x86: simplify pageattr_64.c

simplify pageattr_64.c.

Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

1 files changed, 55 insertions, 113 deletions

diff --git a/arch/x86/mm/pageattr_64.c b/arch/x86/mm/pageattr_64.c
index 7b734ee5b7fd..8493c469f877 100644
--- a/arch/x86/mm/pageattr_64.c
+++ b/arch/x86/mm/pageattr_64.c
@@ -9,6 +9,14 @@
 #include <linux/slab.h>
 #include <linux/mm.h>
 
+void clflush_cache_range(void *addr, int size)
+{
+        int i;
+
+        for (i = 0; i < size; i += boot_cpu_data.x86_clflush_size)
+                clflush(addr+i);
+}
+
 #include <asm/processor.h>
 #include <asm/tlbflush.h>
 #include <asm/uaccess.h>
@@ -47,12 +55,6 @@ split_large_page(unsigned long address, pgprot_t prot, pgprot_t ref_prot)
         base = alloc_pages(GFP_KERNEL, 0);
         if (!base)
                 return NULL;
-        /*
-         * page_private is used to track the number of entries in
-         * the page table page have non standard attributes.
-         */
-        SetPagePrivate(base);
-        page_private(base) = 0;
 
         address = __pa(address);
         addr = address & LARGE_PAGE_MASK;
@@ -64,80 +66,13 @@ split_large_page(unsigned long address, pgprot_t prot, pgprot_t ref_prot)
         return base;
 }
 
-void clflush_cache_range(void *addr, int size)
-{
-        int i;
-
-        for (i = 0; i < size; i += boot_cpu_data.x86_clflush_size)
-                clflush(addr+i);
-}
-
-static void flush_kernel_map(void *arg)
-{
-        struct list_head *l = (struct list_head *)arg;
-        struct page *pg;
-
-        __flush_tlb_all();
-
-        /* When clflush is available always use it because it is
-           much cheaper than WBINVD. */
-        /* clflush is still broken. Disable for now. */
-        if (1 || !cpu_has_clflush) {
-                wbinvd();
-        } else {
-                list_for_each_entry(pg, l, lru) {
-                        void *addr = page_address(pg);
-
-                        clflush_cache_range(addr, PAGE_SIZE);
-                }
-        }
-}
-
-static inline void flush_map(struct list_head *l)
-{
-        on_each_cpu(flush_kernel_map, l, 1, 1);
-}
-
-static LIST_HEAD(deferred_pages); /* protected by init_mm.mmap_sem */
-
-static inline void save_page(struct page *fpage)
-{
-        if (!test_and_set_bit(PG_arch_1, &fpage->flags))
-                list_add(&fpage->lru, &deferred_pages);
-}
-
-/*
- * No more special protections in this 2/4MB area - revert to a
- * large page again.
- */
-static void revert_page(unsigned long address, pgprot_t ref_prot)
-{
-        unsigned long pfn;
-        pgd_t *pgd;
-        pud_t *pud;
-        pmd_t *pmd;
-        pte_t large_pte;
-
-        pgd = pgd_offset_k(address);
-        BUG_ON(pgd_none(*pgd));
-        pud = pud_offset(pgd, address);
-        BUG_ON(pud_none(*pud));
-        pmd = pmd_offset(pud, address);
-        BUG_ON(pmd_val(*pmd) & _PAGE_PSE);
-        pfn = (__pa(address) & LARGE_PAGE_MASK) >> PAGE_SHIFT;
-        large_pte = pfn_pte(pfn, ref_prot);
-        large_pte = pte_mkhuge(large_pte);
-
-        set_pte((pte_t *)pmd, large_pte);
-}
-
 static int
 __change_page_attr(unsigned long address, unsigned long pfn, pgprot_t prot,
                    pgprot_t ref_prot)
 {
         struct page *kpte_page;
-        pgprot_t ref_prot2;
         pte_t *kpte;
+        pgprot_t ref_prot2, oldprot;
         int level;
 
         kpte = lookup_address(address, &level);
@@ -145,8 +80,12 @@ __change_page_attr(unsigned long address, unsigned long pfn, pgprot_t prot,
                 return 0;
 
         kpte_page = virt_to_page(kpte);
+        oldprot = pte_pgprot(*kpte);
         BUG_ON(PageLRU(kpte_page));
         BUG_ON(PageCompound(kpte_page));
+        ref_prot = canon_pgprot(ref_prot);
+        prot = canon_pgprot(prot);
+
         if (pgprot_val(prot) != pgprot_val(ref_prot)) {
                 if (level == 4) {
                         set_pte(kpte, pfn_pte(pfn, prot));
@@ -165,38 +104,29 @@ __change_page_attr(unsigned long address, unsigned long pfn, pgprot_t prot,
                         set_pte(kpte, mk_pte(split, ref_prot2));
                         kpte_page = split;
                 }
-                page_private(kpte_page)++;
         } else {
                 if (level == 4) {
                         set_pte(kpte, pfn_pte(pfn, ref_prot));
-                        BUG_ON(page_private(kpte_page) == 0);
-                        page_private(kpte_page)--;
                 } else
                         BUG();
         }
 
-        /* on x86-64 the direct mapping set at boot is not using 4k pages */
-        BUG_ON(PageReserved(kpte_page));
-
-        save_page(kpte_page);
-        if (page_private(kpte_page) == 0)
-                revert_page(address, ref_prot);
         return 0;
 }
 
-/*
- * Change the page attributes of an page in the linear mapping.
- *
- * This should be used when a page is mapped with a different caching policy
- * than write-back somewhere - some CPUs do not like it when mappings with
- * different caching policies exist. This changes the page attributes of the
- * in kernel linear mapping too.
+/**
+ * change_page_attr_addr - Change page table attributes in linear mapping
+ * @address: Virtual address in linear mapping.
+ * @numpages: Number of pages to change
+ * @prot:    New page table attribute (PAGE_*)
  *
- * The caller needs to ensure that there are no conflicting mappings elsewhere.
- * This function only deals with the kernel linear map.
+ * Change page attributes of a page in the direct mapping. This is a variant
+ * of change_page_attr() that also works on memory holes that do not have
+ * mem_map entry (pfn_valid() is false).
  *
- * Caller must call global_flush_tlb() after this.
+ * See change_page_attr() documentation for more details.
  */
+
 int change_page_attr_addr(unsigned long address, int numpages, pgprot_t prot)
 {
         int err = 0, kernel_map = 0, i;
@@ -236,7 +166,26 @@ int change_page_attr_addr(unsigned long address, int numpages, pgprot_t prot)
         return err;
 }
 
-/* Don't call this for MMIO areas that may not have a mem_map entry */
+/**
+ * change_page_attr - Change page table attributes in the linear mapping.
+ * @page: First page to change
+ * @numpages: Number of pages to change
+ * @prot: New protection/caching type (PAGE_*)
+ *
+ * Returns 0 on success, otherwise a negated errno.
+ *
+ * This should be used when a page is mapped with a different caching policy
+ * than write-back somewhere - some CPUs do not like it when mappings with
+ * different caching policies exist. This changes the page attributes of the
+ * in kernel linear mapping too.
+ *
+ * Caller must call global_flush_tlb() later to make the changes active.
+ *
+ * The caller needs to ensure that there are no conflicting mappings elsewhere
+ * (e.g. in user space) * This function only deals with the kernel linear map.
+ *
+ * For MMIO areas without mem_map use change_page_attr_addr() instead.
+ */
 int change_page_attr(struct page *page, int numpages, pgprot_t prot)
 {
         unsigned long addr = (unsigned long)page_address(page);
@@ -245,29 +194,22 @@ int change_page_attr(struct page *page, int numpages, pgprot_t prot)
 }
 EXPORT_SYMBOL(change_page_attr);
 
-void global_flush_tlb(void)
+static void flush_kernel_map(void *arg)
 {
-        struct page *pg, *next;
-        struct list_head l;
-
         /*
-         * Write-protect the semaphore, to exclude two contexts
-         * doing a list_replace_init() call in parallel and to
-         * exclude new additions to the deferred_pages list:
+         * Flush all to work around Errata in early athlons regarding
+         * large page flushing.
          */
-        down_write(&init_mm.mmap_sem);
-        list_replace_init(&deferred_pages, &l);
-        up_write(&init_mm.mmap_sem);
+        __flush_tlb_all();
 
-        flush_map(&l);
+        if (boot_cpu_data.x86_model >= 4)
+                wbinvd();
+}
 
-        list_for_each_entry_safe(pg, next, &l, lru) {
-                list_del(&pg->lru);
-                clear_bit(PG_arch_1, &pg->flags);
-                if (page_private(pg) != 0)
-                        continue;
-                ClearPagePrivate(pg);
-                __free_page(pg);
-        }
+void global_flush_tlb(void)
+{
+        BUG_ON(irqs_disabled());
+
+        on_each_cpu(flush_kernel_map, NULL, 1, 1);
 }
 EXPORT_SYMBOL(global_flush_tlb);