (pgd && !pgd_prepopulate_pmd(mm, pgd)) {
+ quicklist_free(0, pgd_dtor, pgd);
+ pgd = NULL;
+ }
+
return pgd;
out_oom:
pmd_cache_free(pmd, i);
}
/* in the non-PAE case, free_pgtables() clears user pgd entries */
+ pgd_mop_up_pmds(pgd);
quicklist_free(0, pgd_dtor, pgd);
}
{
quicklist_trim(0, pgd_dtor, 25, 16);
}
-