[PATCH 2 of 7] x86: add common mm/pgtable.c

From: Jeremy Fitzhardinge
Date: Sat Feb 02 2008 - 04:09:53 EST


Add a common arch/x86/mm/pgtable.c file for common pagetable functions.

Signed-off-by: Jeremy Fitzhardinge <jeremy@xxxxxxxxxxxxx>
---
arch/x86/mm/Makefile_32 | 2
arch/x86/mm/Makefile_64 | 2
arch/x86/mm/pgtable.c | 234 ++++++++++++++++++++++++++++++++++++++++++
arch/x86/mm/pgtable_32.c | 185 ---------------------------------
include/asm-x86/pgalloc.h | 19 +++
include/asm-x86/pgalloc_32.h | 11 -
include/asm-x86/pgalloc_64.h | 61 ----------
7 files changed, 255 insertions(+), 259 deletions(-)

diff --git a/arch/x86/mm/Makefile_32 b/arch/x86/mm/Makefile_32
--- a/arch/x86/mm/Makefile_32
+++ b/arch/x86/mm/Makefile_32
@@ -2,7 +2,7 @@
# Makefile for the linux i386-specific parts of the memory manager.
#

-obj-y := init_32.o pgtable_32.o fault.o ioremap.o extable.o pageattr.o mmap.o
+obj-y := init_32.o pgtable.o pgtable_32.o fault.o ioremap.o extable.o pageattr.o mmap.o

obj-$(CONFIG_NUMA) += discontig_32.o
obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o
diff --git a/arch/x86/mm/Makefile_64 b/arch/x86/mm/Makefile_64
--- a/arch/x86/mm/Makefile_64
+++ b/arch/x86/mm/Makefile_64
@@ -2,7 +2,7 @@
# Makefile for the linux x86_64-specific parts of the memory manager.
#

-obj-y := init_64.o fault.o ioremap.o extable.o pageattr.o mmap.o
+obj-y := init_64.o fault.o ioremap.o extable.o pageattr.o pgtable.o mmap.o
obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o
obj-$(CONFIG_NUMA) += numa_64.o
obj-$(CONFIG_K8_NUMA) += k8topology_64.o
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
new file mode 100644
--- /dev/null
+++ b/arch/x86/mm/pgtable.c
@@ -0,0 +1,235 @@
+#include <asm/pgalloc.h>
+#include <asm/tlb.h>
+
+pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
+{
+ return (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
+}
+
+struct page *pte_alloc_one(struct mm_struct *mm, unsigned long address)
+{
+ struct page *pte;
+
+#ifdef CONFIG_HIGHPTE
+ pte = alloc_pages(GFP_KERNEL|__GFP_HIGHMEM|__GFP_REPEAT|__GFP_ZERO, 0);
+#else
+ pte = alloc_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO, 0);
+#endif
+ return pte;
+}
+
+#ifdef CONFIG_X86_64
+static inline void pgd_list_add(pgd_t *pgd)
+{
+ struct page *page = virt_to_page(pgd);
+
+ spin_lock(&pgd_lock);
+ list_add(&page->lru, &pgd_list);
+ spin_unlock(&pgd_lock);
+}
+
+static inline void pgd_list_del(pgd_t *pgd)
+{
+ struct page *page = virt_to_page(pgd);
+
+ spin_lock(&pgd_lock);
+ list_del(&page->lru);
+ spin_unlock(&pgd_lock);
+}
+
+pgd_t *pgd_alloc(struct mm_struct *mm)
+{
+ unsigned boundary;
+ pgd_t *pgd = (pgd_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT);
+ if (!pgd)
+ return NULL;
+ pgd_list_add(pgd);
+ /*
+ * Copy kernel pointers in from init.
+ * Could keep a freelist or slab cache of those because the kernel
+ * part never changes.
+ */
+ boundary = pgd_index(__PAGE_OFFSET);
+ memset(pgd, 0, boundary * sizeof(pgd_t));
+ memcpy(pgd + boundary,
+ init_level4_pgt + boundary,
+ (PTRS_PER_PGD - boundary) * sizeof(pgd_t));
+ return pgd;
+}
+
+void pgd_free(pgd_t *pgd)
+{
+ BUG_ON((unsigned long)pgd & (PAGE_SIZE-1));
+ pgd_list_del(pgd);
+ free_page((unsigned long)pgd);
+}
+
+#else
+/*
+ * List of all pgd's needed for non-PAE so it can invalidate entries
+ * in both cached and uncached pgd's; not needed for PAE since the
+ * kernel pmd is shared. If PAE were not to share the pmd a similar
+ * tactic would be needed. This is essentially codepath-based locking
+ * against pageattr.c; it is the unique case in which a valid change
+ * of kernel pagetables can't be lazily synchronized by vmalloc faults.
+ * vmalloc faults work because attached pagetables are never freed.
+ * -- wli
+ */
+static inline void pgd_list_add(pgd_t *pgd)
+{
+ struct page *page = virt_to_page(pgd);
+
+ list_add(&page->lru, &pgd_list);
+}
+
+static inline void pgd_list_del(pgd_t *pgd)
+{
+ struct page *page = virt_to_page(pgd);
+
+ list_del(&page->lru);
+}
+
+#define UNSHARED_PTRS_PER_PGD \
+ (SHARED_KERNEL_PMD ? USER_PTRS_PER_PGD : PTRS_PER_PGD)
+
+static void pgd_ctor(void *p)
+{
+ pgd_t *pgd = p;
+ unsigned long flags;
+
+ /* Clear usermode parts of PGD */
+ memset(pgd, 0, USER_PTRS_PER_PGD*sizeof(pgd_t));
+
+ spin_lock_irqsave(&pgd_lock, flags);
+
+ /* If the pgd points to a shared pagetable level (either the
+ ptes in non-PAE, or shared PMD in PAE), then just copy the
+ references from swapper_pg_dir. */
+ if (PAGETABLE_LEVELS == 2 ||
+ (PAGETABLE_LEVELS == 3 && SHARED_KERNEL_PMD)) {
+ clone_pgd_range(pgd + USER_PTRS_PER_PGD,
+ swapper_pg_dir + USER_PTRS_PER_PGD,
+ KERNEL_PGD_PTRS);
+ paravirt_alloc_pd_clone(__pa(pgd) >> PAGE_SHIFT,
+ __pa(swapper_pg_dir) >> PAGE_SHIFT,
+ USER_PTRS_PER_PGD,
+ KERNEL_PGD_PTRS);
+ }
+
+ /* list required to sync kernel mapping updates */
+ if (!SHARED_KERNEL_PMD)
+ pgd_list_add(pgd);
+
+ spin_unlock_irqrestore(&pgd_lock, flags);
+}
+
+static void pgd_dtor(void *pgd)
+{
+ unsigned long flags; /* can be called from interrupt context */
+
+ if (SHARED_KERNEL_PMD)
+ return;
+
+ spin_lock_irqsave(&pgd_lock, flags);
+ pgd_list_del(pgd);
+ spin_unlock_irqrestore(&pgd_lock, flags);
+}
+
+#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 */
+
+pgd_t *pgd_alloc(struct mm_struct *mm)
+{
+ pgd_t *pgd = quicklist_alloc(0, GFP_KERNEL, pgd_ctor);
+
+ mm->pgd = pgd; /* so that alloc_pd can use it */
+
+ if (pgd && !pgd_prepopulate_pmd(mm, pgd)) {
+ quicklist_free(0, pgd_dtor, pgd);
+ pgd = NULL;
+ }
+
+ return pgd;
+}
+
+void pgd_free(pgd_t *pgd)
+{
+ pgd_mop_up_pmds(pgd);
+ quicklist_free(0, pgd_dtor, pgd);
+}
+
+void check_pgt_cache(void)
+{
+ quicklist_trim(0, pgd_dtor, 25, 16);
+}
+#endif
diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c
--- a/arch/x86/mm/pgtable_32.c
+++ b/arch/x86/mm/pgtable_32.c
@@ -178,191 +178,6 @@
__VMALLOC_RESERVE += reserve;
}

-pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
-{
- return (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
-}
-
-struct page *pte_alloc_one(struct mm_struct *mm, unsigned long address)
-{
- struct page *pte;
-
-#ifdef CONFIG_HIGHPTE
- pte = alloc_pages(GFP_KERNEL|__GFP_HIGHMEM|__GFP_REPEAT|__GFP_ZERO, 0);
-#else
- pte = alloc_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO, 0);
-#endif
- return pte;
-}
-
-/*
- * List of all pgd's needed for non-PAE so it can invalidate entries
- * in both cached and uncached pgd's; not needed for PAE since the
- * kernel pmd is shared. If PAE were not to share the pmd a similar
- * tactic would be needed. This is essentially codepath-based locking
- * against pageattr.c; it is the unique case in which a valid change
- * of kernel pagetables can't be lazily synchronized by vmalloc faults.
- * vmalloc faults work because attached pagetables are never freed.
- * -- wli
- */
-static inline void pgd_list_add(pgd_t *pgd)
-{
- struct page *page = virt_to_page(pgd);
-
- list_add(&page->lru, &pgd_list);
-}
-
-static inline void pgd_list_del(pgd_t *pgd)
-{
- struct page *page = virt_to_page(pgd);
-
- list_del(&page->lru);
-}
-
-#define UNSHARED_PTRS_PER_PGD \
- (SHARED_KERNEL_PMD ? USER_PTRS_PER_PGD : PTRS_PER_PGD)
-
-static void pgd_ctor(void *p)
-{
- pgd_t *pgd = p;
- unsigned long flags;
-
- /* Clear usermode parts of PGD */
- memset(pgd, 0, USER_PTRS_PER_PGD*sizeof(pgd_t));
-
- spin_lock_irqsave(&pgd_lock, flags);
-
- /* If the pgd points to a shared pagetable level (either the
- ptes in non-PAE, or shared PMD in PAE), then just copy the
- references from swapper_pg_dir. */
- if (PAGETABLE_LEVELS == 2 ||
- (PAGETABLE_LEVELS == 3 && SHARED_KERNEL_PMD)) {
- clone_pgd_range(pgd + USER_PTRS_PER_PGD,
- swapper_pg_dir + USER_PTRS_PER_PGD,
- KERNEL_PGD_PTRS);
- paravirt_alloc_pd_clone(__pa(pgd) >> PAGE_SHIFT,
- __pa(swapper_pg_dir) >> PAGE_SHIFT,
- USER_PTRS_PER_PGD,
- KERNEL_PGD_PTRS);
- }
-
- /* list required to sync kernel mapping updates */
- if (!SHARED_KERNEL_PMD)
- pgd_list_add(pgd);
-
- spin_unlock_irqrestore(&pgd_lock, flags);
-}
-
-static void pgd_dtor(void *pgd)
-{
- unsigned long flags; /* can be called from interrupt context */
-
- if (SHARED_KERNEL_PMD)
- return;
-
- spin_lock_irqsave(&pgd_lock, flags);
- pgd_list_del(pgd);
- spin_unlock_irqrestore(&pgd_lock, flags);
-}
-
-#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 */
-
-pgd_t *pgd_alloc(struct mm_struct *mm)
-{
- pgd_t *pgd = quicklist_alloc(0, GFP_KERNEL, pgd_ctor);
-
- mm->pgd = pgd; /* so that alloc_pd can use it */
-
- if (pgd && !pgd_prepopulate_pmd(mm, pgd)) {
- quicklist_free(0, pgd_dtor, pgd);
- pgd = NULL;
- }
-
- return pgd;
-}
-
-void pgd_free(pgd_t *pgd)
-{
- pgd_mop_up_pmds(pgd);
- quicklist_free(0, pgd_dtor, pgd);
-}
-
-void check_pgt_cache(void)
-{
- quicklist_trim(0, pgd_dtor, 25, 16);
-}
-
void __pte_free_tlb(struct mmu_gather *tlb, struct page *pte)
{
paravirt_release_pt(page_to_pfn(pte));
diff --git a/include/asm-x86/pgalloc.h b/include/asm-x86/pgalloc.h
--- a/include/asm-x86/pgalloc.h
+++ b/include/asm-x86/pgalloc.h
@@ -1,5 +1,23 @@
+#ifndef _ASM_X86_PGALLOC_H
+#define _ASM_X86_PGALLOC_H
+
+#include <linux/threads.h>
+#include <linux/mm.h> /* for struct page */
+#include <linux/pagemap.h>
+
+/*
+ * Allocate and free page tables.
+ */
+pgd_t *pgd_alloc(struct mm_struct *mm);
+void pgd_free(pgd_t *pgd);
+
+pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address);
+struct page *pte_alloc_one(struct mm_struct *mm, unsigned long address);
+
#ifdef CONFIG_X86_32
# include "pgalloc_32.h"
#else
# include "pgalloc_64.h"
#endif
+
+#endif /* _ASM_X86_PGALLOC_H */
diff --git a/include/asm-x86/pgalloc_32.h b/include/asm-x86/pgalloc_32.h
--- a/include/asm-x86/pgalloc_32.h
+++ b/include/asm-x86/pgalloc_32.h
@@ -1,11 +1,5 @@
#ifndef _I386_PGALLOC_H
#define _I386_PGALLOC_H
-
-#include <linux/threads.h>
-#include <linux/mm.h> /* for struct page */
-#include <linux/pagemap.h>
-#include <asm/tlb.h>
-#include <asm-generic/tlb.h>

#ifdef CONFIG_PARAVIRT
#include <asm/paravirt.h>
@@ -35,11 +29,6 @@
/*
* Allocate and free page tables.
*/
-extern pgd_t *pgd_alloc(struct mm_struct *);
-extern void pgd_free(pgd_t *pgd);
-
-extern pte_t *pte_alloc_one_kernel(struct mm_struct *, unsigned long);
-extern struct page *pte_alloc_one(struct mm_struct *, unsigned long);

static inline void pte_free_kernel(pte_t *pte)
{
diff --git a/include/asm-x86/pgalloc_64.h b/include/asm-x86/pgalloc_64.h
--- a/include/asm-x86/pgalloc_64.h
+++ b/include/asm-x86/pgalloc_64.h
@@ -1,8 +1,6 @@
#ifndef _X86_64_PGALLOC_H
#define _X86_64_PGALLOC_H

-#include <linux/threads.h>
-#include <linux/mm.h>
#include <asm/pda.h>

static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte)
@@ -47,64 +45,6 @@
free_page((unsigned long)pud);
}

-static inline void pgd_list_add(pgd_t *pgd)
-{
- struct page *page = virt_to_page(pgd);
-
- spin_lock(&pgd_lock);
- list_add(&page->lru, &pgd_list);
- spin_unlock(&pgd_lock);
-}
-
-static inline void pgd_list_del(pgd_t *pgd)
-{
- struct page *page = virt_to_page(pgd);
-
- spin_lock(&pgd_lock);
- list_del(&page->lru);
- spin_unlock(&pgd_lock);
-}
-
-static inline pgd_t *pgd_alloc(struct mm_struct *mm)
-{
- unsigned boundary;
- pgd_t *pgd = (pgd_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT);
- if (!pgd)
- return NULL;
- pgd_list_add(pgd);
- /*
- * Copy kernel pointers in from init.
- * Could keep a freelist or slab cache of those because the kernel
- * part never changes.
- */
- boundary = pgd_index(__PAGE_OFFSET);
- memset(pgd, 0, boundary * sizeof(pgd_t));
- memcpy(pgd + boundary,
- init_level4_pgt + boundary,
- (PTRS_PER_PGD - boundary) * sizeof(pgd_t));
- return pgd;
-}
-
-static inline void pgd_free(pgd_t *pgd)
-{
- BUG_ON((unsigned long)pgd & (PAGE_SIZE-1));
- pgd_list_del(pgd);
- free_page((unsigned long)pgd);
-}
-
-static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
-{
- return (pte_t *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT);
-}
-
-static inline struct page *pte_alloc_one(struct mm_struct *mm, unsigned long address)
-{
- void *p = (void *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT);
- if (!p)
- return NULL;
- return virt_to_page(p);
-}
-
/* Should really implement gc for free page table pages. This could be
done with a reference count in struct page. */



--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/